视觉机制模拟中的局部参数自组织映射方法  

Self-Organizing Map of Local Parameters for Visual Mechanism Simulation

作　　者：马煜[1] 顾晓东[1] 汪源源[1] 

机构地区：[1]复旦大学电子工程系,上海200433

出　　处：《应用科学学报》2009年第3期247-252,共6页Journal of Applied Sciences

基　　金：国家"973"重点基础研究发展计划基金(No.2005CB724303);国家自然科学基金(No.60671062)资助项目

摘　　要：为模拟视觉系统对彩色场景进行初步处理的机制,提出一种局部参数自组织映射方法.以局部颜色均值、局部颜色对比度以及位置作为特征,用自组织映射进行分类,实现图像分割、边缘检测和轮廓分离等功能.对仿真及自然彩色图像的实验结果表明,该方法能并行实现上述功能,将具有不同类型特征的部分映射到输出空间的不同位置,符合视觉系统的特征映射和并行处理的特性.该方法为研究和模拟视觉系统的机制提供了参考,也可用于图像处理中的多任务并行处理.A self-organizing map of local parameters is proposed to simulate the initial visual processing mechanism for color scenes. The method employs local color mean values, local color contrasts, and positions as features, and uses a self-organizing map for classification to deal with multiple tasks such as image segmentation, edge detection, and contour separation. Experimental results for both synthetic and natural color images show that the method can perform these tasks simultaneously. It maps image parts with different features to different positions of the output space, conforming to the feature mapping and simultaneously processing characteristics of the visual system. This method can be used to investigate and simulate visual mechanisms, and handle multiple image processing tasks.

关 键 词：视觉机制模拟 自组织映射 图像分割 边缘检测 轮廓分离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]