首页 | 本学科首页   官方微博 | 高级检索  
     

基于视觉非线性的图象分割新方法
引用本文:张天序,彭嘉雄.基于视觉非线性的图象分割新方法[J].计算机学报,1993,16(4):248-256.
作者姓名:张天序  彭嘉雄
作者单位:华中理工大学图象识别与人工智能研究所,国家模式识别实验室,北京 100080 武汉 430074
摘    要:本文分析了在感知目标与其背景时Otsu判别准则与人类视觉机理间的不一致性,并根据视觉的非线性和适应性原理提出了新的目标图象分割计算模型和算法.实验结果表明,与传统的分割法相比,该方法具有优良的从低反差图象中抽取目标的性能.

关 键 词:图象分割  视觉非线性  计算机视觉

A NEW APPROACH TO IMAGE SEGMENTATION BASED ONVISUAL NONLINEARITY
Zhang Tianxu and Peng JiaxiongInstitute of Pattern Recognition and artificial Intelligence,Huazhong University af Science and Technology,Wuhan National Laboratory of Pattern Recognition,Beijing.A NEW APPROACH TO IMAGE SEGMENTATION BASED ONVISUAL NONLINEARITY[J].Chinese Journal of Computers,1993,16(4):248-256.
Authors:Zhang Tianxu and Peng JiaxiongInstitute of Pattern Recognition and artificial Intelligence  Huazhong University af Science and Technology  Wuhan National Laboratory of Pattern Recognition  Beijing
Affiliation:Zhang Tianxu and Peng JiaxiongInstitute of Pattern Recognition and artificial Intelligence,Huazhong University af Science and Technology,Wuhan130074 National Laboratory of Pattern Recognition,Beijing 100080
Abstract:It is analysed in this paper that the behavior of the human vision system (HVS) differs from Otsu's discriminant criterion when perceiving an object and its background. 'Based on the visual nonlinearity and adaptability, a new computational model and a new algorithm for object image segmentation are presented. Experiments show that, compared to some traditional algorithms, this method reveals excellent capability of extracting objects from the images with low contrast.
Keywords:Image segmentation  visual nonlinearity  machine vision  object recognition    
本文献已被 CNKI 维普 等数据库收录!
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