Mastering Computer Vision with TensorFlow 2.x

Apply neural network architectures to build state-of-the-art computer vision applications using the Python programming language
 Key Features Gain a fundamental understanding of advanced computer  vision and neural network models in use today  Cover tasks such as  low-level vision, image classification, and object detection  Develop  deep learning models on cloud platforms and optimize them using  TensorFlow Lite and the OpenVINO toolkitBook Description
Computer  vision allows machines to gain human-level understanding to visualize,  process, and analyze images and videos. This book focuses on using  TensorFlow to help you learn advanced computer vision tasks such as  image acquisition, processing, and analysis. You'll start with the key  principles of computer vision and deep learning to build a solid  foundation, before covering neural network architectures and  understanding how they work rather than using them as a black box. Next,  you'll explore architectures such as VGG, ResNet, Inception, R-CNN,  SSD, YOLO, and MobileNet. As you advance, you'll learn to use visual  search methods using transfer learning. You'll also cover advanced  computer vision concepts such as semantic segmentation, image inpainting  with GAN's, object tracking, video segmentation, and action  recognition. Later, the book focuses on how machine learning and deep  learning concepts can be used to perform tasks such as edge detection  and face recognition. You'll then discover how to develop powerful  neural network models on your PC and on various cloud platforms.  Finally, you'll learn to perform model optimization methods to deploy  models on edge devices for real-time inference. By the end of this book,  you'll have a solid understanding of computer vision and be able to  confidently develop models to automate tasks.
What you will learn  Explore methods of feature extraction and image retrieval and visualize  different layers of the neural network model  Use TensorFlow for various  visual search methods for real-world scenarios  Build neural networks  or adjust parameters to optimize the performance of models  Understand  TensorFlow DeepLab to perform semantic segmentation on images and DCGAN  for image inpainting  Evaluate your model and optimize and integrate it  into your application to operate at scale  Get up to speed with  techniques for performing manual and automated image annotationWho this  book is for
This book is for computer vision professionals, image  processing professionals, machine learning engineers and AI developers  who have some knowledge of machine learning and deep learning and want  to build expert-level computer vision applications. In addition to  familiarity with TensorFlow, Python knowledge will be required to get  started with this book.
Table of Contents Computer Vision and  Tensorflow Fundamentals Content Recognition using Local Binary Pattern  Face Recognition and Tracking using Viola Jones Algorithm & OpenCV  Deep learning on images Neural Network Architecture & Models Visual  Search using Transfer Learning Object Detection using YOLO Semantic  Segmentation and Neural Style Transfer Action Recognition using  Multitask Deep Learning Object Classification and Detection using RCNN  Deep Learning on Edge Devices with GPU/CPU Optimization Cloud Computing  Platform for Computer Vision