Vision With Direction: A Systematic Introduction to Image Processing And Computer Vision

This general textbook presents in a systematic way the modern signal processing concepts used in computer vision and image analysis. For the first time in a textbook on image processing, single direction, group direction, corners and edges, Hough transforms, and motion estimation are developed in a principled way using one single concept: direction tensors. The topics include Hilbert spaces, Fourier transform, scale analysis, direction fields, structure tensor, motion tensor, Hough transform, grouping, and segmentation. The topics are richly illustrated by color graphics and applications, including biometric person authentication, texture analysis, optical character recognition, motion estimation and tracking. Directional signal processing, increasingly a crucial element of computer vision and for which there exists neural circuits in human vision, is presented in depth by use of tensors.