Document Detail


Computational model for perception of objects and motions.
MedLine Citation:
PMID:  18488173     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Perception of objects and motions in the visual scene is one of the basic problems in the visual system. There exist 'What' and 'Where' pathways in the superior visual cortex, starting from the simple cells in the primary visual cortex. The former is able to perceive objects such as forms, color, and texture, and the latter perceives 'where', for example, velocity and direction of spatial movement of objects. This paper explores brain-like computational architectures of visual information processing. We propose a visual perceptual model and computational mechanism for training the perceptual model. The computational model is a three-layer network. The first layer is the input layer which is used to receive the stimuli from natural environments. The second layer is designed for representing the internal neural information. The connections between the first layer and the second layer, called the receptive fields of neurons, are self-adaptively learned based on principle of sparse neural representation. To this end, we introduce Kullback-Leibler divergence as the measure of independence between neural responses and derive the learning algorithm based on minimizing the cost function. The proposed algorithm is applied to train the basis functions, namely receptive fields, which are localized, oriented, and bandpassed. The resultant receptive fields of neurons in the second layer have the characteristics resembling that of simple cells in the primary visual cortex. Based on these basis functions, we further construct the third layer for perception of what and where in the superior visual cortex. The proposed model is able to perceive objects and their motions with a high accuracy and strong robustness against additive noise. Computer simulation results in the final section show the feasibility of the proposed perceptual model and high efficiency of the learning algorithm.
Authors:
WenLu Yang; LiQing Zhang; LiBo Ma
Related Documents :
16452643 - Large-scale visuomotor integration in the cerebral cortex.
8065563 - Processes of visual recognition in monkeys and their neuronal correlates in the visual ...
15251073 - Representations of pain in the brain.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2008-05-17
Journal Detail:
Title:  Science in China. Series C, Life sciences / Chinese Academy of Sciences     Volume:  51     ISSN:  1006-9305     ISO Abbreviation:  Sci. China, C, Life Sci.     Publication Date:  2008 Jun 
Date Detail:
Created Date:  2008-05-19     Completed Date:  2008-09-03     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9611809     Medline TA:  Sci China C Life Sci     Country:  China    
Other Details:
Languages:  eng     Pagination:  526-36     Citation Subset:  IM    
Affiliation:
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. wenluyang@online.sh.cn
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Computer Simulation*
Humans
Learning
Models, Neurological*
Motion Perception*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  PRGL: A cell wall proline-rich protein containning GASA domain in Gerbera hybrida.
Next Document:  Treatment of chronical myocardial ischemia by adenovirus-mediated hepatocyte growth factor gene tran...