A number of techniques have been proposed to enable extraction of the foreground from a scene, for example, the extraction of a person from a digital image showing the person standing in front of a scenic view. This process of splitting an image into the foreground and background is known as image segmentation. Image segmentation comprises labeling image elements (such as pixels, groups of pixels, voxels or groups of voxels) as either a foreground or a background image element. This is useful in digital photography, medical image analysis, and other application domains where it is helpful to find a boundary between an object in the image and a background. The extracted object and the background may then be processed separately, differently, etc. For example, in the case of a medical image it may be appropriate to segment out a region of an image depicting a tumor or organ such as the lungs in order to enable a surgeon to interpret the image data.
Dependent upon the technique used, the amount of user input that is involved to achieve the segmentation can vary significantly: from systems in which a user traces the approximate outline of the object to be extracted, to systems in which a user marks a rectangle on the image which contains the object. Some of these techniques allow a user to edit the initial segmentation that has been achieved, for example to correct for errors in the initial segmentation.
The embodiments described below are not limited to implementations which solve any or all of the disadvantages of known image segmentation techniques.
The following presents a simplified summary of the disclosure in order to provide a basic understanding to the reader. This summary is not an extensive overview of the disclosure and it does not identify key/critical elements of the invention or delineate the scope of the invention. Its sole purpose is to present some concepts disclosed herein in a simplified form as a prelude to the more detailed description that is presented later.
Methods of updating image segmentation following user input are described. In an embodiment, the properties used in computing the different portions of the image are updated as a result of one or more user inputs. Image elements which have been identified by a user input are given more weight when updating the properties than other image elements which have already been assigned to a particular portion of the image. In another embodiment, an updated segmentation is post-processed such that only regions which are connected to an appropriate user input are updated.
Many of the attendant features will be more readily appreciated as the same becomes better understood by reference to the following detailed description considered in connection with the accompanying drawings.
The present description will be better understood from the following detailed description read in light of the accompanying drawings, wherein:
Like reference numerals are used to designate like parts in the accompanying drawings.
The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. The description sets forth the functions of the example and the sequence of steps for constructing and operating the example. However, the same or equivalent functions and sequences may be accomplished by different examples.
Although the present examples are described and illustrated herein as being implemented in an image labeling system for foreground/background image segmentation, the system described is provided as an example and not a limitation. As those skilled in the art will appreciate, the present examples are suitable for application in a variety of different types of image labeling systems and a non-exhaustive list of examples is: 3D reconstruction, stereo matching, object segmentation, object recognition and optical flow.
The image labeling system receives user input 102 specifying “seeds”, which may comprise brush strokes or other forms of marking parts of an image, for the labeling. In an example, these seeds identify one or more image elements as being part of a particular portion of the image. In the following description the user input is referred to as a brush stroke by way of example only and it will be appreciated that other types of user input which identifies one or more image elements (e.g. through marking a rectangle) may be used. The image labeling system also optionally receives segmentation data 103, which may comprise data labeling each image element in the image or a part of the image as foreground/background or may comprise properties associated with different portions of the segmented image. However, this segmentation data may be computed by the image labeling system itself.
The image labeling system 100 comprises an analysis engine 105 arranged to use the user input 102 and the segmentation data 103 to enable the segmentation of the image to be updated as described in more detail below. The image labeling system 100 may also comprise a segmentation engine 106 for performing image segmentation (which may involve optimizing energy functions, as described in more detail below) in order to generate the segmentation data 103.
A number of methods of improving image segmentation through user input are described below. The methods described may be used with any suitable method of performing the image segmentation and one example of a suitable method (referred to herein as ‘GrabCut’) is described in U.S. patent application Ser. No. 10/861,771 (Publication No. 2005/0271273) which is incorporated herein by reference in its entirety. A brief overview of an embodiment of GrabCut is provided below with reference to
αn=0 for nεTB
αn=1 for nεTU
Gaussian mixture models (GMMs) may be used in defining the foreground and background properties (in block 204) and the foreground and background GMMs are initialized from sets αn=0 and αn=1 respectively. Each GMM (one for the background and one for the foreground) is taken to be a full-covariance Gaussian mixture with K components (e.g. K=5). A vector k=(k1, . . . , kn) is used, with knε{1, . . . , K} to assign a unique GMM component (one component either from the background or the foreground model) to each pixel according to the opacity value αn. For each pixel in the unknown region (i.e. for each n in TU) GMM components are assigned using:
And then the GMM parameters are learnt from the data z using:
The Gibbs energy for segmentation may be defined (in block 206) as:
E(α,k,θ,z)=U(α,k,θ,z)+V(α,z) (3)
Where the parameter θ describes the image foreground and background distributions (as learned in block 204 using equation (2)), V is a smoothness term computed by Euclidean distance in color space, U evaluates the fit of opacity distribution α to the data z, given the parameter θ and taking account of the color GMM models, where:
U(α,k,θ,z):=ΣDn(αn,kn,θ,zn) (4)
Where:
Dn(αn,kn,θ,zn)=−log p(zn|αn,kn,θ)−log π(αn,kn)
p( ) is a Gaussian probability distribution and π( ) are mixture weighting coefficients, so that (up to a constant):
Therefore the parameters of the model are:
θ={π(α,k),μ(α,k),Σ(α,k),α=0,1,k=1 . . . K} (6)
The smoothness term V is computed as follows, (where the contrast term is computed using Euclidean distance in the color space):
Where C is the set of pairs of neighboring pixels. When the constant β=0, the smoothness term is simply the well-known Ising prior, encouraging smoothness everywhere, to a degree determined by the constant γ. In an implementation, β may be greater than zero to relax the tendency to smoothness in regions of high contrast. The constant β may be chosen as:
Where < > denotes expectation over an image sample. In an implementation, such a choice of β ensures that the exponential term in V (equation (7)) switches appropriately between high and low contrast.
Given the energy model described above, the foreground and background portions can be computed (in block 208) by using a standard minimum cut algorithm to solve:
All pixels in the trimap region TB are assigned to background and all pixels in TF to foreground. Pixels in TU are assigned to either foreground or background, depending on the result of the energy minimization (equation (8)).
