I have a couple of questions about the TessBaseAPI... A little bit of background - I've compiled Tesseract for the PXA270 ARM processor and am looking to make the recognition as fast as possible even if it compromises on accuracy. I'd like to input a file that's already in binary format similar to phototest.tif and suppress Tesseract from looking for words. Is it possible to omit the test for IsValidWord using SetVariable in some way?
Are there any other tricks to speeding up recognition at the expense of accuracy? For example, on 677MHz Pentium III, running Tesseract on phototest.tif takes a little over a second, but on the 520MHz ARM processor it takes almost 20 seconds... Any advice will be greatly appreciated! Thanks in advance, Ben -- 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.
