/OCR

Optical Character Recognition using Google's Tesseract engine

Primary LanguagePythonMIT LicenseMIT

OCR-Text

Optical Character Recognition using Google's Tesseract engine

Learn open cv from openCV documentation

Learn more about Tesseract here

trans_color function

  1. Load the example image and convert it to grayscale

  2. Check preprocess to apply thresholding on the image

  3. Load the image as a PIL/Pillow image

  4. Additional processing such as spellchecking for OCR errors or NLP should be applied

In order to run this script

  1. Open terminal
  2. Run command in this sequence : $ python ocr.py -image image.jpg

(Applying Gaussian Blur/Thresholding) $ python ocr.py -image image.jpg -preprocess blur

OUTPUT

image

OUTPUT

image