Practical Computer Vision

A practical guide designed to get you from basics to current state of art in computer vision systems.

Key Features

• Master the different tasks associated with Computer Vision and develop your own Computer Vision applications with ease
• Leverage the power of Python, Tensorflow, Keras, and OpenCV to perform image processing, object detection, feature detection and more
• With real-world datasets and fully functional code, this book is your one-stop guide to understanding Computer Vision

Book Description

In this book, you will find several recently proposed methods in various domains of computer vision. You will start by setting up the proper Python environment to work on practical applications. This includes setting up libraries such as OpenCV, TensorFlow, and Keras using Anaconda. Using these libraries, you'll start to understand the concepts of image transformation and filtering. You will find a detailed explanation of feature detectors such as FAST and ORB; you'll use them to find similar-looking objects.

With an introduction to convolutional neural nets, you will learn how to build a deep neural net using Keras and how to use it to classify the Fashion-MNIST dataset. With regard to object detection, you will learn the implementation of a simple face detector as well as the workings of complex deep-learning-based object detectors such as Faster R-CNN and SSD using TensorFlow. You'll get started with semantic segmentation using FCN models and track objects with Deep SORT. Not only this, you will also use Visual SLAM techniques such as ORB-SLAM on a standard dataset.

By the end of this book, you will have a firm understanding of the different computer vision techniques and how to apply them in your applications.

What you will learn

• Learn the basics of image manipulation with OpenCV
• Implement and visualize image filters such as smoothing, dilation, histogram equalization, and more
• Set up various libraries and platforms, such as OpenCV, Keras, and Tensorflow, in order to start using computer vision, along with appropriate datasets for each chapter, such as MSCOCO, MOT, and Fashion-MNIST
• Understand image transformation and downsampling with practical implementations.
• Explore neural networks for computer vision and convolutional neural networks using Keras
• Understand working on deep-learning-based object detection such as Faster-R-CNN, SSD, and more
• Explore deep-learning-based object tracking in action
• Understand Visual SLAM techniques such as ORB-SLAM

Who This Book Is For

This book is for machine learning practitioners and deep learning enthusiasts who want to understand and implement various tasks associated with Computer Vision and image processing in the most practical manner possible. Some programming experience would be beneficial while knowing Python would be an added bonus.

Table of Contents

1. A fast introduction to Computer vision
2. Libraries, Development platform and Datasets
3. Image filtering and Transformations in OpenCV
4. Application of Feature Extraction Extraction technique
5. Introduction to Advanced Features
6. Feature based object detection
7. Object Tracking and Segmentation
8. 3D Computer Vision
9. Appendix A
10. Appendix B

Abhinav Dadhich is a Researcher and Application Developer on deep learning at Abeja Inc. Tokyo. His day is often filled with designing deep learning models for computer vision applications like image classification, object detection, segmentation etc. His passion lies in understanding and replicating human vision system. Previously, he has worked on 3D mapping and robot navigation. He has graduated with B.Tech. in EE from IIT Jodhpur, India and has done his M.Eng. in Information Science from NAIST, Japan. He puts up notes and codes for several topics on GitHub profile.