首页 | 本学科首页   官方微博 | 高级检索  
     

基于视觉模型的图像边缘检测算法
引用本文:张永平,郑南宁,赵荣椿.基于视觉模型的图像边缘检测算法[J].电子学报,2000,28(1):101-103.
作者姓名:张永平  郑南宁  赵荣椿
作者单位:1. 陕西师范大学数学系,西安 710062;2. 西安交通大学人工智能与机器人研究所,西安 710049;3. 西北工业大学计算机系,西安 710072
基金项目:国家自然科学基金!(NO.69735010)
摘    要:文章提出了一种基于视觉模型的图像边缘检测算法.作者采用具有反馈和前项控制连接的侧抑制模型进行图像信息进行处理,用零阶和二阶厄米特(Hermite)函数的组合产生系统的控制模板,组合系数通过梯度下降学习算法确定.这种以生物视觉感知机理为基础的神经计算方法可有效地均衡滤除噪声和增强边缘,同时将系统高维参数的学习问题转化为对少数几个参数的确定,降低了问题的维数和计算的复杂性.

关 键 词:边缘检测  厄米特函数  视觉模型  神经计算  
文章编号:0372-2112 (2000) 01-0101-03
收稿时间:1998-10-09

An Algorithm of Image Edge Detection Based on Visual Model
ZHANG Yong-ping,ZHENG Nan-ning,ZHAO Rong-chun.An Algorithm of Image Edge Detection Based on Visual Model[J].Acta Electronica Sinica,2000,28(1):101-103.
Authors:ZHANG Yong-ping  ZHENG Nan-ning  ZHAO Rong-chun
Affiliation:1. Dept.of Mathematics,Shanxi Normal University,Xi'an 710062,China;2. The Institute of Artificial Intelligence and Robotics,Xi'an Jiaotong University,Xi'an 710049,China;3. Dept.of Computer Science,Northwestern Polytechnic University,Xi'an 710072,China
Abstract:An algorithm of edge detection based on visual model is Proposed. In which image information is processed by using a lateral inhibitory modal with feedback and forward coned connections. The forward templates are generated by a combination of zero- and Second- Order Hermite functions with scale parameters. Corresponding combination coefficients are trained by neural computing. Such method based on biological visual mechanisms can efficiently perform balancing of noise reduction and edge enhancement. Furthermore,the dimension and complexity of Problems are reduced.
Keywords:the detection  Hermite function  visual model  neural computing
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》下载全文
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