Difference between revisions of "Kifu: Go game record (kifu) generator"

From ElphelWiki
Jump to: navigation, search
Line 4: Line 4:
  
 
[[Image:kifu_region.jpg]]
 
[[Image:kifu_region.jpg]]
 +
  
 
2. The selection is rectified using a perspective correction matrix that OpenCV can also compute,
 
2. The selection is rectified using a perspective correction matrix that OpenCV can also compute,
  
 
[[Image:kifu_rectify.jpg]]
 
[[Image:kifu_rectify.jpg]]
 +
  
 
3. OpenCV find lines in the rectified selection and we compute the intersections for each detected line segment.
 
3. OpenCV find lines in the rectified selection and we compute the intersections for each detected line segment.
Line 14: Line 16:
  
 
[[Image:kifu_Intersections.jpg]]
 
[[Image:kifu_Intersections.jpg]]
 +
  
 
4. After, we round the results to group close neighbour points, and compute or approximate the center of each group (ie: intersection).
 
4. After, we round the results to group close neighbour points, and compute or approximate the center of each group (ie: intersection).
 +
  
 
5. Finally we can verify the intersection count and relative alignment to validate the region or restart at step 1 with another threshold
 
5. Finally we can verify the intersection count and relative alignment to validate the region or restart at step 1 with another threshold
Line 26: Line 30:
 
it is easy to compute the image coordinates of a played stone
 
it is easy to compute the image coordinates of a played stone
  
−
[[Image:kifu_diff.jpg]]
+
[[Image:kifu_threshold.jpg]] [[Image:kifu_sums.jpg]]
  
−
[[Image:kifu_threshold.jpg]]
 
  
−
[[Image:kifu_vsum.jpg]]
 
−
 
−
[[Image:kifu_hsum.jpg]]
 
  
 
'''Stone detection:'''
 
'''Stone detection:'''
Line 50: Line 50:
  
 
'''Methods for mapping the coordinates:'''
 
'''Methods for mapping the coordinates:'''
 +
  
 
"2.2 Perspective transformation with two vanishing points"
 
"2.2 Perspective transformation with two vanishing points"
Line 74: Line 75:
  
 
'''Links:'''
 
'''Links:'''
 +
  
 
irc://irc.freenode.net/#kifu
 
irc://irc.freenode.net/#kifu
 +
  
 
http://www.sourceforge.net/projects/kifu
 
http://www.sourceforge.net/projects/kifu
 +
  
 
http://opencvlibrary.sourceforge.net/
 
http://opencvlibrary.sourceforge.net/
 +
  
 
Photointerpretation and Small Scale Stereoplotting with Digitally Rectified Photographs with Geometrical constraints:
 
Photointerpretation and Small Scale Stereoplotting with Digitally Rectified Photographs with Geometrical constraints:
 
http://cipa.icomos.org/fileadmin/papers/potsdam/2001-21-gf01a.pdf
 
http://cipa.icomos.org/fileadmin/papers/potsdam/2001-21-gf01a.pdf
 +
  
 
Vision par Ordinateur:
 
Vision par Ordinateur:
 
http://www-prima.imag.fr/jlc/Courses/2002/DEA-IVR.VO/DEA-IVR.VO.S2.pdf
 
http://www-prima.imag.fr/jlc/Courses/2002/DEA-IVR.VO/DEA-IVR.VO.S2.pdf
 +
  
 
Projective Mappings for Image Warping:
 
Projective Mappings for Image Warping:
 
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7803
 
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7803
 +
  
 
http://sciences.ch/htmlfr/geometrie/geometrieprojective01.php
 
http://sciences.ch/htmlfr/geometrie/geometrieprojective01.php

Revision as of 17:49, 18 August 2008

Goban and Grid Detection:

1. The input image is filtered and thresholded and a big quadrilateral shape containing many smaller quadrilaterals is selected, sorting contours detected with OpenCV.

Kifu region.jpg


2. The selection is rectified using a perspective correction matrix that OpenCV can also compute,

Kifu rectify.jpg


3. OpenCV find lines in the rectified selection and we compute the intersections for each detected line segment.

(The test image below hasnt been rectified before)

Kifu Intersections.jpg


4. After, we round the results to group close neighbour points, and compute or approximate the center of each group (ie: intersection).


5. Finally we can verify the intersection count and relative alignment to validate the region or restart at step 1 with another threshold


Image change detection:

Using vertical and horizontal RGB components sums of a thresholded difference between a reference image and the current one,

it is easy to compute the image coordinates of a played stone

Kifu threshold.jpg Kifu sums.jpg


Stone detection:

When a stone is played it overlaps 1 grid square on a corner, 2 on the borders and 4 in the center.

Computing horizontal and vertical pixel sums for each grid cell or around each intersection can tell where the stone is played and reveal the color of the stone, being darker or brighter than the empty intersection region.

The intersection can also be seen on the difference image when the stone is white, that could also be used to detect the stone color.



Methods for mapping the coordinates:


"2.2 Perspective transformation with two vanishing points" (pages 2 and 3, equations 7 and 10)

http://cipa.icomos.org/fileadmin/papers/potsdam/2001-21-gf01a.pdf


Inverse homography and plane image rectification (page 14)

http://www-prima.imag.fr/jlc/Courses/2002/DEA-IVR.VO/DEA-IVR.VO.S2.pdf


"Inferring Projective Mappings" (page 3)

http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7803

with related java and C source code here: http://www.developpez.net/forums/showthread.php?t=591698



Links:


irc://irc.freenode.net/#kifu


http://www.sourceforge.net/projects/kifu


http://opencvlibrary.sourceforge.net/


Photointerpretation and Small Scale Stereoplotting with Digitally Rectified Photographs with Geometrical constraints: http://cipa.icomos.org/fileadmin/papers/potsdam/2001-21-gf01a.pdf


Vision par Ordinateur: http://www-prima.imag.fr/jlc/Courses/2002/DEA-IVR.VO/DEA-IVR.VO.S2.pdf


Projective Mappings for Image Warping: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7803


http://sciences.ch/htmlfr/geometrie/geometrieprojective01.php

Retrieved from "https://wiki.elphel.com/index.php?title=Kifu:_Go_game_record_(kifu)_generator&oldid=5144"