Efficient edge detection in digital images using a cellular neural network optimized by differential evolution algorithm

被引:58
作者
Bastuerk, Alper [1 ]
Guenay, Enis [2 ]
机构
[1] Erciyes Univ, Dept Comp Engn, TR-38039 Kayseri, Turkey
[2] Erciyes Univ, Dept Elect & Elect Engn, TR-38039 Kayseri, Turkey
关键词
Cellular neural networks; Cloning template; Differential evolution algorithm; Edge detection; TEMPLATE; NOISY;
D O I
10.1016/j.eswa.2008.01.082
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A cellular neural network (CNN) based edge detector optimized by differential evolution (DE) algorithm is presented. Cloning template of the proposed CNN is adaptively tuned by using simple training images. The performance of the proposed edge detector is evaluated on different test images and compared with popular edge detectors from the literature. Simulation results indicate that the proposed CNN operator outperforms competing edge detectors and offers Superior performance in edge detection in digital images. (C) 2008 Elsevier Ltd. All rights reserved.
引用
收藏
页码:2645 / 2650
页数:6
相关论文
共 39 条