The process may be repeated, as indicated by the dotted arrow 20, in an iterative minimization process (or other optimization process) until convergence. Further processing may then be used, such as border matting.
It will be appreciated that alternative segmentation methods may alternatively be used and GrabCut provides just one example of a suitable method. For example, where the image is monochrome (instead of color) the foreground and background properties may be defined in terms of histograms of gray values and a segmentation method such as that described in the paper ‘Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images’ by Boykov and Jolley (published in Proc. IEEE International Conference on Computer Vision 2001) may be used.
The examples shown in
On receipt of a user input identifying one or more image elements (in block 402), it is determined from the user input, whether the user input identifies one or more image elements as being part of the foreground or part of the background portions of the image (block 404). If the user input is determined to be a foreground input, i.e. identifying (or marking) one or more image elements as belonging to a foreground portion (‘Yes’ in block 404, and as shown in the example of
The term ‘current segmentation’ is used herein to refer to the segmentation before it is updated in block 408 or block 412 and which may, in the case of the first user input received, be the initial segmentation (i.e. the segmentation performed before receipt of any of these user inputs updating the segmentation). The user input(s) may be received in response to displaying the results of this current segmentation to the user e.g. the foreground or the background portions may be displayed to the user or the two portions may be displayed as different layers within an image editing application or tool.
In an example, the foreground properties may be updated using a weighted combination of properties of the image elements within the foreground. Different weights are applied to the properties of image elements which have been identified and to the properties of other image elements within the foreground (which have not been identified by a user input). The weight applied to the identified image elements is larger (and in some examples, significantly larger) than the weight applied to the other foreground elements. In the situation where the identified image elements only comprise background image elements, the ‘other image elements within the foreground’ comprise all the image elements labeled as foreground in the current segmentation. A method of updating the foreground properties (block 406) is described in more detail below using the GrabCut notation by way of example.
In a corresponding manner, if the user input is determined to be a background input, i.e. identifying (or marking) one or more image elements as belonging to a background portion (‘No’ in block 404), the background properties (e.g. the background properties determined in performing the current segmentation) are updated giving more weight to those image elements that have been identified by the user input than to those image elements which are labeled as background in the current segmentation but have not been identified (block 410, e.g. as performed by analysis engine 105 in
Having updated the segmentation, in block 408 or 412, the updated segmentation results may be displayed to the user via a display device (not shown in
The determination as to whether the user input identifies image elements as belonging to the background or foreground, i.e. whether the input is a foreground or background input, (in block 404) may be made in many different ways. For example the user may click on an icon labeled ‘Background’ or ‘Foreground’ before marking the image (e.g. before placing the brush stroke) or the user may depress a different control (e.g. a keyboard key or mouse button) whilst making the mark on the image (e.g. whilst making the brush stroke). It will be appreciated that these are provided by way of example only and where icons are used they may be labeled in a different manner (e.g. ‘+’ for foreground and ‘−’ for background as shown in the example of
FnotBrush(k)={n:kn=k and αn=1, and not identified by a foreground input}
FBrush(k), as defined in block 502, is the set of image elements indices (e.g. pixels indices) which are identified by the foreground input and are assigned to the Gaussian with index k. This can be written as:
FBrush(k)={n:kn=k and identified by a foreground input}
Having defined the two sets (in blocks 502 and 504), the foreground properties are updated giving more weight to the pixels in the set FBrush(k) than to the pixels in the set FnotBrush(k) (block 506), using a weighted combination (e.g. a weighted average) of parameters. Where the segmentation uses GMM as the foreground and background properties (as in GrabCut described above) and the image element is a pixel, parameters, such as the mean, μ, and the covariance, Σ, of the foreground GMM may be updated as follows. Here we consider for example μ(1,k), using the notation as before, which means the mean of kth Gaussian of the foreground model:
μ(1,k)=1/Z*Σn[w(Brush)*zn*σ[n is in the set FBrush(k)]+w(notBrush)*zn*σ[n is in the set FnotBrush(k)]
where w(Brush) and w(notBrush) are two weights and σ[argument] is ‘1’ if “argument” is true and ‘0’ if not. The value Z is a normalization constant and can be computed as:
Z=Σn[w(Brush)*σ[n is in the set FBrush(k)]+w(notBrush)*σ[n is in the set FnotBrush(k)]
The mixing weighting π(α,k) for each Gaussian is also updated. Note that for both α=1 and α=0 it is Σk π(α,k)=1. The update is done in the following way:
π(1,k)=1/Z2Σn[w(Brush)*σ[n is in the set FBrush(k)]+w(notBrush)*σ[n is in the set FnotBrush(k)]
where:
Z2=Σnw(Brush)*σ[n is in a set FBrushSuper]+w(notBrush)*σ[n is in the set FnotBrushSuper]
In the above equation, FBrushSuper is a superset, i.e. a merging of all sets FBrush(k) with k=1, . . . , K; and FnotBrushSuper is also superset, i.e. a merging of all sets FnotBrush(k) with k=1, . . . , K. In the same way π(0,k) is computed. The covariance matrix Σ(α,k) is as above weighted depending on the respective pixel being part of FBrush(k)] or FnotBrush(k (here α=1). If data with 3-dimensions is used (e.g. RGB) then is a 3×3 matrix. An entry for Σ(1,k) is then:
Σij=1/Z3*Σn[w(Brush)*(zn,i−μi)*(zn,j−μj)*σ[n is in the set FBrush(k)]+w(notBrush)*(zn,i−μi)*(zn,j−μj)*σ[n is in the set FnotBrush(k)]
where μi is the ith dimension of μ(1,k); zn,i is the ith dimension of input data. The normalization constant Z3 is then the same as Z. This means:
Z3=Σn[w(Brush)*σ[n is in the set FBrush(k)]+w(notBrush)*σ[n is in the set FnotBrush(k)]
The values of the two weights, w(Brush) and w(notBrush), which are used in relation to sets FBrush(k) and FnotBrush(k) respectively, may be set to any value such that w(Brush) is larger than w(notBrush). In an example, w(Brush)=80 and w(notBrush)=1. These weights may be user defined, defined by the image labeling system or fixed in value.
