视觉感知的目标识别算法
|
摘要
针对图像的目标识别问题,采用视觉感知的方法,模拟感受野的分层信息处理机制,并引入神经元间的侧抑制机制,对神经元响应进行筛选,通过检测视觉基本特征的方式识别图像中的目标.算法首先在简单细胞的感受野中对图像进行预处理;其次,在复杂细胞的感受野中,将简单细胞的感受野刺激进一步拓扑特征提取,得到感受野刺激响应;最后,通过侧抑制机制对响应神经元筛选,找出对刺激响应较强烈的神经元,将其输出作为目标识别的参数标准.实验结果表明,基于视觉感知的算法可以用少量样本解决大量图像中的目标识别问题,识别率高于边缘检测和图像分割方法,算法的目标识别率达到95.56%.
Aiming at the problem of target recognition in image processing,a novel algorithm based on visual perception with better information processing mechanism was proposed for target recognition,in which the hierarchical information processing mechanism of receptive field were simulated and the lateral inhibition mechanism which was used to filter response of neurons was introduced.Firstly,in receptive field of simple cells,the images are initially processed.Secondly,in receptive field of complex cells,stimulation of receptive field from former layer is further feature extracted,and then a new receptive field is obtained.And finally,the neurons which are strongly responded to the stimulation are found out by lateral inhibition mechanism,and their correspondent content can be output as the standard of aerial target recognition,the recognition rate of algorithm is 95.56%.Experimental results show that this novel algorithm has high efficiency,and can achieve a great number of target recognitions with few samples,and the recognition rate is higher than that of edge detection and image segmentation method.
Aiming at the problem of target recognition in image processing,a novel algorithm based on visual perception with better information processing mechanism was proposed for target recognition,in which the hierarchical information processing mechanism of receptive field were simulated and the lateral inhibition mechanism which was used to filter response of neurons was introduced.Firstly,in receptive field of simple cells,the images are initially processed.Secondly,in receptive field of complex cells,stimulation of receptive field from former layer is further feature extracted,and then a new receptive field is obtained.And finally,the neurons which are strongly responded to the stimulation are found out by lateral inhibition mechanism,and their correspondent content can be output as the standard of aerial target recognition,the recognition rate of algorithm is 95.56%.Experimental results show that this novel algorithm has high efficiency,and can achieve a great number of target recognitions with few samples,and the recognition rate is higher than that of edge detection and image segmentation method.
引文
[1]LEI Xiaogang,LI Ying,ZHAO Na,et al.Fastsegmentation approach for SAR image based on simpleMarkov random field[J].Journal of Systems Engineeringand Electronics,2010,21(1):31-36.
[2]CHEN Weibin,ZHANG Xin.Based on an improvedsobel edged etection operator in the application[C]//Proceedings of 2010 4th International Conference onIntelligent Information Technology Application(IITA).Hebei Province:IEEE,2010:439-442.
[3]OUYANG Yi,XING Jianguo.Based on adaptiveweighted CAMSHIFT human motion tracking algorithm[C]//Proceedings of 2010 2nd InternationalConference on Intellectual Technology in IndustrialPractice(ITIP2010).Hebei Province:IEEE,2010:85-87.
[4]逯鹏,李永强,王治忠,等.基于视觉感知的故障图像检测算法[J].仪器仪表学报,2010,31(9):1997-2002.
[5]张菁,沈兰荪,David Dagan Feng.基于视觉感知的图像检索的研究[J].电子学报,2008,36(3):494-499.
[6]HARUTIUNIAN-KOZAK B A,KHACHVANKYAN DK,GRIGORYAN G G,et al.Dynamic spatialorganization of receptive fields of neurons in the 21acortical area[J].Neurophysiology,2010,45(3):175-184.
[7]XU Wanying,HUANG Xinsheng,WANG Yiping,et al.A biologically motivated corner detection method basedon the oriented receptive fields of simple cortical cells[C]//Proceedings of the 2010 InternationalConference on Biomedical Engineering and ComputerScience(ICBECS).Washington,DC:IEEEComputer Society,2010:1-4.
