Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

I suppose you have been already registered image of the page ... I mean page alignment

If tables don't have borders it's bit hard .. you could try searching for text as standard paragraph and save as separate images all that fails your check

If tables has border you could try If it so table should have lines a 0 or 90 degrees +/- small tolerance

  • (template matching)[http://docs.opencv.org/doc/tutorials/imgproc/histograms/template_matching/template_matching.html] using an image of crossing lines as template to detect cells and a 4 template for the 4 boundary corners.
  • (hough line)[http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/hough_lines/hough_lines.html] to detect horiz and vert lines than check/group if/which lines are compatible with a table... vert lines have of a table should have same Y in X,Y space, while horizz lines should have same X coordinate.

    Once you have table boundaries coordinates you can easily define a rect roi on your page image and save it to a new file.

I suppose you have been already registered image of the page ... I mean page alignment

If tables don't have borders it's bit hard .. you could try searching for text as standard paragraph and save as separate images all that fails your check

If tables has border you could try If it so table should have lines a 0 or 90 degrees +/- small tolerance

  • (template matching)[http://docs.opencv.org/doc/tutorials/imgproc/histograms/template_matching/template_matching.html] template matching using an image of crossing lines as template to detect cells and a 4 template for the 4 boundary corners.
  • (hough line)[http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/hough_lines/hough_lines.html] hough line to detect horiz and vert lines than check/group if/which lines are compatible with a table... vert lines have of a table should have same Y in X,Y space, while horizz lines should have same X coordinate.

    Once you have table boundaries coordinates you can easily define a rect roi on your page image and save it to a new file.

I suppose you have been already registered image of the page ... I mean page alignment

If tables don't have borders it's bit hard .. you could try searching for text as standard paragraph and save as separate images all that fails your check

If tables table has border you could try If it so table should have lines a at 0 or 90 degrees +/- small tolerancetolerance, than you could try:

  • template matching using an image of crossing lines as template to detect cells and a 4 template templates for the 4 boundary corners.
  • hough line to detect horiz and vert lines lines, than check/group if/which lines are compatible with a table... vert lines have of a table should have same Y in X,Y cartesian space, while horizz lines should have same X coordinate.X.

    Once you have table boundaries coordinates you can easily define a rect roi on your page image and save it to a new file.