Im using Terrasact and have noticed that for my purposes, it keeps repeating mistakes on certain characters - having dabbed into OCR via Neural Nets in the past, I figured some additional training would be simple enough. Reading the Training wiki though, I'm left with more questions than answers.
For example... In one image, the word "gesso" is written. However Tesseract misreads the g as a Q, which leads it to read the image as "QBSSO" In another image, the word "imbed" is written. However Tesseract somehow reads the i as an E. I have similar issues with it reading a lower case L as well as a lowercase R. Have tried increasing image size and DPI count to no avail (doubling image size seemed to drastically lower accuracy). -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en.
