Patent Application
20230220612
The present invention relates to apparel finishing and, more specifically, the use of a laser in the finishing of garments, especially denim including jeans, shirts, shorts, jackets, vests, and skirts, to obtain a faded, distressed, washed, or worn finish or appearance.
In 1853, during the California Gold Rush, Levi Strauss, a 24-year-old German immigrant, left New York for San Francisco with a small supply of dry goods with the intention of opening a branch of his brother's New York dry goods business. Shortly after arriving in San Francisco, Mr. Strauss realized that the miners and prospectors (called the “forty niners”) needed pants strong enough to last through the hard work conditions they endured. So, Mr. Strauss developed the now familiar jeans which he sold to the miners. The company he founded, Levi Strauss & Co., still sells jeans and is the most widely known jeans brand in the world. Levi's is a trademark of Levi Strauss & Co. or LS&Co.
Though jeans at the time of the Gold Rush were used as work clothes, jeans have evolved to be fashionably worn everyday by men and women, showing up on billboards, television commercials, and fashion runways. Fashion is one of the largest consumer industries in the U.S. and around the world. Jeans and related apparel are a significant segment of the industry.
As fashion, people are concerned with the appearance of their jeans. Many people desire a faded or worn blue jeans look. In the past, jeans became faded or distressed through normal wash and wear. The apparel industry recognized people's desire for the worn blue jeans look and began producing jeans and apparel with a variety of wear patterns. The wear patterns have become part of the jeans style and fashion. Some examples of wear patterns include combs or honeycombs, whiskers, stacks, and train tracks.
Despite the widespread success jeans have enjoyed, the process to produce modern jeans with wear patterns takes processing time, has relatively high processing cost, and is resource intensive. A typical process to produce jeans uses significant amounts of water, chemicals (e.g., bleaching or oxidizing agents), ozone, enzymes, and pumice stone. For example, it may take about twenty to sixty liters of water to finish each pair of jeans.
Therefore, there is a need for an improved process for finishing jeans that reduces environmental impact, processing time, and processing costs, while maintaining the look and style of traditional finishing techniques. There is a need for a tool to create and preview patterns on jeans before laser finishing.
A system automatically generates apparel collection imagery from user-provided imagery. The user-provided imagery includes images of people wearing one or more garments. The system uses segmenting analysis to analyze the user-provided image to identify locations of the garment. From the locations of the garments, the system can determine which garments from an apparel collection can be used to replace those in the user-provided imagery. The system uses pose estimation on the user-provided imagery and modifies a preview image of a replacement garment from the collection. This modified replacement garment image is used to replace the garment in the user-provided imagery.
A tool allows a user to create new designs for apparel and preview these designs before manufacture. Software and lasers are used in finishing apparel to produce a desired wear pattern or other design. Based on a laser input file with a pattern, a laser will burn the pattern onto apparel. With the tool, the user will be able to create, make changes, and view images of a design, in real time, before burning by a laser. Input to the tool includes fabric template images, laser input files, and damage input. The tool allows adding of tinting and adjusting of intensity and bright point. The user can also move, rotate, scale, and warp the image input.
In an implementation, a method for automated apparel collection imagery includes: providing a garment previewing tool that allows previewing on a computer screen of a garment base customized by a user with a finishing pattern, where the garment previewing tool includes: providing an option for the user to select the garment base and upon the user's selection, showing a first garment preview image on the computer screen including a jeans base image for the selected garment base, providing an option for the user to select a wear pattern from a menu of wear patterns, where each wear pattern is associated with a laser input file to be used by a laser to produce that wear pattern onto a jeans garment, and after the wear pattern is selected, allowing the user to select the wear pattern and modify a sizing or position of the wear pattern relative to the jeans base image; in response to a selection from the user to modify the sizing or positioning of the wear pattern relative to the jeans base image, creating a garment preview image including the jeans base image and selected wear pattern, with modified sizing or modified positioning, or a combination. The method includes receiving a user-provided image, where the user-provided image includes one or more persons captured in the user-provided image and the user-provided image has at least one location suitable for including a jeans garment; analyzing the user-provided image using segmenting analysis to identify one or more locations in the user-provided image where garments may be placed, where the one or more locations includes a first location identifies a location suitable for including a jeans garment. The method includes for the first location, determining a first pose of a person at the first location captured in the user-provided image; modifying the garment preview image to correct for the first pose captured in the user-provided image; and replacing at the first location the modified garment preview image. The method includes providing a target garment corresponding to the garment base selected by the user; and based on a laser input file associated with a selected wear pattern with modified sizing or modified positioning, or a combination, using a laser to create a finishing pattern on an outer surface of the target garment.
The method includes replacing more than one item in the user-provided image. The method includes: for a second garment created using the garment previewing tool, creating a second garment preview image including a second jeans base image and second selected wear pattern, with modified sizing or modified positioning, or a combination; for a second location, determining a second pose of a person at the second location captured in the user-provided image; modifying the second garment preview image to correct for the second pose captured in the user-provided image; and replacing at the second location the modified second garment preview image. The method includes for a second location, determining a second location in the user-provided image where an accessory or clothing top may be placed; and replacing at the second location an accessory or clothing top.
The method includes pose estimation techniques. The method includes where determining the first pose includes detecting an articulation point corresponding to a knee area of the person captured in the user-provided image and the modified garment preview image includes an adjustment for the articulation point.
The user-provided image may include various objects. The method includes an advertisement or store signage.
The method includes a jeans garment. The method includes where a method of manufacturing the target garment includes: assembling the target garment from fabric panels of a woven first material including a warp including indigo ring-dyed cotton yarn, where the fabric panels are sewn together using thread. The method includes where based on the laser input file, the laser removes selected amounts of material from the surface of a material of the target garment at different pixel locations of the garment, and for lighter pixel locations of the finishing pattern, a greater amount of the indigo ring-dyed cotton warp yarn is removed, while for darker pixel locations of the finishing pattern, a lesser amount of the indigo ring-dyed cotton warp yarn is removed. The method includes where when using the laser to create a finishing pattern, different laser levels are obtained by varying an output of the laser beam by altering a characteristic of the laser including at least one of a frequency, period, pulse width, power, duty cycle, or burning speed. The method includes where the target garment is made of at least one of a twill material or a cotton twill material. The method includes where the garment base corresponds to a base fit fabric and the base fit fabric includes known characteristics regarding the suitability of the base fit fabric for finishing using the laser.
Other objects, features, and advantages of the present invention will become apparent upon consideration of the following detailed description and the accompanying drawings, in which like reference designations represent like features throughout the figures.
