基于简化脉冲耦合神经网络的人脸识别

计算机科学 ›› 2014, Vol. 41 ›› Issue (2): 297-301.

基于简化脉冲耦合神经网络的人脸识别

聂仁灿,姚绍文,周冬明

云南大学信息学院昆明650091;云南大学研究生院昆明650091;云南大学信息学院昆明650091

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61065008),云南省应用基础研究计划项目(2012FD003)资助

Face Recognition Using Simplified Pulse Coupled Neural Network

NIE Ren-can,YAO Shao-wen and ZHOU Dong-ming

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 基于简化脉冲耦合神经网络(S-PCNN),提出了一种新颖的人脸识别方法。首先通过对神经元振荡特性的分析,将神经元振荡时间序列(OTS)分解为捕获性振荡时间序列(C-OTS)和自激性振荡时间序列(S-OTS)。然后通过图像几何变换和振荡频图,分析了X-OTS(OTS、C-OTS和S-OTS)的鉴别特性。最后利用C-OTS+S-OTS和余弦距离测度给出了人脸识别的系统结构。人脸库中的实验结果验证了所提方法的有效性,显示了它比其它传统算法具有更好的识别性能。

关键词: 简化脉冲耦合神经网络,振荡时间序列,人脸识别中图法分类号TP183文献标识码A

Abstract: A novel face recognition method using Simplified Pulse Coupled Neural Network was proposed．First by the analysis of the oscillation characteristics for neurons,the neuronal Oscillation Time sequences (OTS) were decomposed to captured-OTS(C-OTS) and self-OTS(S-OTS)．Then the identification characteristics for X-OTS(OTS,C-OTS and S-OTS) were analyzed by image geometric transformation and oscillation frequency map．Finally,a face recognition system structure was given with C-OTS+S-OTS and cosine distance．Experimental results on face database verify the effectiveness of the proposed method,and it shows better recognition performance than other traditional methods．

Key words: Simplified pulse coupled neural network,Oscillation time sequence,Face recognition

聂仁灿,姚绍文,周冬明. 基于简化脉冲耦合神经网络的人脸识别[J]. 计算机科学, 2014, 41(2): 297-301. https://doi.org/

NIE Ren-can,YAO Shao-wen and ZHOU Dong-ming. Face Recognition Using Simplified Pulse Coupled Neural Network[J]. Computer Science, 2014, 41(2): 297-301. https://doi.org/

参考文献

[1] Lu Guan-chun,Lin Chun-yi.PCA based immune networks forhuman face recognition[J].Applied Soft Computing,2011,1(2):1743-1752
[2] Lu Gui-fu,Zou Jian,Wang Yong．Incremental complete LDA for face recognition [J].Pattern Recognition,2012,45(7):2501-2521
[3] 郭恺,付永生,冷严,等.应用小指数多项式的KPCA+零空间人脸识别[J].计算机工程,2006,2(22):203-205[3]王卫东,韩斌,杨静宇.基于PCA及ICA的双空间特征提取算法[J].中国图象图形学报,2008,3(11):2163-2169
[4] 刘嵩.结合DCT与KPCA的人脸识别[J].计算机工程与应用,2012,8(27):186-188,5
[5] 黄诚,王福龙,刘晓亮.指数衰减下的KFDA方法及其人脸识别[J].广东工业大学学报,2009,6(4):62-64,7
[6] Javad H,Karlm F,Majid A．A fuzzy hybrid learning algorithmfor radial basis function neural network with application in human face recognition [J]．Pattern Recognition,2003,36(5):1187-1202[4]Johson J L,Ritter D.Observation of periodic wanes In a Pulse-coupled neural network[J].Opt Lett,1993,18(15):1253-1255
[7] Johson J L,Ritter D．Observation of periodic wanes in a Pulse-coupled neural network [J]．Opt Lett,1993,18(15):1253-1255
[8] 陈粟宋.一种融合PCNN和Watershed变换的图像分割方法[J].武汉大学学报,2011,4(2):269-272
[9] 严春满,郭宝龙,易盟.基于改进LP变换及自适应PCNN的多聚焦图像融合方法[J].控制与决策,2012,7(5):703-707,2
[10] Johson J L．Pulse-coupled neural nets:translation,rotation,scale,distortion,and intensity signal invariance for images[J]．Applied Optics,1994,33(26):6239-6253
[11] 朱红伟,周冬明,聂仁灿,等.利用PCNN实现商标图像检索新方法[J].云南大学报,2012(3):276-284
[12] 许敏丰,韩力群.基于脉冲耦合神经网络的手掌纹理识别[J].现代科学仪器,2010(6):71-74
[13] 王玮,黄非非,李见为,等.使用多尺度LBP特征与识别人脸[J].光学精密工程,2009,6(4):696-705
[14] 程万里,李伟生.基于Gabor-2DLDA方法的人脸识别研究[J].计算机工程与应用,2008,4(35):179-181

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed