Hi Ankit, Did you make any progress on this, or is this still an open question?
On Tuesday, February 5, 2013 5:24:11 AM UTC-5, ankit rawat wrote: > > Hi > We need to perform handwritten character recognition (English alphabets, > numerals). > We installed both Tesseract-OCR and Ocropus and tested a handwritten image > document with both the engines. With their default existing training data, > both the engines gave unsatisfactory results, however Tesseract gave much > better result than Ocropus. Speed-wise also Tesseract was giving faster > results. In some of the posts in this forum, people have suggested that > Ocropus gives better results for handwriting recognition than Tesseract. > However our initial test suggests otherwise. > Also we need an OCR engine which would update its training set on the fly, > on a wrong recognition of a character. > > Our problem is now following: > 1. If we train both the OCRs with sufficient amount of training data, how > do Ocropus and Tesseract fare against each other in that scenario ? > 2. Does any of Ocropus or Tesseract has support for updation of training > data whenever a bad character recognition is made ? > > Thanks in advance! > Ankit > -- -- 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 --- 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]. For more options, visit https://groups.google.com/groups/opt_out.