Some examples of natural fibers include cotton, flax, hemp, sisal, jute, kenaf, and coconut; fibers from animal sources include silk, wool, cashmere, and mohair. Some examples of synthetic fibers include polyester, nylon, spandex or elastane, and other polymers. Some examples of semisynthetic fibers include rayon, viscose, modal, and lyocell, which are made from a regenerated cellulose fiber. A fabric can be a natural fiber alone (e.g., cotton), a synthetic fiber alone (e.g., polyester alone), a blend of natural and synthetic fibers (e.g., cotton and polyester blend, or cotton and spandex), or a blend of natural and semisynthetic fibers, or any combination of these or other fibers.
For jeans, the fabric is typically a denim, which is a sturdy cotton warp-faced textile in which a weft passes under two or more warp threads. This twill weaving produces a diagonal ribbing. The yarns (e.g., warp yarns) are dyed using an indigo or blue dye, which is characteristic of blue jeans.
Although this patent describes the apparel processing and finishing with respect to jeans, the invention is not limited jeans or denim products, such as shirts, shorts, jackets, vests, and skirts. The techniques and approaches described are applicable to other apparel and products, including non-denim products and products made from knit materials. Some examples include T-shirts, sweaters, coats, sweatshirts (e.g., hoodies), casual wear, athletic wear, outerwear, dresses, evening wear, sleepwear, loungewear, underwear, socks, bags, backpacks, uniforms, umbrellas, swimwear, bed sheets, scarves, and many others.
A manufacturer creates a design 115 (design I) of its product. The design can be for a particular type of clothing or garment (e.g., men's or women's jean, or jacket), sizing of the garment (e.g., small, medium, or large, or waist size and inseam length), or other design feature. The design can be specified by a pattern or cut used to form pieces of the pattern. A fabric is selected and patterned and cut 118 based on the design. The pattern pieces are assembled together 121 into the garment, typically by sewing, but can be joined together using other techniques (e.g., rivets, buttons, zipper, hoop and loop, adhesives, or other techniques and structures to join fabrics and materials together).
Some garments can be complete after assembly and ready for sale. However, other garments are unfinished 122 and have additional finishing 124, which includes laser finishing. The finishing may include tinting, washing, softening, and fixing. For distressed denim products, the finishing can include using a laser to produce a wear pattern according to a design 127 (design II). Some additional details of laser finishing are described in U.S. patent application 62/377,447, filed Aug. 19, 2016, and Ser. No. 15/682,507, filed Aug. 21, 2017, issued as U.S. Pat. No. 10,051,905 on Aug. 21, 2018, which are incorporated by reference along with all other references cited in this application. U.S. patent applications 62/636,108, filed Feb. 27, 2018, and 62/715,788, filed Aug. 7, 2018, describe some specific implementations of a brief builder application and are incorporated by reference.
U.S. patent application Ser. Nos. 16/288,035, 16/288,036, 16/288,038, 16/288,042, 16/288,046, 16/288,047, 16/288,048, 16/288,050, and 16/288,054, filed Feb. 27, 2019, are incorporated by reference.
Design 127 is for postassembly aspects of a garment while design 115 is for preassembly aspects of a garment. After finishing, a finished product 130 (e.g., a pair of jeans) is complete and ready for sale. The finished product is inventoried and distributed 133, delivered to stores 136, and sold to consumers or customers 139. The consumer can buy and wear worn blue jeans without having to wear out the jeans themselves, which usually takes significant time and effort.
Traditionally, to produce distressed denim products, finishing techniques include dry abrasion, wet processing, oxidation, or other techniques, or combinations of these, to accelerate wear of the material in order to produce a desired wear pattern. Dry abrasion can include sandblasting or using sandpaper. For example, some portions or localized areas of the fabric are sanded to abrade the fabric surface. Wet processing can include washing in water, washing with oxidizers (e.g., bleach, peroxide, ozone, or potassium permanganate), spraying with oxidizers, washing with abrasives (e.g., pumice, stone, or grit).
These traditional finishing approaches take time, incur expense, and impact the environment by utilizing resources and producing waste. It is desirable to reduce water and chemical usage, which can include eliminating the use agents such as potassium permanganate and pumice. An alternative to these traditional finishing approaches is laser finishing.
The laser is controlled by an input file 210 and control software 213 to emit a laser beam onto fabric at a particular position or location at a specific power level for a specific amount of time. Further, the power of the laser beam can be varied according to a waveform such as a pulse wave with a particular frequency, period, pulse width, or other characteristic. Some aspects of the laser that can be controlled include the duty cycle, frequency, marking or burning speed, and other parameters.
The duty cycle is a percentage of laser emission time. Some examples of duty cycle percentages include 40, 45, 50, 55, 60, 80, and 100 percent. The frequency is the laser pulse frequency. A low frequency might be, for example, 5 kilohertz, while a high frequency might be, for example, 25 kilohertz. Generally, lower frequencies will have higher surface penetration than high frequencies, which has less surface penetration.
The laser acts like a printer and “prints,” “marks,” or “burns” a wear pattern (specified by input file 210) onto the garment. The fabric that is exposed to the laser beam (e.g., infrared beam) changes color, lightening the fabric at a specified position by a certain amount based on the laser power, time of exposure, and waveform used. The laser continues from position to position until the wear pattern is completely printed on the garment.
In a specific implementation, the laser has a resolution of about 34 dots per inch (dpi), which on the garment is about 0.7 millimeters per pixel. The technique described in this patent is not dependent on the laser's resolution, and will work with lasers have more or less resolution than 34 dots per inch. For example, the laser can have a resolution of 10, 15, 20, 25, 30, 40, 50, 60, 72, 80, 96, 100, 120, 150, 200, 300, or 600 dots per inch, or more or less than any of these or other values. Typically, the greater the resolution, the finer the features that can be printed on the garment in a single pass. By using multiple passes (e.g., 2, 3, 4, 5, or more passes) with the laser, the effective resolution can be increased. In an implementation, multiple laser passes are used.
Jeans are dyed using an indigo dye, which results in a blue colored fabric. The blue color is caused by chromophores trapped in the fabric which reflect light as a blue color. U.S. patent application 62/433,739, filed Dec. 13, 2016, which is incorporated by reference, describes a denim material with enhanced response characteristics to laser finishing. Using a denim material made from indigo ring-dyed yarn, variations in highs and lows in indigo color shading is achieved by using a laser.
For denim, dyed yarn is used for the warp, and undyed or white yarn is typically used for the weft yarn. In some denim fabrics, the weft yarn can be dyed and have a color other than white, such as red. In the denim weave, the weft passes under two or more warp threads.
