:) I wonder why I didn't come up with that idea before doing the complex ImageJ processing.
Am Montag, 14. Juli 2014 11:06:30 UTC+2 schrieb Alex Ryan: > > Paul, > > Thankfully the RGB values of the colors of the pixels I want arent used > anywhere else in the area of the image I want scanned. So yeah I simply > just turn all other colors white, and turn the colors I want black. > > On Sunday, July 13, 2014 10:24:06 AM UTC-7, Paul wrote: >> >> Do you simply filter out any color other than brown and white or is your >> algorithm more sophisticated? If it is, it would be great if you could >> share the basic idea. >> >> Paul >> >> Am Samstag, 12. Juli 2014 00:06:29 UTC+2 schrieb Alex Ryan: >>> >>> just wanted to follow up >>> >>> I wrote some simple code to preprocess the image because I realized I >>> will be doing basically the same image every time so its foolish to try and >>> use Tesseracts binaziration technique which was designed for a different >>> and more general purpose. So basically I just turned every pixel white that >>> wasnt a pixel that contained part of a letter, and when I send that to >>> tesseract I get flawless output with the language data I trained. Thanks so >>> much for the replies Paul and Nick, I learned a lot and it put me in the >>> right direction! cheers! >>> >> -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b8283ae4-0a01-4f1a-8ee7-b6059dd8b598%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
