This book is intended for anyone who wishes to explore the core of scene text and object detection and recognition techniques to comprehend the purpose of a given scene image. Introduction on various features, feature extraction and description techniques, learning algorithms, performance measurement metrics and classical datasets is presented. Therefore, the book can be considered as a general guide for anyone who is beginning to work on machine learning applications that require principally object and scene text detection and recognition. Moreover, the book highlights major problems with fundamental components of the problem which are being used currently.