Because of the weave, one side of the fabric exposes more of the warp yarns (e.g., warp-faced side), while the other side exposes more of the weft yarns (e.g., weft-faced side). When the warp yarns are blue and weft yarns are white, a result of the weave is the warp-faced side will appear mostly blue while the reverse side, weft-faced side, will appear mostly white.
In denim, the warp is typically 100 percent cotton. But some warp yarns can be a blend with, for example, elastane to allow for warp stretch. And some yarns for other fabrics may contain other fibers, such as polyester or elastane as examples.
In an indigo ring-dyed yarn, the indigo does not fully penetrate to a core of the yarn. Rather, the indigo dye is applied at a surface of the cotton yarn and diffuses toward the interior of the yarn. So when the yarn is viewed cross-sectionally, the indigo dyed material will appear as a ring on around an outer edge of the yarn. The shading of the indigo dye will generally lighten in a gradient as a distance increases from the surface of the yarn to the center (or core) of the yarn.
During laser finishing, the laser removes a selected amount of the surface of the indigo dyed yarn (e.g., blue color) to reveal a lighter color (e.g., white color) of the inner core of the ring-dyed yarn. The more of the indigo dyed material that is removed, the lighter the color (e.g., lighter shade of blue). The more of the indigo dyed material that remains, the darker the color (e.g., deeper shade of blue). The laser can be controlled precisely to remove a desired amount of material to achieve a desired shade of blue in a desired place or position on the material.
With laser finishing, a finish can be applied (e.g., printed or burned via the laser) onto apparel (e.g., jeans and denim garments) that will appear similar to or indistinguishable from a finish obtained using traditional processing techniques (e.g., dry abrasion, wet processing, and oxidation). Laser finishing of apparel is less costly and is faster than traditional finishing techniques and also has reduced environmental impact (e.g., eliminating the use of harsh chemical agents and reducing waste).
As shown in
Finishing II can include laser finishing. Base A is lasered with different designs to obtain various final product based on base A (e.g., FP(A)1 to FP(A)i, where i is an integer). Base B is lasered with different designs to obtain various final products based on base B (e.g., FP(B)1 to FP(B)j, where j is an integer). Base C is lasered with different designs to obtain various final products based on base C (e.g., FP(C)1 to FP(C)k, where k is an integer). Each base can be used to obtain a number of different final designs. For example, the integers i, j, and k can have different values.
As described above and shown in
In an implementation, laser finishing is used to create many different finishes (each a different product) easily and quickly from the same fabric template or BFF or “blank.” For each fabric, there will be a number of base fit fabrics. These base fit fabrics are lasered to produce many different finishes, each being a different product for a product line. Laser finishing allows greater efficiency because by using fabric templates (or base fit fabrics), a single fabric or material can be used to create many different products for a product line, more than is possible with traditional processing. This reduces the inventory of different fabric and finish raw materials.
For a particular product (e.g., 511 product), there can be two different fabrics, such as base B and base C of
For example, FP(B)1 can be laser finished using different laser files (e.g., laser file 1, laser file 2, laser file 3, or others) or have different postlaser wash (e.g., postlaser wash recipe 1, postlaser wash recipe 2, postlaser wash recipe 3, or others), or any combination of these. A first product would be base fit fabric FP(B)1 lasered using laser file 1 and washed using postlaser wash recipe 1. A second product would be base fit fabric FP(B)1 lasered using laser file 2 and washed using postlaser wash recipe 1. A third product would be base fit fabric FP(B)1 lasered using laser file 2 and washed using postlaser wash recipe 2. And there can be many more products based on the same base fit fabric. Each can have a different product identifier or unique identifier, such as a different PC9 or nine-digit product code.
With laser finishing, many products or PC9s are produced for each base fit fabric or blank. Compared to traditional processing, this is a significant improvement in providing greater numbers of different products with less different fabrics and finishes (each of which in traditional processing consume resources, increasing cost, and take time). Inventory is reduced. The technique of providing base fit finishes or fabric templates for laser finishing has significant and many benefits.
A system incorporating laser finishing can include a computer to control or monitor operation, or both.
Communication network 1024 may itself be comprised of many interconnected computer systems and communication links. Communication links 1028 may be hardwire links, optical links, satellite or other wireless communications links, wave propagation links, or any other mechanisms for communication of information. Communication links 1028 may be DSL, Cable, Ethernet or other hardwire links, passive or active optical links, 3G, 3.5G, 4G and other mobility, satellite or other wireless communications links, wave propagation links, or any other mechanisms for communication of information.
Various communication protocols may be used to facilitate communication between the various systems shown in
Distributed computer network 1000 in
Client systems 1013, 1016, and 1019 typically request information from a server system which provides the information. For this reason, server systems typically have more computing and storage capacity than client systems. However, a particular computer system may act as both as a client or a server depending on whether the computer system is requesting or providing information. Additionally, although aspects of the invention have been described using a client-server environment, it should be apparent that the invention may also be embodied in a stand-alone computer system.
Server 1022 is responsible for receiving information requests from client systems 1013, 1016, and 1019, performing processing required to satisfy the requests, and for forwarding the results corresponding to the requests back to the requesting client system. The processing required to satisfy the request may be performed by server system 1022 or may alternatively be delegated to other servers connected to communication network 1024.
Client systems 1013, 1016, and 1019 enable users to access and query information stored by server system 1022. In a specific embodiment, the client systems can run as a standalone application such as a desktop application or mobile smartphone or tablet application. In another embodiment, a “Web browser” application executing on a client system enables users to select, access, retrieve, or query information stored by server system 1022. Examples of Web browsers include the Internet Explorer browser program provided by Microsoft Corporation, Firefox browser provided by Mozilla, Chrome browser provided by Google, Safari browser provided by Apple, and others.
In a client-server environment, some resources (e.g., files, music, video, or data) are stored at the client while others are stored or delivered from elsewhere in the network, such as a server, and accessible via the network (e.g., the Internet). Therefore, the user's data can be stored in the network or “cloud.” For example, the user can work on documents on a client device that are stored remotely on the cloud (e.g., server). Data on the client device can be synchronized with the cloud.
It should be understood that the present invention is not limited any computing device in a specific form factor (e.g., desktop computer form factor), but can include all types of computing devices in various form factors. A user can interface with any computing device, including smartphones, personal computers, laptops, electronic tablet devices, global positioning system (GPS) receivers, portable media players, personal digital assistants (PDAs), other network access devices, and other processing devices capable of receiving or transmitting data.
