一种基于特征整合理论的物体识别模型_英文_.doc

第 29 卷第 3 期 2012 年 5 月 中国科学院研究生院学报 Journal of Graduate University of Chinese Academy of Sciences Vol． 29 No． 3 May 2012  Article ID: 1002 -1175 ( 2012 ) 03 -0399 -07 A new object recognition model based on feature integration theory* WANG Xi-Shun1 ，2 ，LIU Xi1 ，2 ，SHI Zhong-Zhi2 ，SUI Hong-Jian1 ( 1 Graduate University，Chinese Academy of Sciences，Beijing 100049 ，China; 2 Key Laboratory of Intelligent Information Processing，Institute of Computing Technology，Chinese Academy of Sciences，Beijing 100190 ，China) ( Received 13 October 2010 ; Revised 4 March 2011 ) Wang X S，Liu X，Shi Z Z，et al． A new object recognition model based on feature integration theory［J］． Journal of Graduate University of Chinese Academy of Sciences，2012 ，29 ( 3 ) : 399 -405 ． Abstract We propose a new computational model for object recognition based on the vision cognitive findings． Feature integration theory offers the roadmap for our computing model． We construct the learning procedure to acquire necessary pre-knowledge for the recognition network on the basis of the hypothesis-maximum entropy principle． With the recognition network，we can bind the low-level image features and the high-level knowledge． Fundamental concepts and principles of conditional random fields are employed to model the binding process． We apply our model to real object recognition problem and evaluate it on the benchmark image databases to show its satisfactory performance． Key words conditional random fields; feature binding; feature integration; object recognition CLC TP181 The “binding problem ” is a widely concerned issue across many fields， including psychophysics， neuroscience and even philosophy． How does our brain combine the tremendous amount of external visual information to generate an internal organized perception? This is the topic of the binding problem［1 -3］． Increasing attention and enormou