Optical Character Recognition (OCR) in Python

Course Curriculum

Chapter 1: Introduction

Lecture 1: Course content

Lecture 2: Introduction to OCR

Lecture 3: Course materials

Chapter 2: OCR with Tesseract

Lecture 1: Introduction to Tesseract

Lecture 2: Preparing the environment

Lecture 3: First text recognition

Lecture 4: Support for other languages

Lecture 5: Page segmentation mode (PSM)

Lecture 6: Page orientation detection

Lecture 7: Selection of texts 1

Lecture 8: Selection of texts 2

Lecture 9: Selection of texts 3

Lecture 10: Search using regular expressions

Lecture 11: Detections in natural scenarios

Chapter 3: Techniques for image pre-processing

Lecture 1: Grayscale

Lecture 2: Thresholding – intuition

Lecture 3: Simple thresholding

Lecture 4: Thresholding with Otsu method

Lecture 5: Adaptive thresholding

Lecture 6: Gaussian adaptive thresholding

Lecture 7: Color inversion

Lecture 8: Resizing – intuition

Lecture 9: Resizing – implementation

Lecture 10: Morphological operations – intuition

Lecture 11: Morphological operations – implementation

Lecture 12: Noise removal – intuition

Lecture 13: Noise removal – implementation

Lecture 14: Text recognition with OCR

Lecture 15: HOMEWORK

Lecture 16: Homework solution

Chapter 4: OCR with EAST for natural scenes

Lecture 1: EAST – introduction

Lecture 2: Pre-processing the image

Lecture 3: Loading the neural network

Lecture 4: Decoding the image 1

Lecture 5: Decoding the image 2

Lecture 6: Text recognition

Chapter 5: Training a custom OCR

Lecture 1: Importing the libraries

Lecture 2: MNIST 0-9 dataset

Lecture 3: Kaggle A-Z dataset

Lecture 4: Joining the datasets

Lecture 5: Pre-processing the data

Lecture 6: Building the neural network

Lecture 7: Training the neural network

Lecture 8: Evaluating the neural network

Lecture 9: Saving the neural network

Lecture 10: Testing with images

Lecture 11: Preparing the environment

Lecture 12: Pre-processing the image

Lecture 13: Contour detection

Lecture 14: Processing the detections 1

Lecture 15: Processing the detections 2

Lecture 16: Character recognition

Lecture 17: Problems with 0 and O, 1 and l, 5 and S

Lecture 18: Problems with undetected texts

Chapter 6: Natural scenarios with EasyOCR

Lecture 1: Preparing the environment

Lecture 2: Text recognition

Lecture 3: Writing the results on the image

Lecture 4: Other languages – French and Chinese

Lecture 5: Text recognition (background)

Chapter 7: OCR in videos

Lecture 1: Preparing the environment

Lecture 2: Video settings

Lecture 3: Processing the video

Lecture 4: OCR with EAST and Tesseract

Lecture 5: OCR with EasyOCR

Chapter 8: Project 1: Searching for specific terms

Lecture 1: Preparing the environment

Lecture 2: Text recognition

Lecture 3: Searching for texts

Lecture 4: Word cloud

Lecture 5: Named entity recognition

Lecture 6: Search for texts in images

Lecture 7: Saving the results

Chapter 9: Project 2: Scanner + OCR

Lecture 1: Preparing the environment

Lecture 2: Contour detection

Lecture 3: Perspective transformation

Lecture 4: OCR with Tesseract

Lecture 5: Improving image quality

Lecture 6: Putting all together

Chapter 10: Project 3: License plate reading

Lecture 1: Pre-processing the image

Lecture 2: Text recognition

Lecture 3: Improving image quality

Chapter 11: Extra content 1: artificial neural networks

Lecture 1: Biological fundamentals

Lecture 2: Single layer perceptron

Lecture 3: Multilayer perceptron – sum and activation functions

Lecture 4: Multilayer perceptron – error calculation

Lecture 5: Gradient descent

Lecture 6: Delta parameter

Lecture 7: Updating weights with backpropagation

Lecture 8: Bias, error, stochastic gradient descent, and more parameters

Chapter 12: Extra content 2: convolutional neural networks