I use opencv for most of pre-processing tasks, El miércoles, 12 de septiembre de 2012 17:14:05 UTC+2, sk escribió: > > For image pre processing what sw should use, i'm going to implement > tesseract with my project, what is the best way to produce good results, > can i convert image quality as good and give to produce better result? > > > On Wednesday, 30 December 2009 03:19:34 UTC+5:30, Haiku Automation wrote: >> >> Your net scraping to OCR and republish/migrate to another real estate >> system... Or so it seems. You have originated 72 dpi images, and >> they are not going to give you squat for results. 150x150 is the real >> minimum you will need, and 200x200 or better yet 300x300 dpi are >> best. I have scanned up to 400+ dpi, and found anything over 300 dpi >> really doesn't result in significant improved results. You need to >> train a system much more tightly with low DPI, so find a tool that >> will do it with your expert help (mapping a image region to a >> particular unicode). >> >
-- 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