For example, in a specific implementation, the client device can be a smartphone or tablet device, such as the Apple iPhone (e.g., Apple iPhone 6), Apple iPad (e.g., Apple iPad, Apple iPad Pro, or Apple iPad mini), Apple iPod (e.g, Apple iPod Touch), Samsung Galaxy product (e.g., Galaxy S series product or Galaxy Note series product), Google Nexus and Pixel devices (e.g., Google Nexus 6, Google Nexus 7, or Google Nexus 9), and Microsoft devices (e.g., Microsoft Surface tablet). Typically, a smartphone includes a telephony portion (and associated radios) and a computer portion, which are accessible via a touch screen display.
There is nonvolatile memory to store data of the telephone portion (e.g., contacts and phone numbers) and the computer portion (e.g., application programs including a browser, pictures, games, videos, and music). The smartphone typically includes a camera (e.g., front facing camera or rear camera, or both) for taking pictures and video. For example, a smartphone or tablet can be used to take live video that can be streamed to one or more other devices.
Enclosure 1107 houses familiar computer components, some of which are not shown, such as a processor, memory, mass storage devices 1117, and the like. Mass storage devices 1117 may include mass disk drives, floppy disks, magnetic disks, optical disks, magneto-optical disks, fixed disks, hard disks, CD-ROMs, recordable CDs, DVDs, recordable DVDs (e.g., DVD-R, DVD+R, DVD-RW, DVD+RW, HD-DVD, or Blu-ray Disc), flash and other nonvolatile solid-state storage (e.g., USB flash drive or solid state drive (SSD)), battery-backed-up volatile memory, tape storage, reader, and other similar media, and combinations of these.
A computer-implemented or computer-executable version or computer program product of the invention may be embodied using, stored on, or associated with computer-readable medium. A computer-readable medium may include any medium that participates in providing instructions to one or more processors for execution. Such a medium may take many forms including, but not limited to, nonvolatile, volatile, and transmission media. Nonvolatile media includes, for example, flash memory, or optical or magnetic disks. Volatile media includes static or dynamic memory, such as cache memory or RAM. Transmission media includes coaxial cables, copper wire, fiber optic lines, and wires arranged in a bus. Transmission media can also take the form of electromagnetic, radio frequency, acoustic, or light waves, such as those generated during radio wave and infrared data communications.
For example, a binary, machine-executable version, of the software of the present invention may be stored or reside in RAM or cache memory, or on mass storage device 1117. The source code of the software of the present invention may also be stored or reside on mass storage device 1117 (e.g., hard disk, magnetic disk, tape, or CD-ROM). As a further example, code of the invention may be transmitted via wires, radio waves, or through a network such as the Internet.
Arrows such as 1222 represent the system bus architecture of computer system 1101. However, these arrows are illustrative of any interconnection scheme serving to link the subsystems. For example, speaker 1220 could be connected to the other subsystems through a port or have an internal direct connection to central processor 1202. The processor may include multiple processors or a multicore processor, which may permit parallel processing of information. Computer system 1101 shown in
Computer software products may be written in any of various suitable programming languages, such as C, C++, C #, Pascal, Fortran, Perl, MATLAB (from MathWorks, www.mathworks.com), SAS, SPSS, JavaScript, AJAX, Java, Python, Erlang, and Ruby on Rails. The computer software product may be an independent application with data input and data display modules. Alternatively, the computer software products may be classes that may be instantiated as distributed objects. The computer software products may also be component software such as Java Beans (from Oracle Corporation) or Enterprise Java Beans (EJB from Oracle Corporation).
An operating system for the system may be one of the Microsoft Windows® family of systems (e.g., Windows 95, 98, Me, Windows NT, Windows 2000, Windows XP, Windows XP x64 Edition, Windows Vista, Windows 7, Windows 8, Windows 10, Windows CE, Windows Mobile, Windows RT), Symbian OS, Tizen, Linux, HP-UX, UNIX, Sun OS, Solaris, Mac OS X, Apple iOS, Android, Alpha OS, AIX, IRIX32, or IRIX64. Other operating systems may be used. Microsoft Windows is a trademark of Microsoft Corporation.
Any trademarks or service marks used in this patent are property of their respective owner. Any company, product, or service names in this patent are for identification purposes only. Use of these names, logos, and brands does not imply endorsement.
Furthermore, the computer may be connected to a network and may interface to other computers using this network. The network may be an intranet, internet, or the Internet, among others. The network may be a wired network (e.g., using copper), telephone network, packet network, an optical network (e.g., using optical fiber), or a wireless network, or any combination of these. For example, data and other information may be passed between the computer and components (or steps) of a system of the invention using a wireless network using a protocol such as Wi-Fi (IEEE standards 802.11, 802.11a, 802.11b, 802.11e, 802.11g, 802.11i, 802.11n, 802.11ac, and 802.11ad, just to name a few examples), near field communication (NFC), radio-frequency identification (RFID), mobile or cellular wireless (e.g., 2G, 3G, 4G, 3GPP LTE, WiMAX, LTE, LTE Advanced, Flash-OFDM, HIPERMAN, iBurst, EDGE Evolution, UMTS, UMTS-TDD, 1xRDD, and EV-DO). For example, signals from a computer may be transferred, at least in part, wirelessly to components or other computers.
In an embodiment, with a Web browser executing on a computer workstation system, a user accesses a system on the World Wide Web (WWW) through a network such as the Internet. The Web browser is used to download Web pages or other content in various formats including HTML, XML, text, PDF, and postscript, and may be used to upload information to other parts of the system. The Web browser may use uniform resource identifiers (URLs) to identify resources on the Web and hypertext transfer protocol (HTTP) in transferring files on the Web.
In other implementations, the user accesses the system through either or both of native and nonnative applications. Native applications are locally installed on the particular computing system and are specific to the operating system or one or more hardware devices of that computing system, or a combination of these. These applications (which are sometimes also referred to as “apps”) can be updated (e.g., periodically) via a direct internet upgrade patching mechanism or through an applications store (e.g., Apple iTunes and App store, Google Play store, Windows Phone store, and Blackberry App World store).
The system can run in platform-independent, nonnative applications. For example, client can access the system through a Web application from one or more servers using a network connection with the server or servers and load the Web application in a Web browser. For example, a Web application can be downloaded from an application server over the Internet by a Web browser. Nonnative applications can also be obtained from other sources, such as a disk.
Smartphone 1301 has an enclosure that includes a screen 1303, button 1309, speaker 1311, camera 1313, and proximity sensor 1335. The screen can be a touch screen that detects and accepts input from finger touch or a stylus. The technology of the touch screen can be a resistive, capacitive, infrared grid, optical imaging, or pressure-sensitive, dispersive signal, acoustic pulse recognition, or others. The touch screen is screen and a user input device interface that acts as a mouse and keyboard of a computer.
