Hi, I'm trying to use tesseract with text cutted in small images. The aim of this test is to check if performance of tesseract could be improved like this.
Unfortunately, I've seen that results differ according image size. I have downloaded 2 images on this site : interface2-720x576.tif_otsu_19_no_border.pgm and interface2-720x576.tif_otsu_19_4pix_border.pgm Those files are output from the OTSU algorithm. The only difference between them is that in the second image, I have cutted my text with 4 pixels more all around. Results are very different : "Finding Neverland Now ON DEMAND" for 1st file (good result) "- FindingmIan;i Nov; gnu an" for 2nd file Is there any reason to explain this large difference? Thanks --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