It will be appreciated that the method shown in
BnotBrush(k)={n:kn=k and αn=0, and not identified by a background input}
BBrush(k)={n:kn=k and identified by a background input}
Based on these defined sets, the background properties are updated in block 506.
Where the image segmentation is performed using GrabCut, the computing of the foreground and background portions (in blocks 408 and 412) using the updated properties can be performed by using a standard minimum cut algorithm to solve equation (8) above.
The method shown in
Following receipt of a plurality of user inputs (block 602), the foreground properties (e.g. the foreground GMM) are updated based on one or more the foreground inputs in the plurality of user inputs (block 604). This updating of properties may be performed as described above and shown in
Where the user input (received in block 602) only defines foreground inputs, there will be no data upon which to update the background properties (in block 606) and in this situation the existing background properties are used in updating the image segmentation (in block 608). Similarly, where the user input only defines background inputs, there will be no data upon which to update the foreground properties (in block 604) and the existing foreground properties are used in computing the foreground and background portions (in block 608). In another embodiment, however, alternative distributions may be used where there are no updated properties for either the background or the foreground. In an example, where the user input (received in block 602) defines only foreground inputs, the foreground and background portions may be computed (in block 608) using the updated foreground properties and a uniform distribution for the background.
The method shown in
Each group of inputs may be received separately (in block 602) or each group may comprise a subset of the inputs received (in block 602). The method shown in
As described above, the methods give more weight to image elements identified by a user input (e.g. brushed image elements) compared to image elements which, according to the current segmentation, have already be labeled as belonging to the particular portion of the image (e.g. foreground/background) when re-computing the image segmentation. This may provide a better quality of image segmentation and/or improve the user experience.
The method shown in
The input data for the method of
The data relating to the user input may be defined in terms of two sets: a set (b−) of image elements (e.g. pixels) which have been identified by a background input (e.g. brushed by a background brush) and hence have been forced to take the background label (α=0), and a set (b+) of image elements (e.g. pixels) which have been identified by a foreground input (e.g. brushed by a foreground brush) and hence have been forced to take the foreground label (α=1). It will be appreciated that in some examples, only one set may be defined or one or both of the sets may be an empty set.
The method shown in
The method of
The method of
Having computed the sets (in block 702), a connected region in a set (e.g. in set SC− or SC+) is then examined (in block 704 or 706). If a connected region in SC− is identified (in block 704) which does not contain an image element which has been identified by a background input (i.e. an image element which is a member of set b−), the image elements within the particular region being examined are changed back to foreground (block 708). If a connected region in SC+ is identified (in block 706) which does not contain an image element which has been identified by a foreground input (i.e. an image element which is a member of set b+), the image elements in the particular region being examined are changed back to background (block 710). In an embodiment, each of the regions in the sets of connected regions (as computed in block 702) may be examined (in block 704 or 706 as appropriate); however in other embodiments a subset of the regions may be examined.
The method can be further described with reference to the graphical representation of
In an embodiment of the method shown in
In another embodiment of the method shown in
Having updated the segmentation, in block 708 or 710, the updated segmentation results may be displayed to the user via a display device (not shown in
Where the method of
As described above, the groups of user inputs (e.g. brush strokes) may be defined according to the order in which the input is received (e.g. 1st 5 brush strokes, next 5 brush strokes etc) or the groups may be defined in another manner (e.g. first group of connected brush strokes, second group of connected brush strokes etc). In such an embodiment, the method of image segmentation may be as shown in the flow diagram in
According to the method shown in
The results of each iteration of
The methods described above may be implemented in an image editing tool within a software application. In an embodiment, the software application is an image editing application. In another embodiment, the software application is not a dedicated image editing application, but may instead be a word processing application, a spreadsheet application, a slide presentation application, a database application, an email application etc. Where a number of software applications are combined within a multiple functionality application, the image editing tool may be available within each application and may be presented to the user in the same or a similar manner in each application within the multiple functionality application. In an example, a dedicated control 1002 for image segmentation may be provided within a ribbon-shaped user interface 1004 above the software application workspace 1006, as shown in the schematic diagram of
When a user clicks (e.g. with a mouse or other pointing device, which may include a finger if the display device is touch sensitive) on the dedicated control 1002, having selected an image 1008 which is displayed in the software application workspace 1006, the image 1008 may be segmented (e.g. using the method shown in
Computing-based device 1100 comprises one or more processors 1102 which may be microprocessors, controllers or any other suitable type of processors for processing computing executable instructions to control the operation of the device in order to perform image segmentation, as described herein. Platform software comprising an operating system 1104 or any other suitable platform software may be provided at the computing-based device to enable application software 1106 to be executed on the device.
The application software 1106 may include software (i.e. executable instructions) for performing image segmentation or separate software 1108 may be provided. Where separate software is provided, this may be called by the application software 1106 or may be called directly by the user (e.g. as an image segmentation application). The image segmentation software may comprise software for performing the methods of updating the segmentation as described herein or separate software 1110 may be provided.
The computer executable instructions may be provided using any computer-readable media, such as memory 1112. The memory is of any suitable type such as random access memory (RAM), a disk storage device of any type such as a magnetic or optical storage device, a hard disk drive, or a CD, DVD or other disc drive. Flash memory, EPROM or EEPROM may also be used. Although the memory is shown within the computing-based device 1100 it will be appreciated that the storage may be distributed or located remotely and accessed via a network or other communication link (e.g. using communication interface 1114).
The memory 1112 may comprise an image store 1116 for storing the images which are segmented and may also comprise a store for segmentation data 1118.
The communication interface 1114 is arranged to send/receive information over a network 1120. Any suitable network technology (including wired and wireless technologies) and network protocol(s) may be used.
