A new image thresholding method based on relative entropy

Author

Zhu, Hui ; Fu, Zhizhong ; Li, Zaiming

Author_Institution

Coll. of Commun. & Inf. Eng., Univ. of Electron. Sci. & Technol., Chengdu, China

Volume

1

fYear

2002

fDate

29 June-1 July 2002

Firstpage

634

Abstract

This paper analyses the superiority of choosing the two dimensional histogram of an image as the feature space instead of the co-occurrence matrix of an image. Based on the two dimensional histogram of an image, relative entropy is used to measure the difference between an image and its thresholded image. The vector which minimizes the relative entropy is selected as the threshold vector. Experimental results show that compared with other thresholding method, our method can achieve better thresholded results and is of strong robustness.

Keywords

entropy; image segmentation; matrix algebra; probability; statistical analysis; 2D histogram; feature space; image co-occurrence matrix; image segmentation; image thresholding method; probability distributions; relative entropy; threshold vector; thresholded image; thresholding method; two dimensional histogram; Educational institutions; Entropy; Histograms; Image analysis; Image segmentation; Information analysis; Paper technology; Pixel; Probability distribution; Space technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Circuits and Systems and West Sino Expositions, IEEE 2002 International Conference on

Print_ISBN

0-7803-7547-5

Type

conf

DOI

10.1109/ICCCAS.2002.1180698

Filename

1180698