Implementation of parallel thinning algorithms using recurrent neural networks

1 January 1993

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks

Vol. 4 (1) , 142-147
https://doi.org/10.1109/72.182705

Abstract

The use of recurrent neural networks for skeletonization and thinning of binary images is investigated. The networks are trained to learn a deletion rule and they iteratively delete object pixels until only the skeleton remains. Recurrent neural network architectures that implement a variety of thinning algorithms, such as the Rosenfeld-Kak algorithm and the Wang-Zhang (WZ) algorithm, are presented. A modified WZ algorithm which produces skeletons that are intuitively more pleasing is introduced.

Keywords

This publication has 6 references indexed in Scilit:

Iterative neural networks for skeletonization and thinning
Published by SPIE-Intl Soc Optical Eng ,1991
Edge-labeling using dictionary-based relaxation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1990
A fast and flexible thinning algorithm
IEEE Transactions on Computers, 1989
A one-pass two-operation process to detect the skeletal pixels on the 4-distance transform
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
A fast parallel algorithm for thinning digital patterns
Communications of the ACM, 1984
On the Foundations of Relaxation Labeling Processes
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1983