I wish to remove the horizontal bar (Shirorekha) from the word to get characters from the following image, for character recognition. Any ideas as to how can I do that. I tried to use Hough Transforms for line and then looked for longest line. Blue line is the longest, but this too is a vertical line. I do not get results better than this. Since the line is crooked and not straight I do not get good results. Please help.
In order to take out the Hindi language characters, you don't need to remove the horizontal line. The horizontal line is a part of the character, also there are some characters in the hindi language that use small or no horizontal line. So, this means that to separate characters you will need to slice them vertically.
You can search the 'Matras' system for reference of what to consider before vertical slicing.
You need to define the acceptable [theta][1] range. See the below example:
[H,T,R] = hough(BW,'Theta',85:0.01:89.99);