[8]OLSON S J,GROSSBERG S.A neural network modelfor the development of simple and complex cellreceptive fields within cortical maps of orientation andocular dominance[J].Neural Networks,1998,11(2):189-208.
[9]DOU Y,WANG L F,KONG L F.A model ofnonclassical receptive field in visual cortex[J].Journal of Yanshan University,2009,33(2):109-113.
[10]LEE Gin-Chong,LOO Chu-Kiong,LETCHUMANANC.Two-factor face authentication:topographicindependent component analysis(TICA)andmultispace random projection(MRP)[C]//Proceedings of the 2009 International Conference ofSoft Computing and Pattern Recognition.Washington,DC:IEEE Computer Society,2009:756-761.
[11]RATLIFF F,HARTLINE H.The responses of theLimulus optic nerve fibers to patterns of illuminationon the receptor mosaic[J].J Gen Physiol,1959,42(6):1241-1255.
[12]CHEN Yuepeng,FU Hongwei.Study and application oflateral inhibition models in image's contourenhancement[C]//Proceedings of the 2010International Conference on Computer Application andSystem Modeling(ICCASM).Washington,DC:IEEE Computer Society,2010:23-27.
[2]CHEN Weibin,ZHANG Xin.Based on an improvedsobel edged etection operator in the application[C]//Proceedings of 2010 4th International Conference onIntelligent Information Technology Application(IITA).Hebei Province:IEEE,2010:439-442.
[3]OUYANG Yi,XING Jianguo.Based on adaptiveweighted CAMSHIFT human motion tracking algorithm[C]//Proceedings of 2010 2nd InternationalConference on Intellectual Technology in IndustrialPractice(ITIP2010).Hebei Province:IEEE,2010:85-87.
[4]逯鹏,李永强,王治忠,等.基于视觉感知的故障图像检测算法[J].仪器仪表学报,2010,31(9):1997-2002.
[5]张菁,沈兰荪,David Dagan Feng.基于视觉感知的图像检索的研究[J].电子学报,2008,36(3):494-499.
[6]HARUTIUNIAN-KOZAK B A,KHACHVANKYAN DK,GRIGORYAN G G,et al.Dynamic spatialorganization of receptive fields of neurons in the 21acortical area[J].Neurophysiology,2010,45(3):175-184.
[7]XU Wanying,HUANG Xinsheng,WANG Yiping,et al.A biologically motivated corner detection method basedon the oriented receptive fields of simple cortical cells[C]//Proceedings of the 2010 InternationalConference on Biomedical Engineering and ComputerScience(ICBECS).Washington,DC:IEEEComputer Society,2010:1-4.
[8]OLSON S J,GROSSBERG S.A neural network modelfor the development of simple and complex cellreceptive fields within cortical maps of orientation andocular dominance[J].Neural Networks,1998,11(2):189-208.
[9]DOU Y,WANG L F,KONG L F.A model ofnonclassical receptive field in visual cortex[J].Journal of Yanshan University,2009,33(2):109-113.
[10]LEE Gin-Chong,LOO Chu-Kiong,LETCHUMANANC.Two-factor face authentication:topographicindependent component analysis(TICA)andmultispace random projection(MRP)[C]//Proceedings of the 2009 International Conference ofSoft Computing and Pattern Recognition.Washington,DC:IEEE Computer Society,2009:756-761.
[11]RATLIFF F,HARTLINE H.The responses of theLimulus optic nerve fibers to patterns of illuminationon the receptor mosaic[J].J Gen Physiol,1959,42(6):1241-1255.
[12]CHEN Yuepeng,FU Hongwei.Study and application oflateral inhibition models in image's contourenhancement[C]//Proceedings of the 2010International Conference on Computer Application andSystem Modeling(ICCASM).Washington,DC:IEEE Computer Society,2010:23-27.