首页 | 本学科首页   官方微博 | 高级检索  
     

基于脉冲耦合神经网络和遗传算法的图像增强
引用本文:李国友,李惠光,吴惕华. 基于脉冲耦合神经网络和遗传算法的图像增强[J]. 测试技术学报, 2005, 19(3): 304-309
作者姓名:李国友  李惠光  吴惕华
作者单位:燕山大学,电气工程学院,河北,秦皇岛,066004;河北建材学院,河北,秦皇岛,066004;燕山大学,电气工程学院,河北,秦皇岛,066004;河北省科学院,河北,石家庄,050000
基金项目:国家自然科学基金资助项目(60274023)
摘    要:提出了基于脉冲耦合神经网络(PCNN-Pulse Coupled Neural Network)与遗传算法的图像增强算法.对PCNN模型进行了改进使之更适用于图像处理,并利用遗传算法的全局寻优能力自动搜索图像的最佳灰度阈值,再对图像进行处理.该算法既可有效地去除噪声,又能根据图像灰度性质自动选取最佳阈值,并对自适应分割后图像进行不同的灰度变换,从而实现了图像的自适应增强.试验结果表明,该算法显著提高了图像增强效果.

关 键 词:脉冲耦合神经网络  去噪  遗传算法  阈值选择  图像增强
文章编号:1671-7449(2005)03-0304-06
收稿时间:2004-12-05
修稿时间:2004-12-05

The Image Enhancement Based on Modified Pulse Coupled Neural Network and Genetic Algorithm
LI Guo-you,LI Hui-guang,WU Ti-hua. The Image Enhancement Based on Modified Pulse Coupled Neural Network and Genetic Algorithm[J]. Journal of Test and Measurement Techol, 2005, 19(3): 304-309
Authors:LI Guo-you  LI Hui-guang  WU Ti-hua
Abstract:The algorithm of automatic image enhancement based on PCNN and Genetic Algorithm was proposed. A PCNN model was improved in order to be more suitable for image processing and optimal gray threshold was automatic searched by the global optimization capability of Genetic Algorithm before image was processing. The arithmetic can not only remove noises effectively, but also can automaticly select the best threshold based on the image gray characteristic. In addition, different gray switch function is taken for the adaptively segmented image. So, image enhancement is accomplished adaptively. The experiment results indicated that remarkable effect of image enhancement was gained.
Keywords:PCNN   remove noises   genetic algorithm   threshold selecting   image enhancement
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号