This sounds more like a job for OpenCV or some other machine vision library.
Tom On Tuesday, May 10, 2016 at 3:13:36 AM UTC-4, Piotr Gryta wrote: > > Hi everyone, > I am devoloping a Java application to vectorize a raster image. One of the > steps is symbol recognition and I was hoping to train Tesseract to find > them and return their pixel coordinates. > My question is: > 1) Is it possible to make a dictionary of symbols to avoid detection of > letters contained in English dictionary? > 2) What steps should I perform? > I managed to make a box files for my training image, but later I get an > Empty page! error. > I am glad for any suggestion, > Piotrek > > Here is a sample image of tree sybols which I would like to train to check > if it works: > https://gyazo.com/85a1db80f92f2df44625875bcf20d37d > -- 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/3813ef66-cb7f-4d66-8c9a-bba07c43966f%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
