基于图像单调特性的盲源分离算法  

Blind source separation algorithm based on monotone property of image

作　　者：李雪松[1] 张天骐[1] 杨柳飞[1] 代少升[1] 

机构地区：[1]重庆邮电大学信号处理与片上系统研究所,重庆400065

出　　处：《计算机应用研究》2008年第12期3665-3668,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(10776040;60602057);新世纪优秀人才支持计划资助项目(NCET);重庆市科委自然科学基金资助项目(CSTC;2006BB2373);重庆市教委自然科学基金资助项目(KJ060509);重庆邮电大学自然科学基金资助项目(A2006-04;A2006-86)

摘　　要：针对日常生活中两幅图像会出现混叠的情况,根据数字化图像灰度值范围有界特性和一般信号盲源分离的方法,提出了一种利用分离比值函数单调特性达到图像盲分离目的的新算法。新算法根据接收端的观察信号确定信号之间的比值函数,通过函数的单调性分析找到分离矩阵的关键值,从而实现图像的盲源分离。本算法无须先验知识,没有统计相关性的约束条件,而且分离速度快、效果明显,实验仿真结果验证了算法的有效性。This paper presented a new method for analytical solution to image blind source separation based on monotone property of separation ratio function aiming to the two pictures in the daily life would appear to blend and pursuant to the digital image gray value range to have the edge property and common signal blind source separate method. The new arithmetic used observation signal of the receiver and obtained ratio function of signals, analysed functional monotonicity and found key value of separation matrix, realized image blind source separation. This arithmetic has no use for calculate a prior knowledge, there is no the constraint condition which statistical correlation, and separate speed quickly, effect obvious. The simulation result demonstrates the usefulness of arithmetic.

关 键 词：图像盲源分离 灰度值 信号比值 单调性 统计相关 

分 类 号：TN911.7[电子电信—通信与信息系统]