The language that I am working on has characters stacking and overlapping one on top of another. some stack characters touch, some dont. So, I used a simple way using Vertical histogram, horizontal histogram and connected component to separate the characters. Those that are inseparable, i trained in tesseract as it is.
On Tue, Sep 29, 2009 at 2:03 PM, xbshao <[email protected]> wrote: > > btw, > > I am wondering how to do the segmentation. Does your C code > automatically locate the characters in the image, or manually crop the > image with UI? > > any help would be appreciate, thx in advance > > On 9月29日, 下午3时47分, 现彪 邵 <[email protected]> wrote: >> Im new to Tesseract-OCR. >> >> Add "system("tesseract_path/tesseract image_file output_file");" at >> the end >> of you C program should be the easiest way. >> >> You can also add you C program into Tesseract-OCR. Just write the >> pixel data >> of you segmented image into the buffer of tesseract. >> >> On 9月29日, 下午3时18分, "Svetlin Nakov" <[email protected]> wrote: >> >> >> >> > You have the entire source code. You can modify it to fit your needs. >> >> > I usually take the tessearct source code as base and remove anything I >> > don't >> > need and write additional functionality in its main method. >> >> > Svetlin Nakov >> > Managing Partner >> > Consulting and Information Technology Agencyhttp://www.citagency.eu >> >> > -----Original Message----- >> > From: [email protected] >> > [mailto:[email protected]] >> >> > On Behalf Of Tenzin Dendup >> > Sent: Tuesday, September 29, 2009 9:26 AM >> > To: [email protected] >> > Subject: Using tesseract-ocr from c/c++ programs >> >> > Hi, >> >> > I have trained characters of language in tesseract and i have also >> > written a simple program in C to do segmentation. Once the >> > segmentation is done, how can i use tesseract-ocr from within my c >> > program to do recognition. Do I have to run the tesseract command from >> > within C or is there some other way? I am using tesseract-ocr 2.04 on >> > Debian GNU/Linux. >> >> > --Tenzin- 隐藏被引用文字 - >> >> > - 显示引用的文字 -- 隐藏被引用文字 - >> >> - 显示引用的文字 - > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
