I had developed an OCR which was completely dedicated to font type & its size. I just used to calculate the height & width of the font & find out the ratio which I compare with the database value & then choose the font.
I want to extend the logic to all types of fonts & sizes. I want to do it using Artifical Intelligence. I have seen the Coding of some of the open-source OCR. But, it won't be useful.
Please guide me on the way I should follow/start to developer my own OCR. I want to make it an Oper Source Project for the whole world & also want to provide API for further project-specific development in Java.
Thanks in Advance.