Computer Vision - OCR using Python

Description

In this course, you will learn :

• A crash course in OCR Architecture, Commercial Solutions, and Industry Use Cases.
• Learn how to use OpenCV and Deep Learning Models to implement OCR - Text Detection.
• To implement OCR - Text Recognition, use Tesseract and EasyOCR.
• Use OCR - Text Labeling with Spacy and Regular Expression.
• Apply Noise Removal Techniques such as Thresholding, Rescaling, Dilation, Erosion, and Deskewing using OpenCV and Tesseract.
• Learn how to use Flask to create web-based applications such as Business Card Recognition and KYC Digitization for OCR.
• Create OCR Solutions for Invoice Processing, Text Labeling, and XML Output, as well as Vehicle Nameplate Recognition.
• CTPN and EAST Model implementation executable code for text detection and recognition.
• Learn how to train CTPN and EAST Deep Learning Models on the ICDAR dataset.
• Understand the Image Basics and apply it for Image Processing

Syllabus :

• OCR Starter - OCR Architecture
• Setting up Environment - Ubuntu, Windows
• Image Basics - Pixels, Kernel, Image Properties
• Text Detection - CTPN, EAST, Noise Removal, Segmentation
• Text Recognition - EasyOCR, Tesseract, PyTesseract, CTPN, EAST
• Text Labelling - RegEx, Spacy
• Model Training - CTPN, EAST on ICDAR Dataset​​​​​
• 5 Live Projects