Image processing method and image processor

Abstract
An image processing method extracts line segment elements from grayscale captured images, so that line segments are extracted at high-speed without being influenced by contrast ratio, even if morphology processing is used. A selection processing select an area where continuous line segments possibly exist from the captured image and a morphology processing detect line segment elements in the selected area by scanning an operator. Line segments can be extracted in a plurality of directions at high-speed. Also by an extraction target area selection processing, an area of which contrast ratio is low, continuing from an area of which contrast ratio is high in the line segment growth direction is also extracted as one line segment.
Description

BRIEF DESCRIPTION OF THE DRAWINGS


FIG. 1 is a block diagram depicting the image processor according to an embodiment of the present invention;



FIG. 2 is a block diagram depicting the line segment extraction section in FIG. 1;



FIG. 3 shows an example of a captured image in FIG. 1 and FIG. 2;



FIG. 4 shows an example of an image after log filter processing in FIG. 3;



FIG. 5 shows an example of area selection from the image in FIG. 4;



FIG. 6 shows an example of an image after the morphology processing in FIG. 4;



FIG. 7 shows an example of an image after the extraction target selection processing in FIG. 6;



FIG. 8 shows an example of an image after log filter processing in FIG. 7;



FIG. 9 shows an example of an image after the binary processing in FIG. 8;



FIG. 10 is diagram depicting the log filter processing in FIG. 2;



FIG. 11 is a flow chart depicting the area selection processing and top hat summation processing in FIG. 2;



FIG. 12 is a diagram depicting the area selection processing in FIG. 11;



FIG. 13 is a diagram depicting the opening processing in FIG. 11;



FIG. 14 is diagram depicting the area selection processing and top hat summation processing in FIG. 11;



FIG. 15 is a diagram depicting the top hat summation processing in FIG. 11;



FIG. 16 is a flow chart depicting the extraction area selection processing in FIG. 2;



FIG. 17 is a diagram depicting the area specification processing in FIG. 16;



FIG. 18 is a diagram depicting the histogram creation and mask area and marker area detection processing in FIG. 16;



FIG. 19 area diagrams depicting the reconstruction processing in FIG. 16;



FIG. 20 area diagrams depicting the log filter processing in FIG. 2; and



FIG. 21 is diagram depicting the line segment extraction operation by the log filter processing in FIG. 20.