Button 1309 is sometimes referred to as a home button and is used to exit a program and return the user to the home screen. The phone may also include other buttons (not shown) such as volume buttons and on-off button on a side. The proximity detector can detect a user's face is close to the phone, and can disable the phone screen and its touch sensor, so that there will be no false inputs from the user's face being next to screen when talking.
Tablet 1401 is similar to a smartphone. Tablet 1401 has an enclosure that includes a screen 1403, button 1409, and camera 1413. Typically the screen (e.g., touch screen) of a tablet is larger than a smartphone, usually 7, 8, 9, 10, 12, 13, or more inches (measured diagonally).
The system includes wireless components such as a mobile network connection 1527 (e.g., mobile telephone or mobile data), Wi-Fi 1529, Bluetooth 1531, GPS 1533 (e.g., detect GPS positioning), other sensors 1535 such as a proximity sensor, CPU 1537, RAM memory 1539, storage 1541 (e.g. nonvolatile memory), and battery 1543 (lithium ion or lithium polymer cell). The battery supplies power to the electronic components and is rechargeable, which allows the system to be mobile.
There is a digital design tool 1616 merchants and design can use to click and drag finish effects (e.g., laser files) and tint casts over images of base washes in order to visualize possible combinations and build the line visually before the garment finish is actually finished by the laser. The visualizations can be by rendering on a computer system, such as using three-dimensional (3D) graphics.
U.S. patent application 62/433,746, filed Dec. 13, 2016, which is incorporated by reference, describes a system and operating model of apparel manufacture with laser finishing. Laser finishing of apparel products allows an operating model that reduces finishing cost, lowers carrying costs, increases productivity, shortens time to market, be more reactive to trends, reduce product constraints, reduces lost sales and dilution, and more. Improved aspects include design, development, planning, merchandising, selling, making, and delivering. The model uses fabric templates, each of which can be used be produce a multitude of laser finishes. Operational efficiency is improved.
Designers can use the digital design tool to design products that are used to satisfy the requests in open slots 1609. Designs created using the digital design tool can be stored in a digital library 1622. Input to the digital design tool include fabric templates or blanks 1627 (e.g., base fit fabrics or BFFs), existing finishes 1633 (e.g., can be further modified by the tool 1616), and new finishes 1638. New finishes can be from designs 1641 (e.g., vintage design) captured using a laser finish software tool 1645, examples of which are described in U.S. patent applications 62/377,447, filed Aug. 19, 2016, and Ser. No. 15/682,507, filed Aug. 21, 2017. Digital library 1622 can be accessible by the region assorting and sell-in 1650. And the digital library can be used populate or satisfy the box line plan.
Preview tool 1703 can be a single tool in a toolbox or toolkit used for laser finishing of garments, or the tool can be incorporated as a feature of another tool. The preview tool allows a user such as a clothing designer to preview on a computer screen or to generate a digital representation (e.g., image file, JPEG file, BMP file, TIFF file, GIF file, PNG file, PSD file, or others) of jeans in a selected base fit fabric or fabric template 1706 with a selected laser pattern 1709 (e.g., from a laser input file). With the digital representation, the user will be able to see or preview the jeans in the selected base fit fabric as if it had been burned with the selected laser input file, without needing to actually laser or burn the jeans.
Some files are described as being of an image file type. Some examples of image file types or file formats include bitmap or raster graphics formats including IMG, TIFF, EXIF, JPEG, GIF, PNG, PBM, PGM, PPM, BMP, and RAW. The compression for the file can be lossless (e.g., TIFF) or lossy (e.g., JPEG). Other image file types or file formats include vector graphics including DXF, SVG, and the like.
Bitmaps or raster graphics are resolution dependent while vector graphics are resolution independent. Raster graphics generally cannot scale up to an arbitrary resolution without loss of apparent quality. This property contrasts with the capabilities of vector graphics, which generally easily scale up to the quality of the device rendering them.
A raster graphics image is a dot matrix data structure representing a generally rectangular grid of pixels, or points of color, viewable via a monitor, paper, or other display medium. A bitmap, such as a single-bit raster, corresponds bit-for-bit with an image displayed on a screen or output medium. A raster is characterized by the width and height of the image in pixels and by the number of bits per pixel (or color depth, which determines the number of colors it can represent).
The BMP file format is an example of a bitmap. The BMP file format, also known as bitmap image file or device independent bitmap (DIB) file format or simply a bitmap, is a raster graphics image file format used to store bitmap digital images, independently of the display device. The BMP file format is capable of storing two-dimensional digital images of arbitrary width, height, and resolution, both monochrome and color, in various color depths, and optionally with data compression, alpha channels, and color profiles.
The fabric template can be selected from a library of fabric template images 1716 or may be a new image uploaded or provided by the user. Each fabric template images is an image file of a jeans in a base fit fabric or other material. For each jeans model or fit (e.g., models or fits 311, 501, 505, 511, 515, 541, 569, 721, and others), there would be one image in each different material or base fit fabric.
The laser input file can be selected from a library of laser input files 1722 (e.g., files created from vintage jeans or from a group of designers), may be a file 1718 created by the user, or may be a file uploaded or provided by the user. For example, the user may have created the laser pattern (contained within a laser input file) manually using a graphical or image editing tool (e.g., Adobe Photoshop and similar photo editing programs). Or the laser pattern may have been created by another, such as selected from a library of laser files. The laser pattern may be generated by a computer or automated process, such as may be used to obtain a laser pattern from vintage jeans. The user will be able to see the results of a burn, make any manual changes or alterations to the pattern (such as additional changes to a vintage jean pattern in a digital image file) and preview the results again. The preview tool allows a user to make and see changes, to the user can obtain feedback faster than having to laser jeans to see the results and also avoiding unneeded waste (e.g., preliminary versions of burned jeans).
Each digital representation can be saved in a separate images, and a group or set of the images can be a called brief of collection of jeans. The preview tool can be used for merchandising, such as generating images of a proposed line of products for a particular season, and these images can be shared among members of a team to discuss any additions, changes, or deletions to a collection.
A specific version of the preview tool overlays a fabric template input file and a laser input file, and then generates an image to display them together as a representation of the laser-finished apparel. The laser input file is aligned to the garment in the fabric template input file, so that the positioning of features in the laser input file and at appropriate positions or places on the garment. The alignment may be by using alignment marks that are in the input files. The alignment may be an automated alignment or scaling, or a combination.
Brightness, intensity, opacity, blending, transparency, or other adjustable parameters for an image layer, or any combination of these, are selected or adjusted for the laser input file, so that when the laser input file is overlaid above the fabric template image, the look of the garment will appear of simulate the look of a garment had been burned by a laser using that laser input file.
