My current project involves transcribing texts in pdf into text files, and I first tried putting the image file directly into OCR program (tesseract) and it didnt' do that well.
The original image files are old news papers, basically, and have some background noises, which I am sure tesseract has problem with. So I am trying to use some image preprocessing before feeding it into tesseract. Is there any suggestion for open source image preprocessing engine that fits well to this situation??? And instructions on how to use it would be even more appreciated !
Image Preprocessing before OCR process
image processingocrtesseract
Related Solutions
An alternative approach would be to extract features (keypoints) using the scale-invariant feature transform (SIFT) or Speeded Up Robust Features (SURF).
You can find a nice OpenCV code example in Java, C++, and Python on this page: Features2D + Homography to find a known object
Both algorithms are invariant to scaling and rotation. Since they work with features, you can also handle occlusion (as long as enough keypoints are visible).
Image source: tutorial example
The processing takes a few hundred ms for SIFT, SURF is bit faster, but it not suitable for real-time applications. ORB uses FAST which is weaker regarding rotation invariance.
The original papers
Tesseract is very good on clean input text (like your example) if you tinker a bit. some suggestions:
- Before automating, start with tesseract at the command line
- Restrict your character set if possible (e.g. take a look in /usr/local/share/tessdata/configs at ./digits - configure it for English characters upper/lower case etc) and provide it as a command line argument
- Only use PNG or TIFF images (TIFF for older versions) as JPG introduces artefacts
- Upsample the image so your text is larger than the current tiny font. Tesseract lines >10 pixel high characters (if memory serves), it certainly performs worse with tiny characters
- No need to do thresholding if you're bi-level already but it won't hurt if you do and you can see exactly the same image that tesseract will see
I'll check back here to see if I can help more but do join the tesseract mailing list, they're really helpful.
Sidenote - I have some patches for pytesseract which I ought to publish for getting characters & confidences & words via the API (which wasn't possible a couple of months back). Shout if they might be useful.
Best Answer
I never heard of an "image preprocessing engine" for that purpose, but you can take a look at OpenCV (Open Source Computer Vision Library) and implement your own "pre-processing engine". OpenCV is a computer vision library that offers many features to perform image processing.
One interesting thing you might want test as a preprocessing step is apply a threshold to the image to remove noises and stuff. Anyway, I've talked about this kind of stuff in this thread.