摘要
传统基于灰色关联分析的图像分割算法存在很多错分、漏分的情况。为此,提出一种基于灰色关联分析和径向基函数(RBF)网络的分割算法。采用量子遗传算法对RBF网络进行优化,通过灰色关联分析提取待处理图像的边缘信息,识别噪声点与非噪声点,以此作为优化后RBF网络的输入,利用该网络良好的逼近能力纠正错分和漏分像素点。实验结果证明,与传统算法相比,该算法的分割效果更优,且能进一步提高抗噪性能。
Traditional image segmentation based on grey relational analysis makes many mistakes.For this problem,this paper gives a complex optimization method based on grey relational analysis and Radial Basis Function（RBF） neural network.It optimizes RBF neural network by Quantum Genetic Algorithm（QGA）.In this way,the approach performance of RBF neural network is improved.It extracts the edge information by grey relational analysis,identifies which pixel is noise,and gives this information to the optimized RBF neural network.Its good approach performance can rectify the mistake mentioned above.Experimental results show that the outcome of image segmentation procedure is better,and eliminates the noise more exactly.
出处
《计算机工程》
CAS
CSCD
2012年第1期225-226,235,共3页
Computer Engineering
基金
科技部国际科技合作基金资助项目(2009DFA12870)
关键词
图像分割
灰色关联分析
径向基函数网络
量子遗传算法
边缘信息
image segmentation
grey relational analysis
Radial Basis Function（RBF） network
Quantum Genetic Algorithm（QGA）
edge information
