![]() ambiguous letters such as i versus l: surprisingly, Tesseract makes a ton of incongruous mistakes that lead me to believe there is no feature analysis whatsoever - for example a 'y' may get mapped to 'g', even though there is 0% chance of that based on a wide open gap on top. For example VV is usually corrected back to W - but there are hundreds more cases obvious mistakes: this is by far the largest category of corrections we make. spacing: we don't trust any spacing determination by Tesseract and reevaluate every space indicated by Tesseract for possible elimination or consider every two letters for a possible space insertion It's really a long list of approaches, including: IPhone / Android business card reader app. ABBY powers two iPhoneĪpps made by German company - Business Card Reader (by Shape Services)Īnd Card Reader (by xRoot Software) - and of course ABBY's own Installing the free version of ScanBizCards. ![]() You can also test instead on your Android or iPhone mobile device by when done testing please delete the test images from this demoĪccount (or get your own online account). click that image then "Image Editor" on top and OCR it If you tested on something *like* a business card (sparse text), not a Geared towards recognizing text on business cards so it would be best ScanBizCards is case #3 around Tesseract 3.01. However, if you compare Tesseract + image processing + heuristics &Ĭorrections, Tesseract actually beats ABBY hands down. Without applying any post-Tesseract heuristic, ABBY may have anģ. If you compare Tesseract and ABBY on a clean (processed) image, Processing is not an issue and refer to case 2 below.Ģ. Produced (for example) by a flatbed scanner, the lack of image Preprocessing to it, ABBY wins (because Tesseract's image processing ![]() If you compare Tesseract and ABBY on a same image, without applying
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |