5.1. Introduction

The design and implementation of a complete artificial vision system is a daunting challenge. The computer vision community has made significant progress in many areas, but the ultimate goal is still far off. A key component of a general computer vision system is a computational framework that can address a wide range of problems in a unified way. We have developed such a framework over the past several years [40], which is the basis of the augmented framework presented in this chapter. It is based on a data representation formalism that uses tensors and an information propagation mechanism termed tensor voting.

Most computer vision problems are inverse problems, because the imaging process maps 3D "world" features onto 2D arrays ...

Get Emerging Topics in Computer Vision now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.