OCR

Computer Vision

View project on GitHub

Computer Vision

This repository consists scripts for OCR (Optical Character Recognition) of white paper receipts. It includes Cropping (removing background), Improving Quality (if image is blurred), Binarization, Segmentation and Prediction.

Tools/Technologies Used:

Python, OpenCV, Ocropus and Tesseract.

Flowchart (How to use?)

References

  1. Sharpening and Convolutions, OpenCv, https://www.pyimagesearch.com/2016/07/25/convolutions-with-opencv-and-python/
  2. Gaussian Sharpening, Theory, http://biomedpharmajournal.org/vol7no2/image-sharpening-by-gaussian-and-butterworth-high-pass-filter/
  3. https://en.wikipedia.org/wiki/Unsharp_masking#Digital_unsharp_masking
  4. Gaussian Sharpening, OpenCV, https://stackoverflow.com/a/4993701
  5. Laplacian Sharpening Theory, http://www.idlcoyote.com/ip_tips/sharpen.html.
  6. Laplacian, https://stackoverflow.com/questions/39619222/laplacian-sharpening-grey-image-as-result
  7. Modified Laplacian, https://stackoverflow.com/a/51138416
  8. Lossy Problem, https://stackoverflow.com/a/52442741
  9. Google Vision, https://www.quora.com/How-does-Google-Vision-API-works
  10. 4-point transform algorithm, https://www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
  11. Document Scanner, https://www.pyimagesearch.com/2014/09/01/build-kick-ass-mobile-document-scanner-just-5-minutes/
  12. Detect and Crop, https://www.quora.com/How-can-I-detect-an-object-from-static-image-and-crop-it-from-the-image-using-openCV
  13. Crop a Contour, https://stackoverflow.com/questions/28759253/how-to-crop-the-internal-area-of-a-contour
  14. Ocropus Part-A, http://www.danvk.org/2015/01/07/finding-blocks-of-text-in-an-image-using-python-opencv-and-numpy.html
  15. Ocropus Part-B, https://www.danvk.org/2015/01/09/extracting-text-from-an-image-using-ocropus.html
  16. Ocropus Part-C, http://www.danvk.org/2015/01/11/training-an-ocropus-ocr-model.html