I resized the image (double the original size) and got the results that were 100% correct. Thanks for the tip.
However, I'm wondering how I could automate the process. That is, without manually viewing a given image, how can I pre-process it (including resizing) so it is suitable for OCR? I don't think that I could blindly blow up each image because some of them could already be large enough. I've checked some on-line OCR services (including the ones that use tesseract) and they seem to be doing an excellent job. So, somehow they are 'smart' enough to know what to do with input images. I'd appreciate any pointers. Thanks. On Friday, October 24, 2014 5:20:27 PM UTC-4, Robert Melton wrote: > > Is that tiny file the actual file size you are running OCR on? If so, > scale up the image and I am guessing results will improve greatly. > > On Fri, Oct 24, 2014 at 2:25 PM, BDristan <[email protected] <javascript:>> > wrote: > > I'm quite new to tesseract. I just tried to OCR an image as follows: > > > > tesseract LockBits.tif LockBits -l eng > > > > The output text was pretty messed up. I ran tesseract 3.02 on Win7. > > > > I then run an on-line OCR and got a perfect result. > > > > Could someone please give me some hints on how to improve OCR with > > tesseract. > > > > Attached is an image file that I used. > > > > Thanks. > > > > -- > > 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] <javascript:>. > > To post to this group, send email to [email protected] > <javascript:>. > > 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/0274edc9-8744-489b-bcf5-0eabc9dbd5c0%40googlegroups.com. > > > > For more options, visit https://groups.google.com/d/optout. > > > > -- > Robert Melton | http://robertmelton.com > -- 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/953af195-b995-4122-8c36-e1078815ba13%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
