Re: tesseract testing suite

On Sun, Feb 24, 2013 at 12:20 AM, Nick White nick.wh...@durham.ac.ukwrote: On Fri, Feb 22, 2013 at 03:20:49PM +, Nick White wrote: On Sun, Jun 03, 2012 at 10:27:23PM +0100, zdenko podobny wrote: it looks like it is ASCII only oriented (at least in report non-ASCII are malformed...),

Re: lib and all in win 64bit

If you still have the details can you send them to me as well please? malkif at hotmail.co.uk. Thanks On Thursday, 20 December 2012 02:44:13 UTC, beigon...@gmail.com wrote: I have built the 64bit libs and dlls in windows.I want to share with others. If you want ,send me emails. -- -- You

Errors that might be decreasing my OCR precision

Hello all, I've noticed that OCRing a treated image the script yields some errors that affect its precision. First I treat the image with the script to enhance it and make it grayscale. textcleaner -g -e normalize -s 1 scan.tif scan2.tif Then, I OCR it with tesseract and get the following

How to treat TIF images before scanning using an enhancer script

Hi all, If I scan a page with 300 dpi black and white with one scanner, I have noticed that the image is still saved with RGB color. I wonder what is the best practice for improving OCR success. There is a script called TEXTCLEANER done by Fred which is located at

how can I read these images

hello there! I want to read the numbers below using tesseract and imageMagick,but after tried lots of time,I got Empty page in img1,and wrong resault in img2. I'm new in ocr.i changed the image to black-white ,color depth is 8,and use nobatch digits in tesseract.please help! thanks a lot!

Re: Problem using Tesseract to training character image for chi

Thanks for the information. Actually, the original process I did follow the wiki instruction closely. The example given above is just an example to illustrate the problem I faced. The original process I have taken looks like this. Training text (chi.ming.exp0.txt): - from

How to add a new font? am i doing it right?

im new to tesseract and i want it train it in order to optimize the recognisation of certain numbers. so i thought, id would be the easiest to add a new font to the english data so i created certain tiff files and use qt box editor(https://github.com/zdenop/qt-box-editor) to create and edit the

Tesseract Training - Empty Page

im new to tesseract and i wanted to train it in order to improve my results. i need to recognise numbers only, so i thought adding the numbers as a new font to english should work fine. i created tiff files containing pictures of the numbers and created the box files with