I don't think you are likely to have very good results with video captured images without heavy processing.
In most cases I would say that you should ensure that the input image is at least 200dpi. You might be able to simulate this by combining many video frames. This is not an easy task. I would think poking around on google scholar might produce some papers on this. If you find a good solution I'd love to hear about it. -Rick On Mar 23, 1:33 am, hemanth p <[email protected]> wrote: > hi all, > Iam using tesseract on images(1024X860) captured from a video > I use the below code > convert $path/difference/$file.jpg yyy.bmp > mkbitmap -x -f 20 -t 0.5 yyy.bmp > convert yyy.pbm $path/bitonal/$file.tif > tesseract $path/bitonal/$file.tif $path/textFiles/$file > I convert the image > from .jpg to .bmp then do thresholding and filtering using "mkbitmap" > then convert it to tiff and pass that to tesseract and i use command > line invocation .Does anyone have an idea what changes can i make in > the code to increase the quality of output.please help -- 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.
