Computer Vision: Python OCR and Object Detection Quick Starter

Description

This course is a quick starter for anyone who wants to explore optical character recognition (OCR), image recognition, object detection, and object recognition using Python without having to deal with all the complexities and mathematics associated with a typical deep learning process.Starting with an introduction to the OCR technology, you'll get your system ready for Python coding by installing Anaconda packages and the necessary libraries and dependencies. As you advance, you'll work with convolutional neural networks (CNNs), the Keras library, and pre-trained models such as VGGNet 16 and VGGNet 19, to perform image recognition with the help of sample images. The course then focuses on object recognition and shows you how to use MobileNet-SSD and Mask R-CNN pre-trained models to detect and label objects in a real-time live video from the computer's webcam as well as in a saved video. Toward the end, you'll learn how the YOLO model and the lite version, Tiny YOLO, fasten the process of detecting an object from a single image. By the end of the course, you'll have developed a solid understanding of OCR and the methods involved and gain the confidence to perform optical character recognition using Python with ease. All resources and code files for this course are placed here: https://github.com/PacktPublishing/Computer-Vision-Python-OCR-Object-Detection-Quick-Starter

What You Will Learn

Install Anaconda packages, dependencies, and libraries such as Tesseract, OpenCV, pillow
Get to grips with optical character recognition in Python using the tesseract library
Perform image recognition using VGGNet 16, VGGNet 19, ResNet, Inception, and Xception pre-trained models in the Keras library
Explore object recognition using MobileNet SSD, Mask R-CNN, YOLO
Achieve a perfect blend of speed and accuracy in object detection and recognition
Learn about optical character recognition with tesseract library and image recognition using Keras

Audience

This course is for beginners or anyone who wants to get started with Python-based OCR, image recognition, and object recognition.

Approach

If you are not from a Python-based programming background, the introductory section and examples will help you learn the basics of Python programming. You will then be able to progress through the subsequent sections that cover image recognition, object detection and recognition, and optical character recognition. With the help of detailed explanations and demonstrations, you'll learn topics such as Python assignments, flow-control, functions, and data structures.

Key Features

Understand the optical character recognition (OCR) technology * Explore convolutional neural networks pre-trained models for image recognition * Use Mask R-CNN pre-trained models and MobileNet-SSD for object detection

Github Repo

https://github.com/PacktPublishing/Computer-Vision-Python-OCR-Object-Detection-Quick-Starter

About the Author

Abhilash Nelson

Abhilash Nelson is a pioneering, talented, and security-oriented Android/iOS mobile and PHP/Python web application developer with more than 8 years of IT experience involving designing, implementing, integrating, testing, and supporting impactful web and mobile applications. He has a master's degree in computer science and engineering and has PHP/Python programming experience, which is an added advantage for server-based Android and iOS client applications. Abhilash is currently a senior solution architect managing projects from start to finish to ensure high quality and innovative and functional design.

Course Outline

1. Course Introduction and Table of Contents

2. Introduction to OCR Concepts and Libraries

3. Setting up Environment - Anaconda

4. Python Basics (Optional)

5. Tesseract OCR Setup

6. OpenCV Setup

7. Tesseract Image OCR Implementation

8. Optional: cv2.imshow() Not Responding Issue Fix

9. Introduction to CNN - Convolutional Neural Networks - Theory Session

10. Installing Additional Dependencies for CNN

11. Introduction to VGGNet Architecture

12. Image Recognition using Pre-Trained VGGNet16 Model

13. Image Recognition using Pre-Trained VGGNet19 Model

14. Image Recognition using Pre-Trained ResNet Model

15. Image Recognition using Pre-Trained Inception Model

16. Image Recognition using Pre-Trained Xception Model

17. Introduction to MobileNet-SSD Pretrained Model

18. Mobilenet SSD Object Detection

19. Mobilenet SSD Realtime Video

20. Mobilenet SSD Pre-saved Video

21. Mask RCNN Pre-trained model Introduction

22. MaskRCNN Bounding Box Implementation

23. MaskRCNN Object Mask Implementation

24. MaskRCNN Realtime Video

25. MaskRCNN Pre-saved Video

26. YOLO Pre-trained Model Introduction

27. YOLO Implementation

28. YOLO Real-time Video

29. YOLO Pre-saved Video

30. Tiny YOLO Pre-saved Video

31. Tiny YOLO Real-time Video