> I would like to get "VT 365 mL" from this image. What do I need to get correct text from this image?
It's more steps, but you could try extracting the bounding rectangle for each letter using the API and then using tesseract's single character mode (-psm 10) to process the results. Tesseract's training function would also give the coordinates for each character, for example: tesseract vt.png vt batch.nochop makebox Extracting the image for each character based on the coordinates, and then resizing for small images, would probably get everything. art -- 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/OFC12E2293.A1B17EAA-ON85257E16.007F87F8-85257E16.0083ACF8%40uwindsor.ca. For more options, visit https://groups.google.com/d/optout.