Claims
  • 1. An image processing method for extracting line segment elements from a grayscale captured image, comprising the steps of: binarizing an image according to said captured image and selecting an extraction area of said captured image from said binary image;executing morphology processing by scanning an operator on said selected extraction area in a plurality of directions and extracting linear elements from the extracted image in each direction; andextracting line segment elements from said extracted linear elements.
  • 2. An image processing method for extracting line segment elements from a grayscale captured image, comprising the steps of: executing morphology processing by scanning an operator over an image according to said captured image in a plurality of directions and extracting linear elements from the extracted images in each direction;extracting an area of which contrast ratio is relatively high and an area of which contrast ratio is relatively low from the image on which said morphology processing is performed; andextracting the linear elements in said area of which contrast ratio is relatively low, connecting to said area of which contrast ratio is relatively high, as the line segment elements.
  • 3. The image processing method according to claim 2, further comprising a step of binarizing an image according to said captured image, and selecting an extraction area of said captured image for which said morphology processing is executed.
  • 4. The image processing method according to claim 1, further comprising a step of creating an image according to said captured image by subjecting said grayscale captured image to smoothing and edge enhancement processing.
  • 5. The image processing method according to claim 1, further comprising: a step of subjecting said extracted line segment elements to smoothing and edge enhancement processing; anda step of creating line segment data by binarizing said smoothed and edge-enhanced line segment elements.
  • 6. The image processing method according to claim 1, wherein said step of executing morphology processing further comprises: a step of scanning said operator in a plurality of directions and creating an open processing image in each direction;a step of creating a top hat processing image in each of said directions from an image according to said captured image and the open processing image in each of said directions; anda step of extracting said linear elements by adding the top hat processing image in each of said directions.
  • 7. The image processing method according to claim 2, wherein said step of extracting line segment elements further comprises: a step of specifying an area of which contrast ratio of the image according to said captured image is possibly high;a step of extracting an area of which contrast ratio is relatively high and an area of which contrast ratio is relatively low for said specified area of said morphology-processed image; anda step of extracting linear elements in said area of which contrast ratio is relatively low, connecting to said area of which contrast ratio is relatively high, as the line segment elements.
  • 8. The image processing method according to claim 7, wherein said step of extracting the area further comprises: a step of calculating a brightness frequency histogram in said specified area; anda step of extracting said area of which contrast ratio is relatively high and area of which contrast ratio is relatively low from said frequency histogram.
  • 9. The image processing method according to claim 8, wherein said extraction step further comprises a step of extracting a mask area of which brightness level is relatively low as an area of which contrast ratio is relatively low, and a marker area of which brightness level is relatively high as an area of which contrast ratio is relatively high, from said frequency histogram.
  • 10. The image processing method according to claim 9, wherein said step of extracting said line segment elements further comprises a step of extracting said mask area having said marker area as said line segment element.
  • 11. The image processing method according to claim 2, further comprising a step of creating an image according to said captured image by subjecting said grayscale captured image to smoothing and edge enhancement processing.
  • 12. The image processing method according to claim 2, further comprising: a step of subjecting said extracted line segment elements to smoothing and edge enhancement processing; anda step of creating line segment data by binarizing said smoothed and edge-enhanced line segment elements.
  • 13. The image processing method according to claim 2, wherein said step of executing morphology processing further comprises: a step of scanning said operator in a plurality of directions and creating an open processing image in each direction;a step of creating a top hat processing image in each of said directions from an image according to said captured image and the open processing image in each of said directions; anda step of extracting said linear elements by adding the top hat processing image in each of said directions.
  • 14. An image processor for extracting line segment elements from a grayscale captured image, comprising: an image capturing device for capturing the image of a test subject; anda line segment extraction device for binarizing an image according to said captured image which is captured by said image capturing device, selecting an extraction area of said captured image, performing morphology processing by scanning an operator over said selected extraction area in a plurality of directions and extracting linear elements from the extracted image in each direction, and extracting line segment elements from said extracted linear elements.
  • 15. An image processor for extracting line segment elements from a grayscale captured image, comprising: an image capturing device for capturing the image of a test subject; anda line segment extraction device for executing morphology processing for extracting linear elements from the extracted images in each direction by scanning an operator over an image according to said captured image which is captured by said image capturing device in a plurality of directions, extracting an area of which contrast ratio is relatively high and an area of which contrast ratio is relatively low from the image on which said morphology processing is performed, and extracting the linear elements in said area of which contrast ratio is relatively low, connecting to said area of which contrast ratio is relatively high, as the line segment elements.
  • 16. The image processor according to claim 15, wherein said line segment extraction device binarizes an image according to said captured image and selects an extraction area of said captured image for which said morphology processing is executed.
  • 17. The image processor according to claim 14, wherein said line segment extraction device creates an image according to said captured image by subjecting said grayscale captured image to smoothing and edge enhancement processing.
  • 18. The image processor according to claim 14, wherein said line segment extraction device subjects the extracted line segment elements to smoothing and edge enhancement processing, and creates line segment data by binarizing the smoothed and edge-enhanced line segment elements.
  • 19. The image processor according to claim 14, wherein said line segment extraction device scans said operator in a plurality of directions, creates an open processing image in each direction, creates a top hat processing image in each of said directions from an image according to said captured image and the open processing image in each of said directions to execute said morphology processing for extracting said linear elements by adding the top hat processing image in each of said directions.
  • 20. The image processor according to claim 15, wherein said line segment extraction device extracts an area of which contrast ratio is relatively high and an area of which contrast ratio is relatively low for an area of which contrast ratio of said captured image is possibly high out of said morphology processed image, and extracts linear elements in said area of which contrast ratio is relatively low, connecting to said area of which contrast ratio is relatively high, as line segment elements.
  • 21. The image processor according to claim 20, wherein said line segment extraction device calculates a brightness frequency histogram in said specified area, and extracts said area of which contrast ratio is relatively high and area of which contrast ratio is relatively low from said brightness frequency histogram.
  • 22. The image processor according to claim 21, wherein said line segment extraction device extracts a mask area of which brightness level is relatively low as an area of which contrast ratio is relatively low, and a marker area of which brightness level is relatively high as an area of which contrast ratio is relatively high, from said frequency histogram.
  • 23. The image processor according to claim 22, wherein said line segment extraction device extracts said mask area having said marker area as said line segment elements.
  • 24. The image processor according to claim 15, wherein said line segment extraction device creates an image according to said captured image by subjecting said grayscale captured image to smoothing and edge enhancement processing.
  • 25. The image processor according to claim 15, wherein said line segment extraction device subjects said extracted line segment elements to smoothing and edge enhancement processing, and creates line segment data by binarizing said smoothed and edge-enhanced line segment elements.
  • 26. The image processor according to claim 15, wherein said line segment extraction device scans said operator in a plurality of directions and creates an open processing image in each direction, and creates a top hat processing image in each of said directions from an image according to said captured image and the open processing image in each of said directions, and extracts said linear elements by adding the top hat processing image in each of said directions.
Priority Claims (1)
Number Date Country Kind
2006-25690 Feb 2006 JP national