The computing-based device 1100 also comprises an input/output controller 1122 arranged to output display information to a display device 1124 which may be separate from or integral to the computing-based device 1100. The display information may provide a graphical user interface and may be arranged to display the results of the updated image segmentation (as generated using any of the methods described herein) to the user. The input/output controller 1122 is also arranged to receive and process input from one or more devices, such as a user input device 1126 (e.g. a mouse or a keyboard). This user input may be the user input which is used to update the segmentation using one of the methods described herein (e.g. user input 102 in
Although the present examples are described and illustrated herein as being implemented in the system shown in
The term ‘computer’ is used herein to refer to any device with processing capability such that it can execute instructions. Those skilled in the art will realize that such processing capabilities are incorporated into many different devices and therefore the term ‘computer’ includes PCs, servers, mobile telephones, personal digital assistants and many other devices.
The methods described herein may be performed by software in machine readable form on a tangible storage medium. Examples of tangible (or non-transitory) storage media include disks, thumb drives, memory etc and do not include propagated signals. The software can be suitable for execution on a parallel processor or a serial processor such that the method steps may be carried out in any suitable order, or simultaneously.
This acknowledges that software can be a valuable, separately tradable commodity. It is intended to encompass software, which runs on or controls “dumb” or standard hardware, to carry out the desired functions. It is also intended to encompass software which “describes” or defines the configuration of hardware, such as HDL (hardware description language) software, as is used for designing silicon chips, or for configuring universal programmable chips, to carry out desired functions.
Those skilled in the art will realize that storage devices utilized to store program instructions can be distributed across a network. For example, a remote computer may store an example of the process described as software. A local or terminal computer may access the remote computer and download a part or all of the software to run the program. Alternatively, the local computer may download pieces of the software as needed, or execute some software instructions at the local terminal and some at the remote computer (or computer network). Those skilled in the art will also realize that by utilizing conventional techniques known to those skilled in the art that all, or a portion of the software instructions may be carried out by a dedicated circuit, such as a DSP, programmable logic array, or the like.
Any range or device value given herein may be extended or altered without losing the effect sought, as will be apparent to the skilled person.
It will be understood that the benefits and advantages described above may relate to one embodiment or may relate to several embodiments. The embodiments are not limited to those that solve any or all of the stated problems or those that have any or all of the stated benefits and advantages. It will further be understood that reference to ‘an’ item refers to one or more of those items.
The steps of the methods described herein may be carried out in any suitable order, or simultaneously where appropriate. Additionally, individual blocks may be deleted from any of the methods without departing from the spirit and scope of the subject matter described herein. Aspects of any of the examples described above may be combined with aspects of any of the other examples described to form further examples without losing the effect sought.
The term ‘comprising’ is used herein to mean including the method blocks or elements identified, but that such blocks or elements do not comprise an exclusive list and a method or apparatus may contain additional blocks or elements.
It will be understood that the above description of a preferred embodiment is given by way of example only and that various modifications may be made by those skilled in the art. The above specification, examples and data provide a complete description of the structure and use of exemplary embodiments of the invention. Although various embodiments of the invention have been described above with a certain degree of particularity, or with reference to one or more individual embodiments, those skilled in the art could make numerous alterations to the disclosed embodiments without departing from the spirit or scope of this invention.
Number | Name | Date | Kind |
---|---|---|---|
4627620 | Yang | Dec 1986 | A |
4630910 | Ross et al. | Dec 1986 | A |
4645458 | Williams | Feb 1987 | A |
4695953 | Blair et al. | Sep 1987 | A |
4702475 | Elstein et al. | Oct 1987 | A |
