Thresholding Using Relaxation

1 September 1981

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. PAMI-3 (5) , 598-606
https://doi.org/10.1109/tpami.1981.4767152

Abstract

If a picture contains dark objects on a light background (or vice versa), the objects can be extracted by thresholding, i.e., by classifying the pixels into ``light'' and ``dark'' classes. If the picture is noisy, so that the object and background gray level populations overlap, there will be errors in the thresholded output. A relaxation process can be used to reduce these errors; we classify the pixels probabilistically, and then adjust the probabilities for each pixel, based on its neighbors' probabilities, with light reinforcing light and dark dark. When this adjustment process is iterated, the dark probabilities become very high for pixels that belong to dark regions, and vice versa, so that thresholding becomes trivial.

Keywords

This publication has 11 references indexed in Scilit:

Relaxation: Evaluation and Applications
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1981
Blob Detection by Relaxation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1981
A New Probabilistic Relaxation Scheme
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1980
Some experiments on LANDSAT pixel classification using relaxation operators
Computer Graphics and Image Processing, 1980
A Relaxation Method for Multispectral Pixel Classification
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1980
Neighbor gray levels as features in pixel classification
Pattern Recognition, 1980
Image segmentation by clustering
Proceedings of the IEEE, 1979
Some experiments in image segmentation by clustering of local feature values
Pattern Recognition, 1979
Scene Labeling by Relaxation Operations
IEEE Transactions on Systems, Man, and Cybernetics, 1976
Programming pattern recognition
Published by Association for Computing Machinery (ACM) ,1955