基于PCNN的小波域超声医学图像去噪方法  

Method of medical ultrasonic image de-noising based on PCNN in the wavelet domain

作　　者：郭业才[1,2] 王绍波[3] 

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001 [2]南京信息工程大学电子与信息工程学院,江苏南京210044 [3]安徽理工大学医学院,安徽淮南232001

出　　处：《安徽大学学报（自然科学版）》2010年第5期54-59,共6页Journal of Anhui University(Natural Science Edition)

基　　金：全国优秀博士学位论文作者专项资金资助项目(200753);江苏省高等学校自然科学基金资助项目(08KJB510010);江苏省"六大人才高峰"培养对象资助项目(2008026);安徽省高等学校自然科学基金资助项目(KJ2009A096)

摘　　要：在分析小波去噪和脉冲耦合神经网络(pulse coupled neural networks,简称为PCNN)去噪优缺点的基础上,提出一种基于PCNN的小波域超声医学图像去噪方法(a method of medical ultrasonicimage de-noising based on PCNN in the Wavelet Domain,简称为PCNN-WD).该方法先对小波系数进行相应的预处理,然后应用PCNN在小波域中修改小波系数,以达到去噪的目的,并且该方法能够自动地设定阈值和修改小波系数的步长.实验结果表明,该方法可以有效地去除斑点噪声,并很好地保留图像细节和图像边缘.A method of medical ultrasonic networks） in the Wavelet Domain （PCNN-WD） image de-noising based on PCNN （pulse coupled neural was proposed, via analyzing the characteristics of wavelet transform and PCNN. In the method, first, the wavelet coefficients were processed. After corresponding pretreatment, the wavelet coefficients were modified by PCNN in the wavelet domain so that the speckle noises could be removed, and the amplification coefficient of threshold and the step by which the coefficients of wavelet were modified could be automatically set in this method. The experiment resuhs showed that the detail information and the image edge were being reserved when the speckle noises were being effectively removed by WT-PCNN.

关 键 词：脉冲耦合神经网络 小波变换 超声医学图像 斑点噪声 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]