Adjustable parameters such as opacity can be used to blend two or more image layers together. For example, a layer's overall opacity determines to what degree it obscures or reveals the layer beneath it. For example, a layer with 1 percent opacity appears nearly transparent, while one with 100 percent opacity appears completely opaque.
Further, a dots per inch (dpi) of the combined image can be adjusted to also more properly simulate the look of a garment more closely with a burned garment. Dots per inch refers to the number of dots in a printed inch. The more dots, the higher the quality of the print (e.g., more sharpness and detail). By reducing the dpi of the image, this will reduce the image quality, resulting a blurring of the image. In an implementation, the preview tool reduces a dpi of the combined image, to be of less dpi than the fabric template input file or the laser input file. By blurring the preview image, this results in improved simulation that corresponds better to a burned laser garment. When burning a garment, the garment material or fabric typically limits the resolution of the result to less than that of the input file.
In an implementation, the dpi of the laser input file is about 72 dpi, while the dpi of the preview image is about 34 dpi. In an implementation, the dpi of the fabric template input file and laser input file are about 36 dpi or above, while the dpi of the preview image is about 36 dpi or lower.
It should be understood that the invention is not limited to the specific flows and steps presented. A flow of the invention may have additional steps (not necessarily described in this patent), different steps which replace some of the steps presented, fewer steps or a subset of the steps presented, or steps in a different order than presented, or any combination of these. Further, the steps in other implementations of the invention may not be exactly the same as the steps presented and may be modified or altered as appropriate for a particular application or based on the data or situation.
The digital brief tool takes as input three types of digital assets 1805, fabric template input 1816, damage input 1819, and laser input file 1822. Fabric template input 1816 and laser input file 1822 are similar to the inputs for the preview tool. Damage input 1819 is an image of damage (e.g., holes, rips, shredded regions, or openings of various shapes and sizes) that can be burned by a laser into jeans. The digital brief tool overlays the damage and laser input files over the fabric template.
The user selects a fabric template input, which an image of a jeans style in a particular base fit fabric. The user can optionally select one or more damage inputs. If a damage input is selected, the damage input will be a layer that overlays the fabric template layer. As for the preview tool, the user selects a laser input file with laser pattern and overlays the fabric template layer. As the user selects the inputs, the user will be able to see in real time the inputs and any changes or updates in a preview image or brief.
After the inputs are selected, the user can select and perform one or more operations 1826 on the inputs using the digital brief tool. These operations including adding tint 1831, adjusting intensity 1834, adjusting bright point 1837, move digital asset 1842, rotate digital asset 1845, scale digital asset 1848, and warp digital asset 1852. As the user selects and performs one or more operations, the user will be able to see in real time the changes or updates in the preview image or brief.
After the fabric template input, the user can add tinting 1831. Tinting will adjust the hue of the color of the fabric template input. Tinting is representative of the tinting which can be added during the postlaser wash or finishing II, described above. The user will be able to select a tint color, and this tint color will be blended with the existing color of the fabric template input. The amount or intensity of the tinting can be increased or decreased, such as by using a slider bar.
The user can adjust intensity 1834. In an implementation, intensity adjusts a weight matrix by a percentage of each value in the array. In an implementation, intensity (or brightness) adjusts an opacity of a generated adjustment layer (see hue saturation lightness adjustment layer described below). The greater the opacity, the more opaque this layer will appear in the preview or brief image. The less the opacity, the less opaque this layer will appear in the preview or brief image; the layer will appear more transparent so that the layer beneath will show through more.
When increasing brightness, the opacity of the adjustment layer increases, and since the adjustment layer is above the fabric template input, the generated adjustment layer will become more prominent or visible, thus making this layer (which has the wear pattern) brighter. Similarly, when decreasing brightness, the opacity of the adjustment layer decreases, the generated adjustment layer will become less prominent or visible, thus making this layer (which has the wear pattern) less bright or fainter. The amount of the intensity can be increased or decreased, such as by using a slider bar.
The user can adjust bright point 1837. Bright point adjusts the effect of the laser input file on the fabric template input. In an implementation, bright point adjustment changes a midpoint of a grayscale, creating a piecewise linear mapping of the pattern file.
Increasing the bright point will increase an effect of the laser pattern (e.g., causing greater laser pattern highlights) in the laser input file on the fabric template input, while decreasing the bright point does the opposite (e.g., diminishing laser pattern highlights). The bright point adjustment can be analogous to changing a pixel time or the time that the laser stays at a particular position for a given input from the laser input file. The amount of the bright point can be increased or decreased, such as by using a slider bar.
The user can move 1842 or reposition a selected digital asset. For example, a damage input (or fabric template or laser file) may be moved to a position desired by the user. The user can rotate 1845 a selected digital asset. For example, a damage input (or fabric template or laser file) may be rotated to any angle relative to the other layers as desired by the user.
The user can scale 1848 a selected digital asset. This scaling can be locked, maintaining the original aspect ratio of the digital asset, or can be unlocked, such that the user can change the aspect ratio. The user can warp 1852 a selected digital asset. With warping, the user can adjust an aspect ratio of a portion of the digital asset differently from another portion. For example, one portion of a damage input (or fabric template or laser file) can be squished (e.g., right and left edges of image pushed toward each other) while another portion is expanded (e.g., right and left edges of image pulled away from each other).
After the user has performed selected operations 1826, the digital brief tool shows an image of the jeans with the laser finishing pattern, including any tinting, damage, or other adjustments, as created by the user. This image can be saved and viewed again later. A user can create multiple designs, and these can be saved together as part of a collection.
To obtain a final result, which is the final image of the jeans with laser finishing pattern, a laser pattern mask is combined with the base image and HSL adjustment layer. A resulting combination will be based on intensity and bright point settings.
The laser pattern mask is a negative image or reverse image of the laser input file. For the laser input file, during laser burning, a white pixel means the pixel is not lasered (which results in the original indigo color of the fabric), and a black pixel means the pixel will be lasered at highest level (which results in the whitest color that can be achieved on the fabric). In an implementation, the laser input file has 256 levels of gray, and for levels between 0 (e.g., black) and 255 (e.g., white), then the amount of laser burning will be proportionally somewhere in between.
The adjusted base template image is created from the base template image by adjusting its hue, saturation, or lightness, or any combination of these. Compared to the original base template image, the adjusted base template image will appear washed out or bleached. In other words, the adjusted base template image will appear as if the garment in the base template image were fully bleached or lasered. The adjusted base template image can be an HLS adjustment layer as discussed above.
