If you want to deal with uneven lighting then you should rather look at thresholding techniques. I had good success with an Android app using Tesseract and OpenCV and using a configuration of Otsu thresholding. More at http://docs.opencv.org/3.1.0/d7/d4d/tutorial_py_thresholding.html
On 25 May 2016 at 12:38, Aung Si Min Htet <pianistjohnli...@gmail.com> wrote: > Dear Arno, I have been searching for how to implement or run ImageMagick > bash script on android code. Can you please guide me on how to run the > script. I am new to both ImageMagick and bash script. I will be really > thankful if anyone can help me. > > On Friday, January 6, 2012 at 12:11:31 AM UTC+6:30, Sven Pedersen wrote: >> >> Thanks, Arno! That looks like a very well designed script. >> --Sven >> >> On Thu, Jan 5, 2012 at 10:03 AM, Arno Teigseth <arno...@gmail.com> wrote: >> > -----BEGIN PGP SIGNED MESSAGE----- >> > Hash: SHA1 >> > >> > On 04/01/12 20:14, Robert T wrote: >> >> I'm developing an open source Android app that uses Tesseract 3.01 >> >> for OCR by passing Tesseract images captured by a phone or tablet >> >> camera. >> >> >> >> The OCR is working adequately for small segments of text--like a >> >> few words--but uneven illumination seems to lower the recognition >> >> quality with larger text input. Because the input comes from the >> >> device camera, there's a lot of shadows and glare. >> > >> > Hi I had the same problem - took pictures of all the pages in a book, >> > and had trouble with this. >> > >> > Tried out >> > >> > http://www.fmwconcepts.com/imagemagick/textcleaner/index.php >> > >> > and that worked well. >> > >> > just ran >> > "./textcleaner badimg.jpg goodimg.jpg" >> > >> > and that was it :D >> > >> > >> > for auto-recognition, deskewing etc I ran unpaper >> > >> > http://unpaper.berlios.de/ >> > >> > >> > This made it possible to OCR 1500 pages basically without much trouble >> :D >> > >> > my 2 cents :) >> > >> > best >> > Arno >> > -----BEGIN PGP SIGNATURE----- >> > Version: GnuPG v1.4.11 (GNU/Linux) >> > Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ >> > >> > iEYEARECAAYFAk8FydkACgkQEMIGVCc8BjALEQCff/n4acxqfL9J5ZrCNLPrJxYx >> > FcIAn1w6/ZVPax2UyMXeC4rSZztsFfqZ >> > =gP0W >> > -----END PGP SIGNATURE----- >> > >> > -- > 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 tesseract-ocr+unsubscr...@googlegroups.com. > To post to this group, send email to tesseract-ocr@googlegroups.com. > Visit this group at https://groups.google.com/group/tesseract-ocr. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/20462c69-3100-41a5-9b50-a520d1c2aff6%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/20462c69-3100-41a5-9b50-a520d1c2aff6%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAORW5vgmcB8Xm61nmi8FeqDEwtmE07J_PZjgbav_27gs4sVp3A%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
