Automatic target segmentation by locally adaptive image thresholding

Author

Lie, Wen-Nung

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Yuan-Ze Inst. of Technol., Taoyuan, Taiwan

Volume

4

Issue

7

fYear

1995

fDate

7/1/1995 12:00:00 AM

Firstpage

1036

Lastpage

1041

Abstract

A locally adaptive thresholding algorithm, concerning the extraction of targets from a given field of background, is proposed. Conventional histogram-based or global-type methods are deficient in detecting small targets of possibly low contrast as well. The present research is notable for solving the mentioned problems by introducing (1) shape connectivity measure based on co-occurrence statistics for threshold evaluation; and (2) no-target identification procedure for modeling a local-processing paradigm. In this manner, thresholds are determined adaptively even in the presence of space-varying noise or clutter. Experiments show that the results are reliable and even outperform those that manual operations can achieve for global thresholding

Keywords

adaptive signal processing; clutter; feature extraction; image recognition; image segmentation; interference (signal); automatic target segmentation; clutter; co-occurrence statistics; extraction; local-processing paradigm; locally adaptive image thresholding; no-target identification procedure; shape connectivity measure; small targets; space-varying noise; threshold evaluation; Filters; Histograms; Image edge detection; Image processing; Image segmentation; Lungs; Manuals; Noise shaping; Shape measurement; Statistics;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/83.392347

Filename

392347