Digital Brief Tool
Embodiments of a digital brief tool (or garment preview tool) may execute on Apple Inc.'s iPad Pro tablet computer device. Although the screens portray the digital brief tool as executing on an iPad Pro, other suitable electronic devices may execute the digital brief tool. For example, the digital brief tool may execute on a Windows device (e.g., Windows 10 tablet), an Android device, other iPad product family models (e.g., iPad or iPad mini), or many other devices.
The iPad Pro 12.9 is a tablet device with rectangular dimensions of 12 inches by 8.68 inch, and is 0.27 inches thick. The iPad Pro has a 12.9-inch screen, and has nonvolatile memory storage of 64, 256, or 512 gigabytes. The iPad Pro has network connectivity via Wi-Fi and optionally cellular. The iPad Pro has an A10X Fusion chip with 64-bit architecture and an embedded M10 coprocessor. Some features of the digital brief tool can be accelerated by using specialized features available in the A10X Fusion chip or embedded M10 coprocessor, or both. An operating system of the iPad Pro is Apple iOS 11 (or greater when released). Further, the iPad Pro can be operated with a stylus, the Apple Pencil product. And in an implementation, the use can use the Apple Pencil with the digital brief tool.
The digital brief tool includes various features, allowing a designer to select, create, and visualize how an apparel item will look with certain characteristics, before the apparel item is produced. The digital brief tool may allow the designer, for one or more characteristics of a proposed apparel item, to assign one or more options to each of the characteristics. While assigning the options for characteristics, the digital brief tool allows the designer to see, based on currently assigned options, how the apparel item may appear when produced, in real time as changes are made.
Selecting gender, series, fit, fabric, or other characteristics in the digital brief tool may result in having only relevant options presented to the designer. For example, some characteristics or options may be specific to a particular gender. Upon selection of the particular gender, characteristics and options with the selected gender will appear for the designer to use for a proposed apparel item.
In an implementation, the digital brief tool is adapted for use with producing jeans. For example, the following figures may include various characteristics and options relevant to designing and stylizing of jeans. However, the digital brief tool may be adapted for use with other apparel items, such as shirts, jackets, pants, or socks.
Some implementations of the digital brief tool are discussed in U.S. application Ser. Nos. 16/177,387, 16/177,412, and 16/177,407, filed Oct. 31, 2018, and are incorporated by reference.
Apparel Management System
Using the sales and order component, a customer can preview and selects garments to order. The customer can be a buyer for a retail store, internal buyer for retail sales of a region, regional salesperson, or other customer. The sales process can include using a variety of tools to assist a customer with showing available products, selecting products to purchase, keeping an order within budget, accessing a history of previous orders, and customizing and selecting fits, styles, and sizes of products. As an example, the customer can view products and order via a digital showroom. The products are shown digitally, which reduces the amount of physical samples that need to be produced. Further, the customer can also order via a Web site managed by the apparel management system. After the customer completes the order, the order is sent via the network (e.g., Internet) to the apparel management system.
The apparel management system sends the order to the manufacturing component, where the order is made. Manufacturing can include cutting the fabric material, assembling or sewing together the cut panels, and finishing the apparel item using a laser. An apparel manufacturer can have numerous manufacturing centers, and the apparel management system will send the order to a manufacturing center that is appropriate for the customer and order. The determination is based on a location of the customer (e.g., shipping time to customer from manufacturing center) and the apparel item selected (e.g., availability of material). The system ensures the order will be fulfilled efficiently in short amount of time.
In an implementation, the laser finishing is done after the garment is assembled. Specifically, the material is cut, assembled into a garment, and then the garment is finished using a laser. The finishing is based on style or customization selected by the customer in the order.
In another implementation, the laser finishing is before the garment is assembled. Specifically, before the material is cut, fabric rolls or sheets of material are finished u sing the laser. The finishing is based on style or customization selected by the customer in the order. Then the material is cut into panels, and the panels are assembled into the garment.
After manufacture of the garments of the order is complete, the apparel management system controls distribution, shipping, and delivering of the ordered garments to the customer. The apparel management system can send the customer tracking information for the order so that the customer can track the order.
Depending on various factors which may delay manufacture of some items, an order with multiple items may be sent to the customer in multiple partial shipments rather than a single complete shipment. The items not shipped at the same time will be shipped later when available. The apparel management system handles communicating with the customer regarding delays and provides an estimate of when the customer can expect to receive the items of the order.
Digital Showroom Tool
The digital showroom 2208 is connected via a network 2216 to a digital showroom computing system 2223, which controls operation of the devices and tools available in the digital showroom. The network can be a computer network. The digital showroom computing system has access to a product info database (e.g., product lifecycle management (PLM) database), base templates, and laser input files. Previews of garment products can be shown on the display panels, tablet, or on the physical displays, or any combination of these.
Order Tool
Collection Imagery
The tool 2401 includes a segmentation feature, which allows tool 2401 to understand what garments are shown in the customer imagery. There may be multiple garments shown in a picture, including accessories. Tool 2401 includes a pose estimation feature that, for garments which are worn or otherwise take on a different shape when used, a pose from the existing imagery. Tool 2401 includes a projection feature that, based on input from the segmentation and pose estimation features, projects garments from the manufacturer garments database 2415 onto the customer imagery.
In a step 2505, the system includes receiving a user-provided image. The user-provided image may be any image that the user feels will be useful in understanding how their image would appear when replaced with garments created using the garment previewing tool, such as an advertisement, store signage, or other. For example, the user-provided image may be a digital photo of one or more models wearing garments that are sold by the user. The image includes a location that is appropriate for a jeans garment, such as legs of a model captured in the image.
In a step 2510, the system includes segmenting the image. Segmenting the image includes identifying where in the image items of interest appear. For example, the system may identify pants, accessories, tops, or other garment areas.
In a step 2515, the system includes using pose estimation to determine a pose where a garment appears. If the garment is a pair of jeans, the system determines whether the garment appears in the image then how the pair of jeans is being worn in the image. For example, a model wearing the pair of jeans may have their leg bent or standing at a lean. The system may determine that the knee area of the model includes an articulation point and garments replacing the pair of jeans would need to similarly bend at the articulation point.
In a step 2520, the system includes modifying a garment preview image to correspond to the pose and replaces the garment in the image. For example, the garment preview image is created using the garment preview tool. The garment preview image is modified to show the pose determined in step 2515, such as a lean or bent leg. In an implementation, one or more garments are identified in the image. Two or more of the garments identified are replaced in the image. The two or more garments may be different types of garments, such as jeans, pants, shirts, jackets, handbags, or any other type of garment.
In an implementation, the system may use the distance methods as explained in greater detail below. For example, the tool 2401 may include a (i) direct image distance measurement or (ii) feature-based image distance measurement, or both.
