A novel generalized entropy and its application in image thresholding

被引：55

作者：

Nie, Fangyan ^{[1
,2
]}

Zhang, Pingfeng ^{[2
]}

Li, Jianqi ^{[1
]}

Ding, Dehong ^{[1
,2
]}

机构：

[1] Hunan Univ Arts & Sci, Hunan Prov Cooperat Innovat Ctr Construct & Dev, Dongting Lake Ecol Econ Zone, Changde 415000, Hunan, Peoples R China

[2] Hunan Univ Arts & Sci, Coll Comp Sci & Technol, Changde 415000, Hunan, Peoples R China

来源：

SIGNAL PROCESSING | 2017年 / 134卷

基金：

中国国家自然科学基金;

关键词：

Image segmentation; Histogram thresholding; Generalized entropy; Entropic parameter; TSALLIS ENTROPY; HISTOGRAM;

D O I：

10.1016/j.sigpro.2016.11.004

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

As a technique for image segmentation, thresholding has been successfully utilized in various image processing tasks. In this paper, a novel generalized entropy, that can handle the additive/nonextensive information exist in physical system by a tunable entropic parameter r, is introduced in image segmentation. A new criterion for thresholding and algorithm based on this entropy are described in detail. The performance of the presented method is compared with the classical entropy-based thresholding methods and some state-of-the-art methods. Experiments on nondestructive testing images, infrared images, and some other real images are conducted. The experimental results show the effectiveness of the proposed method.

引用

页码：23 / 34

页数：12

共 18 条

[11] Threshold selection using Renyi's entropy [J].