In today’s world, computer vision technology is embedded in many of our everyday products and this industry is evolving fast by constantly creating new solutions. This technology advancement has created the need of skilled professionals who can design robust OCR solutions. The course “Computer Vision – OCR using Python” provides you a complete understanding of Optical Character Recognition (OCR) for Data Extraction from Images and PDF using Python. The course is quite comprehensive and guides you to create technical solutions on most relevant OCR uses cases in the industry.
The Key Topics covered in the Course are:
- OCR Architecture
- Pixels and Image Basics
- Image Properties
- Kernel and Feature Map
- Preprocessing Techniques (Binarisation, Thresholding, Rescaling)
- Noise Removal Techniques (Morphology, Dilation, Erosion, Blurring, Orientation, Deskewing, Borders, Perspective Transformation)
- Image Segmentation
- EasyOCR
- PyTesseract Operations
- Tesseract
- Named Entity Recognition
- Spacy for Named Entity Recognition
- Regular Expression for Text and Dates
- CTPN Model for Text Detection & Text Recognition
- EAST Model for Text Detection & Text Recognition Invoice Processing OCR Solution with python code
- Invoice Structured Output in XML Format Solution with python code
- Vehicle Nameplate OCR Solution with python code
- Business Card Recognition OCR Solution with python code
- KYC Digitization OCR Solution with python code
- Training of CTPN and EAST on ICDAR – SIROE Dataset
Check out the course at https://www.udemy.com/course/computer-vision-ocr-using-python/
