Thinning methodologies for pattern recognition
著者
書誌事項
Thinning methodologies for pattern recognition
（Series in machine perception and artificial intelligence / editors, H. Bunke, P.S.P. Wang, v. 8）
World Scientific, c1994
大学図書館所蔵 件 / 全22件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes bibliographical references
内容説明・目次
内容説明
Thinning is a technique widely used in the pre-processing stage of a pattern recognition system to compress data and to enhance feature extraction in the subsequent stage. It reduces a digitized pattern to a skeleton so that all resulting branches are 1 pixel thick. The method seems easy at first and has many advantages, however after two decades of intensive research, it has been found to be very challenging due to the difficulties in programming computers to do it.This collection of 15 papers by leading scientists working in the area examines the theoretical and experimental aspects of thinning methodologies. The authors have addressed the problems faced, compared their performance results with others, and assessed the challenges ahead. Researchers will find the volume helpful in shedding light on difficult issues and stimulating further research in the area.
目次
- A new thinning algorithm based on controlled deletion of edge regions, G. Dimauro et al
- graph-based thinning for binary images, S. Suzuki et al
- a parallel thinning algorithm using the bounding boxes techniques, S. Ubeda
- invariant thinning, U. Eckhardt & G. Maderlechner
- analytical comparison of thinning, Y.Y. Zhang & P.S.P. Wang
- methologies for evaluating thinning algorithms for character recognition, R. Plamondon et al
- automatic comparison of skeletons by shape matching methods, L. Lam & C.Y. Suen
- binary and gray-value skeletons - metrics and algorithms, B.J.H. Verwer et al. (Part contents).
「Nielsen BookData」 より