4711543 | Blair et al. | Dec 1987 | A |
4751642 | Silva et al. | Jun 1988 | A |
4796997 | Svetkoff et al. | Jan 1989 | A |
4809065 | Harris et al. | Feb 1989 | A |
4817950 | Goo | Apr 1989 | A |
4843568 | Krueger et al. | Jun 1989 | A |
4893183 | Nayar | Jan 1990 | A |
4901362 | Terzian | Feb 1990 | A |
4925189 | Braeunig | May 1990 | A |
5101444 | Wilson et al. | Mar 1992 | A |
5148154 | MacKay et al. | Sep 1992 | A |
5182548 | Haeberli | Jan 1993 | A |
5184295 | Mann | Feb 1993 | A |
5229754 | Aoki et al. | Jul 1993 | A |
5229756 | Kosugi et al. | Jul 1993 | A |
5239463 | Blair et al. | Aug 1993 | A |
5239464 | Blair et al. | Aug 1993 | A |
5288078 | Capper et al. | Feb 1994 | A |
5295491 | Gevins | Mar 1994 | A |
5320538 | Baum | Jun 1994 | A |
5347306 | Nitta | Sep 1994 | A |
5385519 | Hsu et al. | Jan 1995 | A |
5405152 | Katanics et al. | Apr 1995 | A |
5417210 | Funda et al. | May 1995 | A |
5423554 | Davis | Jun 1995 | A |
5454043 | Freeman | Sep 1995 | A |
5469740 | French et al. | Nov 1995 | A |
5495576 | Ritchey | Feb 1996 | A |
5516105 | Eisenbrey et al. | May 1996 | A |
5524637 | Erickson | Jun 1996 | A |
5534917 | MacDougall | Jul 1996 | A |
5563988 | Maes et al. | Oct 1996 | A |
5577981 | Jarvik | Nov 1996 | A |
5580249 | Jacobsen et al. | Dec 1996 | A |
5594469 | Freeman et al. | Jan 1997 | A |
5597309 | Riess | Jan 1997 | A |
5616078 | Oh | Apr 1997 | A |
5617312 | Iura et al. | Apr 1997 | A |
5638300 | Johnson | Jun 1997 | A |
5641288 | Zaenglein, Jr. | Jun 1997 | A |
5682196 | Freeman | Oct 1997 | A |
5682229 | Wangler | Oct 1997 | A |
5690582 | Ulrich et al. | Nov 1997 | A |
5703367 | Hashimoto et al. | Dec 1997 | A |
5704837 | Iwasaki et al. | Jan 1998 | A |
5715834 | Bergamasco et al. | Feb 1998 | A |
5875108 | Hoffberg et al. | Feb 1999 | A |
5877803 | Wee et al. | Mar 1999 | A |
5900953 | Bottou et al. | May 1999 | A |
5913727 | Ahdoot | Jun 1999 | A |
5933125 | Fernie et al. | Aug 1999 | A |
5980256 | Carmein | Nov 1999 | A |
5989157 | Walton | Nov 1999 | A |
5995649 | Marugame | Nov 1999 | A |
6005548 | Latypov et al. | Dec 1999 | A |
6009210 | Kang | Dec 1999 | A |
6054991 | Crane et al. | Apr 2000 | A |
6066075 | Poulton | May 2000 | A |
6072494 | Nguyen | Jun 2000 | A |
6073489 | French et al. | Jun 2000 | A |
6077201 | Cheng | Jun 2000 | A |
6098458 | French et al. | Aug 2000 | A |
6100896 | Strohecker et al. | Aug 2000 | A |
6101289 | Kellner | Aug 2000 | A |
6128003 | Smith et al. | Oct 2000 | A |
6130677 | Kunz | Oct 2000 | A |
6141463 | Covell et al. | Oct 2000 | A |
6147678 | Kumar et al. | Nov 2000 | A |
6151025 | Yen et al. | Nov 2000 | A |
6152856 | Studor et al. | Nov 2000 | A |
6159100 | Smith | Dec 2000 | A |
6173066 | Peurach et al. | Jan 2001 | B1 |
6181343 | Lyons | Jan 2001 | B1 |
6188777 | Darrell et al. | Feb 2001 | B1 |
6215890 | Matsuo et al. | Apr 2001 | B1 |
6215898 | Woodfill et al. | Apr 2001 | B1 |
6226396 | Marugame | May 2001 | B1 |
6229913 | Nayar et al. | May 2001 | B1 |
6256033 | Nguyen | Jul 2001 | B1 |
6256400 | Takata et al. | Jul 2001 | B1 |
6283860 | Lyons et al. | Sep 2001 | B1 |
6289112 | Jain et al. | Sep 2001 | B1 |
6299308 | Voronka et al. | Oct 2001 | B1 |
6308565 | French et al. | Oct 2001 | B1 |
6316934 | Amorai-Moriya et al. | Nov 2001 | B1 |
6337925 | Cohen et al. | Jan 2002 | B1 |
6363160 | Bradski et al. | Mar 2002 | B1 |
6384819 | Hunter | May 2002 | B1 |
6411744 | Edwards | Jun 2002 | B1 |
6430997 | French et al. | Aug 2002 | B1 |
6476834 | Doval et al. | Nov 2002 | B1 |
6496598 | Harman | Dec 2002 | B1 |
6503195 | Keller et al. | Jan 2003 | B1 |
6539931 | Trajkovic et al. | Apr 2003 | B2 |
6570555 | Prevost et al. | May 2003 | B1 |
6633294 | Rosenthal et al. | Oct 2003 | B1 |
6640202 | Dietz et al. | Oct 2003 | B1 |
6661918 | Gordon et al. | Dec 2003 | B1 |
6681031 | Cohen et al. | Jan 2004 | B2 |
6714665 | Hanna et al. | Mar 2004 | B1 |
6731799 | Sun et al. | May 2004 | B1 |
6738066 | Nguyen | May 2004 | B1 |
6741755 | Blake et al. | May 2004 | B1 |
6744923 | Zabih et al. | Jun 2004 | B1 |
6765726 | French et al. | Jul 2004 | B2 |
6788809 | Grzeszczuk et al. | Sep 2004 | B1 |
6801637 | Voronka et al. | Oct 2004 | B2 |
6873723 | Aucsmith et al. | Mar 2005 | B1 |
6876496 | French et al. | Apr 2005 | B2 |
6937742 | Roberts et al. | Aug 2005 | B2 |
6950534 | Cohen et al. | Sep 2005 | B2 |
6973212 | Boykov et al. | Dec 2005 | B2 |
6987535 | Matsugu et al. | Jan 2006 | B1 |
7003134 | Covell et al. | Feb 2006 | B1 |
7036094 | Cohen et al. | Apr 2006 | B1 |
7038855 | French et al. | May 2006 | B2 |
7039676 | Day et al. | May 2006 | B1 |
7042440 | Pryor et al. | May 2006 | B2 |
7050606 | Paul et al. | May 2006 | B2 |
7058204 | Hildreth et al. | Jun 2006 | B2 |
7060957 | Lange et al. | Jun 2006 | B2 |
7079992 | Greiffenhagen et al. | Jul 2006 | B2 |
7113918 | Ahmad et al. | Sep 2006 | B1 |
7121946 | Paul et al. | Oct 2006 | B2 |
7170492 | Bell | Jan 2007 | B2 |
7184048 | Hunter | Feb 2007 | B2 |
7202898 | Braun et al. | Apr 2007 | B1 |
7222078 | Abelow | May 2007 | B2 |
7227526 | Hildreth et al. | Jun 2007 | B2 |
