The goal of computer vision (CV) research is to provide computers with human-like perception capabilities so that they can sense the environment, understand the sensed data, take appropriate actions, and learn from this experience in order to enhance future performance. The field has evolved from the application of classical pattern recognition and image processing methods to advanced techniques in image understanding, like model-based and knowledge-based vision. In recent years, there has been an increased demand for computer vision systems to address "real-world" applications, such as navigation, target recognition, manufacturing, photointerpretation, remote sensing, etc. This unique monograph details the way machine learning, a field concerned with the temporal improvement of computer algorithms and systems, can help create robust, flexible vision techniques for optimal functioning in real-world scenarios. Enriched by many concrete examples and illustrations, it is an indispensable reference for industry engineers and academics working in machine vision and AI.