What Tom said. However, let's assume all your variables are constant - resolution has to be just what you have, file format has to be TIF etc. then you can use a divide and conquer distributed computing pattern. That is, grab a machine that holds a queue of work and then make that queue farm out the work to worker machines - you scale to as many worker machines as brings your problem within tolerance. A great and relatively inexpensive platform to do this on would be AWS. It's how Pixar movies are rendered (render farms). That is, if nothing else can be optimised, stop trying to vertically scale and change to horizontal scaling.
All that said, I would start by answering Tom's questions as your resolution may be higher than you need for the recognition problem you have or your machine may be way too underpowered or maybe you just want a 10% speed up, etc. you didn't really say too much. On Sunday, 19 April 2015 13:23:20 UTC+1, James Worldprogram wrote: > > During processing of tiff files, which are having *600 - 700 pages* from > Tesseract OCR engine with hocr option, we monitored that files are taking > around *40 - 50 minutes*. > > We monitored that it is so much time for processing large files. > > Do we have any way to speed up the process? > > Following command is using: - > > <Drive>:\Tesseract-OCR>tesseract.exe "Source_Tiff_File" "Destination_File" > hocr > > -- 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/8c64cf18-f9ad-4f29-8935-4dc8a59eccde%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