7259747 | Bell | Aug 2007 | B2 |
7308112 | Fujimura et al. | Dec 2007 | B2 |
7317836 | Fujimura et al. | Jan 2008 | B2 |
7348963 | Bell | Mar 2008 | B2 |
7359121 | French et al. | Apr 2008 | B2 |
7367887 | Watabe et al. | May 2008 | B2 |
7379563 | Shamaie | May 2008 | B2 |
7379566 | Hildreth | May 2008 | B2 |
7389591 | Jaiswal et al. | Jun 2008 | B2 |
7412077 | Li et al. | Aug 2008 | B2 |
7421093 | Hildreth et al. | Sep 2008 | B2 |
7430312 | Gu | Sep 2008 | B2 |
7430339 | Rother et al. | Sep 2008 | B2 |
7436496 | Kawahito | Oct 2008 | B2 |
7450736 | Yang et al. | Nov 2008 | B2 |
7452275 | Kuraishi | Nov 2008 | B2 |
7460690 | Cohen et al. | Dec 2008 | B2 |
7489812 | Fox et al. | Feb 2009 | B2 |
7536032 | Bell | May 2009 | B2 |
7555142 | Hildreth et al. | Jun 2009 | B2 |
7560701 | Oggier et al. | Jul 2009 | B2 |
7570805 | Gu | Aug 2009 | B2 |
7574020 | Shamaie | Aug 2009 | B2 |
7576727 | Bell | Aug 2009 | B2 |
7589721 | Lorenz | Sep 2009 | B2 |
7590262 | Fujimura et al. | Sep 2009 | B2 |
7593552 | Higaki et al. | Sep 2009 | B2 |
7598942 | Uderkoffler et al. | Oct 2009 | B2 |
7606417 | Steinberg et al. | Oct 2009 | B2 |
7607509 | Schmiz et al. | Oct 2009 | B2 |
7620202 | Fujimura et al. | Nov 2009 | B2 |
7668340 | Cohen et al. | Feb 2010 | B2 |
7676081 | Blake et al. | Mar 2010 | B2 |
7680298 | Roberts et al. | Mar 2010 | B2 |
7683954 | Ichikawa et al. | Mar 2010 | B2 |
7684592 | Paul et al. | Mar 2010 | B2 |
7701439 | Hillis et al. | Apr 2010 | B2 |
7702130 | Im et al. | Apr 2010 | B2 |
7704135 | Harrison, Jr. | Apr 2010 | B2 |
7710391 | Bell et al. | May 2010 | B2 |
7720283 | Sun et al. | May 2010 | B2 |
7729530 | Antonov et al. | Jun 2010 | B2 |
7746345 | Hunter | Jun 2010 | B2 |
7760182 | Ahmad et al. | Jul 2010 | B2 |
7778439 | Kondo et al. | Aug 2010 | B2 |
7809167 | Bell | Oct 2010 | B2 |
7834846 | Bell | Nov 2010 | B1 |
7852262 | Namineni et al. | Dec 2010 | B2 |
7860311 | Chen et al. | Dec 2010 | B2 |
RE42256 | Edwards | Mar 2011 | E |
7898522 | Hildreth et al. | Mar 2011 | B2 |
8004536 | Wilensky | Aug 2011 | B2 |
8035612 | Bell et al. | Oct 2011 | B2 |
8035614 | Bell et al. | Oct 2011 | B2 |
8035624 | Bell et al. | Oct 2011 | B2 |
8050498 | Wilensky et al. | Nov 2011 | B2 |
8072470 | Marks | Dec 2011 | B2 |
8081822 | Bell | Dec 2011 | B1 |
8165369 | Kubota et al. | Apr 2012 | B2 |
8170350 | Steinberg et al. | May 2012 | B2 |
8306333 | Lai et al. | Nov 2012 | B2 |
8463051 | Perronnin et al. | Jun 2013 | B2 |
20030184815 | Shiki et al. | Oct 2003 | A1 |
20040202369 | Paragios | Oct 2004 | A1 |
20050271273 | Blake et al. | Dec 2005 | A1 |
20060039611 | Rother et al. | Feb 2006 | A1 |
20060285747 | Blake et al. | Dec 2006 | A1 |
20070081710 | Hong et al. | Apr 2007 | A1 |
20070122039 | Zhang et al. | May 2007 | A1 |
20070133880 | Sun et al. | Jun 2007 | A1 |
20070165949 | Sinop et al. | Jul 2007 | A1 |
20070211940 | Fluck et al. | Sep 2007 | A1 |
20070216675 | Sun et al. | Sep 2007 | A1 |
20070237393 | Zhang et al. | Oct 2007 | A1 |
20070299667 | Netsch et al. | Dec 2007 | A1 |
20080026838 | Dunstan et al. | Jan 2008 | A1 |
20080120560 | Cohen et al. | May 2008 | A1 |
20080136820 | Yang et al. | Jun 2008 | A1 |
20080152231 | Gokturk et al. | Jun 2008 | A1 |
20080260247 | Grady et al. | Oct 2008 | A1 |
20080266432 | Tsuruoka | Oct 2008 | A1 |
20080304698 | Rasmussen et al. | Dec 2008 | A1 |
20080304735 | Yang et al. | Dec 2008 | A1 |
20090033683 | Schiff et al. | Feb 2009 | A1 |
20090060333 | Singaraju et al. | Mar 2009 | A1 |
20090060334 | Rayner | Mar 2009 | A1 |
20100104163 | Li et al. | Apr 2010 | A1 |
20100266207 | Zhang et al. | Oct 2010 | A1 |
20110117206 | Holt et al. | May 2011 | A1 |
Number | Date | Country |
---|---|---|
201254344 | Jun 2010 | CN |
0583061 | Feb 1994 | EP |
08044490 | Feb 1996 | JP |
WO9310708 | Jun 1993 | WO |
WO 9717598 | May 1997 | WO |
WO9944698 | Sep 1999 | WO |
WO 2008012808 | Jan 2008 | WO |
WO2008012808 | Jan 2008 | WO |
WO2009093146 | Jul 2009 | WO |
WO2009101577 | Aug 2009 | WO |
Entry |
---|
Carsten et al., “GrabCut”—Interactive Foreground Extraction using Iterated Graph Cuts, published on 2004, pp. 309-314, by ACM. |
Jian et al., (hearrafter Jian), “Poisson Matting”, published in 2004, p. 315-321, by ACM. |
Carsten et al., “GrabCut”—Interactive Foreground Extraction using Iterated Graph Cuts, published on 2004, pp. 309-314, ACM. |
Chunxia Xiao et al., Efficient Edit propagation using Hierarchical data structure, published Jan. 2007,in Journal of Latex class files vol. 6. No. 1 , p. 1-14. |
Adobe Photoshop, retrvied at <<http://www.adobe.com/support/photoshop/>> on Jul. 31, 2009, 7 pages. |
An, AppProp: All-Pairs Appearance-Space Edit Propagation, retrieved at <<http://www.cs.dartmouth.edu/˜fabio/papers/appprop08.ppt.pdf>> on Jul. 31, 2009, 36. |
Bai et al., A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting, University of Minnesota, IEEE ICCV 2007, 8 pages. |
Blake et al., “Interactive Image Segmentation using an adaptive GMMRF model”, Microsoft Research Cambridge UK, May 2004, 14 pages. |