In a step 2525, the system includes providing a target garment and creating a wear pattern on the target garment. The target garment includes a real-world version of the base garment selected by the user. For example, the target garment is a pair of jeans, adapted for laser finishing. From the input with modified sizing or positioning from the user, the target garment is finished with the wear pattern. The target garment may be created using the garment preview image identified above. The garment preview image may be generated before creating the wear pattern on the target garment.
The photo or video of the customer imagery is used for subject image segmentation. Subject locations are used for product segmentation which produces product locations. The photo or video of the customer imagery is used for image subject pose estimation. The customer imagery projection tool may determine, for a person in the image, where the person's head or other parts are located.
With the product locations, the subject pose, and the product images, product views are created based on subject pose and product locations. For example, based on the person's pose, products that are projected onto the person are in the proper pose. With the photo or video from the customer imagery and the oriented product views, projections using customer imagery is created.
Techniques are used to determine locations of persons in a customer image with products in the image (segmentation) and estimate the pose of the individuals (pose estimation). With this information the newly created/selected product can be oriented and placed into the customer imagery.
With the location and the pose information of persons in the photo, the customer imagery projection tool can use GAN techniques to translate between undeformed images of a garment to a project that garment into a form (e.g., deformed) and position that will properly fit the person in the image.
An implementation of a GAN technique that may be used is described in U.S. patent application Ser. No. 16/177,393, filed Oct. 31, 2018.
Inventory Swapper
The tool 3301 includes a garment location identifier feature. For example, the customer asset is in digital format or is digitized, so that the tool 3301 can do an analysis of what is displayed in the customer asset. The customer asset is analyzed to identify one or more garments in the customer asset, as well as related information useful for comparison by the tool 3301. Multiple garments or accessories may be identified in a single customer asset. The tool 3301 includes a distance calculator feature that, for each of the garments identified by the garment location identifier feature, compares the identified garments with manufacturer garments database 3310. In an implementation, the garment location identifier feature may include the segmentation feature as discussed above to identify where apparel appears in the customer asset.
The tool 3301 includes a populator feature that populates the customer asset keeping a similar layout as used in the customer asset, but with the identified garments replaced by a garment identified in the manufacturer garments database 3310. The populator feature may use the pose estimation feature described above to properly distort images of garments stored in the garment database 3310 so that it appears similarly to the customer's asset.
In an implementation where the customer asset 3305 is a web page, the tool 3301 may include a code analysis feature. The code analysis feature may analyze code of the user used to create the web page to identify garment location and associated locations where images for the garments are stored, as well as other useful information identifying the garments stored. The code may be HTML code or other code executable on a browser.
In a step 3405, the system includes receiving an existing webpage and identifying existing garments. The existing webpage includes a webpage of the user. The webpage may be a webpage that customers of the user may view to see items that they may decided to purchase. There may be multiple images of each garment available for sale on the existing webpage.
In an implementation, the system includes code analysis of the existing webpage. For example, HTML code of the existing webpage may identify images for items sold on the existing webpage, such as through identification of HTML tags, image storage locations, and other information of the existing webpage.
In a step 3410, the system includes identifying similar garments. For example, each garment on the existing webpage is extracted and analyzed to determine a garment created using the garment previewing tool that is similar to the existing garment.
In a step 3415, the system includes replacing existing garments with similar garments.
In a step 3420, the system includes providing a target garment and creating a wear pattern on the target garment. The target garment includes a real-world version of the base garment selected by the user. For example, the target garment is a pair of jeans, adapted for laser finishing. From the input with modified sizing or positioning from the user, the target garment is finished with the wear pattern. The target garment may be created using the garment preview image identified above. The garment preview image may be generated before creating the wear pattern on the target garment.
If an existing garment does not exist for the manufacturer, other tools (e.g., digital brief tool) can be preselected to create a custom garment (e.g., via laser finishing) that is similar to the competitor's product.
The distance methods can include a (i) direct image distance measurement or (ii) feature-based image distance measurement, or both, or some combination of these methods. As shown on a left-side of the
For the upper flow 3801 on the direct image distance measurement, the customer product image is input to a laser pattern type image conversion process, which results in a type converted image. This type converted image is scale adjusted, which results in a scale adjusted pattern image. The scale adjusted pattern image and the manufacturer's pattern database (e.g., laser file input files) are input to a direct pixel based image measurement process. Based on this process, the distance of the pixels of the images are determined, which results in an image distance score. A result of this distance method is to find similar images to that of the competitor's product.
In an implementation, the tool 3301 uses GAN techniques to extract information used to determine distance. For example, a wear pattern used by a garment in existing customer imagery may be useful for distance matching. After the image of the garment has been identified, it may be difficult to match the used wear pattern with a wear pattern that may be created using a laser as used by the digital brief tool, especially since a laser file used by the digital brief tool is in a 2D format. Using a generative adversarial network technique, the tool 3301 can extract a wear pattern in the existing customer imagery. The extracted wear pattern can then be compared to wear patterns used by the digital brief tool.
For the lower flow 3805 feature-based image distance measurement, neural network training is performed on a database of images, which include images of competitor's garments and the manufacturer's garments. The neural network performs unsupervised image clustering. A result of the training is a trained model. The result is a model that can be used as a deep feature based distance measurement model. When the model is given a customer or competitor image (e.g., Wranglers) and a manufacturer's image (e.g., LS&Co.), the model outputs a distance or an image distance score. This score is used to find similar images to that of the competitor's product.
This description of the invention has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form described, and many modifications and variations are possible in light of the teaching above. The embodiments were chosen and described in order to best explain the principles of the invention and its practical applications. This description will enable others skilled in the art to best utilize and practice the invention in various embodiments and with various modifications as are suited to a particular use. The scope of the invention is defined by the following claims.
This patent application is a continuation of U.S. patent application Ser. No. 17/305,718, filed Jul. 13, 2021, issued as U.S. Pat. No. 11,613,843 on Mar. 28, 2023, which is a continuation of U.S. patent application Ser. No. 16/288,053, filed Feb. 27, 2019, issued as U.S. Pat. No. 11,058,163 on Jul. 13, 2021, which claims the benefit of U.S. patent applications 62/636,108 and 62/636,112, filed Feb. 27, 2018. These applications are incorporated by reference along with all other references cited in this application.
| Number | Date | Country | |
|---|---|---|---|
| 62636112 | Feb 2018 | US | |
| 62636108 | Feb 2018 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 17305718 | Jul 2021 | US |
| Child | 18186134 | US | |
| Parent | 16288053 | Feb 2019 | US |
| Child | 17305718 | US |
