Computer Vision Methods for Fast Image Classification and Retrieval

The book presents selected methods for accelerating image retrieval and classification in large collections of images using what are referred to as ¿hand-crafted features.¿ It introduces readers to novel rapid image description methods based on local and global features, as well as several techniques for comparing images. Developing content-based image comparison, retrieval and classification methods that simulate human visual perception is an arduous and complex process. The book¿s main focus is on the application of these methods in a relational database context. The methods presented are suitable for both general-type and medical images. Offering a valuable textbook for upper-level undergraduate or graduate-level courses on computer science or engineering, as well as a guide for computer vision researchers, the book focuses on techniques that work under real-world large-dataset conditions. von Scherer, Rafal