Boykov et al., “An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision”, IEEE Transactions on PAMI, vol. 26, No. 9, Sep. 2007, pp. 1124-1137. |
Boykov et al., “Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images”, International Conference on Computer Vision, Jul. 2001, vol. 1, pp. 105-pp. 112. |
Chen et al., “Real-Time Edge-Aware Image Processing with the Bilateral Grid”, SIGGRAPH '07, CSAIL-MIT, pp. 1-pp. 34. |
Delong et al., “A Scalable Graph-Cut Algorithm for N-D Grids”, IEEE Conference on Computer Vision and Pattern Recoginition (CVPR), Jun. 2008, pp. 1-pp. 8. |
Olsen et al., “Edge-Respecting Brushes”, Computer Science Department Brigham Young University, ACM, Oct. 19-22, 2008, pp. 171-pp. 180. |
Grady, “Random Walks for Image Segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, No. 11, Nov. 2006, pp. 1-pp. 17. |
Kass et al., “Snakes: Active Contour Models”, International Journal of Computer Vision, 1988, pp. 321-pp. 331. |
Kopf et al., “Joint Bilateral Upsampling”, retived at <<http://johanneskopf.de/publications/jbu/paper/FinalPaper—0185.pdf >>, on Jul. 31, 2009, 5 pages. |
Levin et al., “A Closed-Form Solution to Natural Image Matting”, School of Computer Science and Engineering, retrived at <<http://www.wisdom.weizmann.ac.il/˜levina/papers/Matting-Levin-Lischinski-Weiss-CVPR06.pdf>>, 8 pages. |
Li et al., “Lazy Snapping”, ACM Inc, 2004, 0730-0301/04.0800-0303, retirved at <<http://www.cse.ust.hk/˜cktang/sample—pub/lazy—snapping.pdf>>,pp. 303-pp. 308. |
Li et al., “Scribbleboost: Adding Classification to Edge-Aware Interpolation of Local Image and Video Adjustments”, Eurographics Symposium on Rendering 2008, vol. 27, No. 4, pp. 1-pp. 10. |
Lischinski et al., “Interactive Local Adjustment of Tonal Values”, retrived at <<http://www.cs.huji.ac.il/˜danix/itm/itm.pdf>> on Jul. 31, 2009. |
Lombaert et al., “A Multilevel Banded Graph Cuts Method for Fast Image Segmentation”, Tenth IEEE Internation Conference on Computer Vision, ICCV 2005, vol. 1, pp. 259-pp. 265. |
Mortensen et al., “Intelligent Scissors for Image Composition”, Brigham Young University, retrived at <<http://web.engr.oregonstate.edu/˜enm/publications/SIGGRAPH—95/scissors—comp.pdf>>, 1995, 8 pages. |
Rother et al., “Grabcut—Interactive Foreground Extraction Using Iterated Graph Cuts”, Microsoft Research Cambridge, AK, retrived at <<http://research.microsoft.com/en-us/um/people/ablake/papers/ablake/siggraph04.pdf >>, Aug. 2004, pp. 1-6. |
Wang et al., “An Iterative Optimization Approach for Unified Image Segmentation and Matting”, retrived at <<http://research.microsoft.com/en-us/um/people/cohen/iccv2005.pdf >>, Oct. 2005, pp. 1-8. |
Wang et al., “Soft Scissors: An Interactive Tool for Realtime High Quality Matting”, retrived at <<http://juew.org/publication/softscissors-SIG07.pdf>>on Jul. 31, 2009, 6 pages. |
Aggarwal et al., “Human Motion Analysis: A Review”, IEEE Nonrigid and Articulated Motion Workshop, 1997, University of Texas at Austin, Austin, TX. |
Azarbayejani et al., “Visually Controlled Graphics”, Jun. 1993, vol. 15, No. 6, IEEE Transactions on Pattern Analysis and Machine Intelligence. |
Breen et al., “Interactive Occlusion and Collusion of Real and Virtual Objects in Augmented Reality”, Technical Report ECRC-95-02, 1995, European Computer-Industry Research Center GmbH, Munich, Germany. |
Brogan et al., “Dynamically Simulated Characters in Virtual Environments”, Sep./Oct. 1998, pp. 2-13, vol. 18, Issue 5, IEEE Computer Graphics and Applications. |
Fisher et al., “Virtual Environment Display System”, ACM Workshop on Interactive 3D Graphics, Oct. 1986, Chapel Hill, NC. |
Freeman et al., “Television Control by Hand Gestures”, Dec. 1994, Mitsubishi Electric Research Laboratories, TR94-24, Caimbridge, MA. |
Granieri et al., “Simulating Humans in VR”, The British Computer Society, Oct. 1994, Academic Press. |
Hasegawa et al., “Human-Scale Haptic Interaction with a Reactive Virtual Human in a Real-Time Physics Simulator”, Jul. 2006, vol. 4, No. 3, Article 6C, ACM Computers in Entertainment, New York, NY. |
He, “Generation of Human Body Models”, Apr. 2005, University of Auckland, New Zealand. |
Hongo et al., “Focus of Attention for Face and Hand Gesture Recognition Using Multiple Cameras”, Mar. 2000, pp. 156-161, 4th IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France. |
“Interactive Simulation and Training”, 1994, Division Incorporated, 6 pages. |
Isard et al., “Condensation—Conditional Density Propagation for Visual Tracking”, 1998, pp. 5-28, International Journal of Computer Vision 29(1), Netherlands. |
Kanade et al., “A Stereo Machine for Video-rate Dense Depth Mapping and Its New Applications”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1996, pp. 196-202,The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. |
Kohler, “Special Topics of Gesture Recognition Applied in Intelligent Home Environments”, In Proceedings of the Gesture Workshop, 1998, pp. 285-296, Germany. |
Kohler, “Technical Details and Ergonomical Aspects of Gesture Recognition applied in Intelligent Home Environments”, 1997, Germany. |
