首页 | 本学科首页   官方微博 | 高级检索  
     

视觉机制研究对机器视觉的启发示例
引用本文:李雄,刘允才.视觉机制研究对机器视觉的启发示例[J].中国图象图形学报,2013,18(2):152-156.
作者姓名:李雄  刘允才
作者单位:上海交通大学自动化系,上海,200240
基金项目:国家重点基础研究发展计划(973)基金项目(2011CB302203);国家自然基金项目(60833009,60975012)
摘    要:研究灵长类的视觉系统机制并以此为基础设计机器视觉的算法已成为重要研究方向,并对机器视觉产生了重要的推动作用.本文从视觉机制和机器视觉方法的角度出发,分析了两大类视觉机制或模型,并列举受其影响和推动的多种重要机器视觉方法:1)合作学习和竞争学习机制,其中合作学习和竞争学习模型相关的机器视觉算法包括立体视觉算法、神经网络、稀疏编码;2)简单细胞和复杂细胞模型,相关的机器视觉算法包括HMAX特征、SIFT描述子和deep belief network.

关 键 词:灵长类动物的视觉机制  机器视觉方法  合作学习与竞争学习  简单细胞与复杂细胞
收稿时间:2012/10/8 0:00:00
修稿时间:2012/12/4 0:00:00

The motivation of visual mechanisms to machine vision: examples
Li Xiong and Liu Yuncai.The motivation of visual mechanisms to machine vision: examples[J].Journal of Image and Graphics,2013,18(2):152-156.
Authors:Li Xiong and Liu Yuncai
Affiliation:Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China
Abstract:It has been a promising methodology that designs machine vision algorithms based on the vision mechanism of primate. In this paper, from the intersection points of vision mechanism and machine vision algorithms, we summarize two categories of important vision mechanisms or models, and present their corresponding machine vision algorithms. 1)Cooperative learning and competitive learning: machine vision algorithms motivated by the models typically include stereo vision, neural networks and sparse coding. 2)Simple cell and complex cell: machine vision algorithms corresponding to the models focus on HMAX feature, SFIT feature and deep belief networks.
Keywords:vision mechanism of primate  machine vision algorithm  cooperative learning and competitive learning  simple cell and complex cell
本文献已被 万方数据 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF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