EARLY ORIENTATION SELECTION—INFERRING TRACE, TANGENT, AND CURVATURE FIELDS

作     者：STEVEN W. ZUCKER 

作者机构：Canadian Institute for Advanced Research Computer Vision and Robotics Laboratory Department of Electrical Engineering McGill University Montréal Québec Canada 

出 版 物：《International Journal of Pattern Recognition and Artificial Intelligence》 

年 卷 期：1988年第2卷第3期

页      面：443-457页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Computer vision Orientation selection Curve detection Relaxation Edge detection Texture 

摘      要：Orientation selection is the inference of orientation information out of images. It is one of the foundations on which other visual structures are built, since it must precede the formation of contours out of pointillist data and surfaces out of surface markings. We take a differential geometric view in defining orientation selection and develop algorithms for actually doing it. The goal of these algorithms is formulated in mathematical terms as the inference of a vector field of tangents (to the contours), and the algorithms are studied in both abstract and computational forms. They are formulated as matching problems, and algorithms for solving them are reduced to biologically plausible terms. We show that two different matching problems are necessary, the first for 1-dimensional contours (which we refer to as Type I processes) and the second for 2-dimensional flows (or Type II processes).