Kohler, “Vision Based Remote Control in Intelligent Home Environments”, University of Erlangen-Nuremberg/Germany, 1996, pp. 147-154, Germany. |
Livingston, “Vision-based Tracking with Dynamic Structured Light for Video See-through Augmented Reality”, 1998, University of North Carolina at Chapel Hill, North Carolina, USA. |
Miyagawa et al., “CCD-Based Range Finding Sensor”, Oct. 1997, pp. 1648-1652, vol. 44 No. 10, IEEE Transactions on Electron Devices. |
Pavlovic et al., “Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review”, Jul. 1997, pp. 677-695, vol. 19, No. 7, IEEE Transactions on Pattern Analysis and Machine Intelligence. |
Qian et al., “A Gesture-Driven Multimodal Interactive Dance System”, Jun. 2004, pp. 1579-1582, IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan. |
Rosenhahn et al., “Automatic Human Model Generation”, 2005, pp. 41-48, University of Auckland (CITR), New Zealand. |
Shao et al., “An Open System Architecture for a Multimedia and Multimodal User Interface”, Aug. 24, 1998, Japanese Society for Rehabilitation of Persons with Disabilities (JSRPD), Japan. |
Sheridan et al., “Virtual Reality Check”, Technology Review, Oct. 1993, pp. 22-28, vol. 96, No. 7. |
Stevens, “Flights into Virtual Reality Treating Real World Disorders”, The Washington Post, Mar. 27, 1995, Science Psychology, 2 pages. |
“Virtual High Anxiety”, Tech Update, Aug. 1995, pp. 22. |
Wren et al., “Pfinder: Real-Time Tracking of the Human Body”, MIT Media Laboratory Perceptual Computing Section Technical Report No. 353, Jul. 1997, vol. 19, No. 7, pp. 780-785, IEEE Transactions on Pattern Analysis and Machine Intelligence, Caimbridge, MA. |
Zhao, “Dressed Human Modeling, Detection, and Parts Localization”, 2001, The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. |
Office action for U.S. Appl. No. 12/718,232, mailed on Jun. 22, 2012, Rother et al, “Up-Sampling Binary Images for Segmentation”, 11 pages. |
“3.18. Stroke Path”. retrieved on Dec. 4, 2009 at <<http://docs.gimp.org/en/gimp-path-stroke.html>>, 2009, pp. 1-3. |
Garain, et al., “On Foreground-Background Separation in Low Quality Color Document Images”, retrieved on Dec. 3, 2009 at <<http://I3iexp.univ-lr.fr/madonne/publications/garain2005a.pdf>>, IEEE Computer Society, Proceedings of International Conference on Document Analysis and Recognition (ICDAR), 2005, pp. 585-589. |
Hertzmann, “Stroke-Based Rendering”, retrieved on Dec. 3, 2009 at <<http://www.dgp.toronto.edu/˜hertzman/sbr02/hertzmann-sbr02.pdf>>, Recent Advances in NPR for Art and Visualization, SIGGRAPH, vol. 3, 2002, pp. 1-31. |
Kang, et al., “A Unified Scheme for Adaptive Stroke-Based Rendering”, retrieved on Dec. 3, 2009 at <<http://www.cs.umsl.edu/˜kang/Papers/kang—tvc06.pdf>>, Springer Berlin, The Visual Computer, vol. 22, No. 9-11, Sep. 2006, pp. 814-824. |
Kolmogorov, et al., “Applications of parametric maxflow in computer vision”, IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, BR, Oct. 2007, pp. 1-8. |
Lempitsky, et al., “Image Segmentation with a Bounding Box Prior”, IEEE International Conference on Computer Vision (ICCV), Kyoto, JP, 2009, pp. 1-8. |
Liu, et al., “Paint Selection”, retrieved on Dec. 3, 2009 at <<http://yuwing.kaist.ac.kr/courses/CS770/reading/PaintSelection.pdf>>, ACM, Transactions on Graphics (TOG), vol. 28, No. 3, Article 69, Aug. 2009, pp. 1-7. |
Lu, et al., “Dynamic Foreground/Background Extraction from Images and Videos using Random Patches”, retrieved on Dec. 3, 2009 at <<http://books.nips.cc/papers/files/nips19/NIPS2006—0103.pdf>>, Conference on Neural Information Processing Systems (NIPS), 2006, pp. 351-358. |
Mannan, “Interactive Image Segmentation”, retrieved on Dec. 2, 2009 at <<http://www.c,s.mcgill.ca/˜fmanna/ecse626/InteractiveImageSegmentation—Report.pdf>>, McGill University, Montreal, CA, Course ECSE-626: Statistical Computer Vision, 2009, pp. 1-5. |
Mortensen, et al., “Intelligent Selection Tools”, retrieved on Dec. 4, 2009 at <<http://web.engr.oregonstate.edu/˜enm/publications/CVPR—00/demo.html>>, IEEE Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), Hilton Head Island, SC, vol. 2, 2000, pp. 776-777. |
Protiere, et al., “Interactive Image Segmentation via Adaptive Weighted Distances”, retrieved on Dec. 2, 2009 at <<http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.97.776&rep=rep1&type=pdf>>, IEEE Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, Aug. 2006, pp. 160-167. |
Tan, et al., “Selecting Objects With Freehand Sketches”, retrieved on Dec. 3, 2009 at <<http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.83.4105&rep=repl&type=pdf>>, IEEE Proceedings of International Conference on Computer Vision (ICCV), Vancouver, CA, vol. 1, Jul. 2001, pp. 337-345. |
Vicente, et al., “Joint optimization of segmentation and appearance models”, IEEE International Conference on Computer Vision (ICCV), Kyoto, JP, Oct. 2009, pp. 1-8. |
Number | Date | Country | |
---|---|---|---|
20110216976 A1 | Sep 2011 | US |