阈值控制下的融合股权多示例人脸鉴别技术

Abstract
Figure/Table
References
Related Citation (13)

Download: PDF (386 KB) HTML (0 KB)
Export: BibTeX | EndNote (RIS)

Abstract Image retrieval based on multi-instance learning (MIL) has great value in the field of regional image retrieval. The traditional voting mechanism in MIL is prone to misunderstanding,because the local similarity does not mean the overall similarity in face identification. Firstly,instance equity concepts of equity MIL are presented. Each kind of instance has different equity and the training set has the similar features to the test set. Therefore,the classification attribution for different packets can be obtained by the sum of results from multiplying every discriminant result and its instance equity. Secondly,the overall characteristic is considered as a special instance,and the overall sample equity threshold is used to control equity ratio. At the same time,the abnormal conditions,such as two persons have similar facial features,are prevented by means of the feature fusion. And the recognition rate is improved by the use of threshold control. The experimental results on the ORL and FERET show that the algorithm is feasible and the performance is superior to other algorithms.

Key words： Face Identification Equity Multi-Instance Learning Instance Equity Feature Fusion Threshold Control

Received: 01 November 2011

ZTFLH:

TP391

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	DENG Jian-Xun
	XIONG Zhong-Yang
	ZENG Dai-Min

Cite this article:

DENG Jian-Xun,XIONG Zhong-Yang,ZENG Dai-Min. Equity Multi-Instance Face Identification Based on Threshold Control and Fusion Feature[J]. , 2013, 26(1): 14-19.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/ OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2013/V26/I1/14

[1] Dietterich T G,Lathrop R H,Tomas L P. Solving the Multiple Instance Problem with Axis-Parallel Rectangles. Artificial Intelligence,1997,89(1/2): 31-71
[2] Cai Zixing,Li Meiyi. Multi-Instance Learning and Its Current Research Status. Control and Decision,2004,19(6): 607-610,615 (in Chinese)
(蔡自兴,李枚毅.多示例学习及其研究现状.控制与决策,2004,19(6): 607-610,615)
[3] Li Daxiang,Peng Jinye,Li Zhan. Object-Based Image Retrieval Using Semi-Supervised MIL Algorithm. Control and Decision,2010,25(7): 981-986 (in Chinese)
(李大湘,彭进业,李展.基于半监督多示例学习的对象图像检索.控制与决策,2010,25(7): 981-986)
[4] Su Yu,Shan Shiguang,Chen Xilin,et al. Integration of Global and Local Feature for Face Recognition. Journal of Software,2010,21(8): 1849-1862 (in Chinese)
(苏煜,山世光,陈熙霖,等.基于全局和局部特征集成的人脸识别.软件学报,2010,21(8): 1849-1862)
[5] Zhang Chunyu,Li Bin,Chen Mianshu,et al. Kernel-Based Global Orthogonal Folley-Sammon Discriminant Vectors. Journal of Jilin University: Engineering and Technology Edition,2009,39(1): 204-209 (in Chinese)
(张春雨,李斌,陈绵书,等.基于核空间的全局正交鉴别矢量集方法.吉林大学学报:工学版,2009,39(1): 204-209)
[6] Wen Hao,Sun Lei. New Face Recognition Algorithm Using Tensor Local and Global Information. Journal of Xidian University,2010,37(3): 429-435 (in Chinese)
(温浩,孙蕾.基于张量局部和全局信息的人脸识别算法.西安电子科技大学学报,2010,37(3): 429-435)
[7] Li Jianke,Zhao Baojun,Zhang Hui,et al. Fusing DCT and LBP Features for Face Recognition. Transactions of Beijing Institute of Technology,2010,30(11): 1355-1359 (in Chinese)
(李建科,赵保军,张辉,等.DCT和LBP特征融合的人脸识别.北京理工大学学报, 2010,30(11): 1355-1359)
[8] Zhang Haiyang,Ma Huadong. Adaptive Elastic Graph Face Matching Method in Grid. Journal of Computer-Aided Design Computer Graphics, 2008,20(2): 253-258 (in Chinese)
(张海旸,马华东.基于网格的自适应弹性图人脸匹配方法.计算机辅助设计与图形学学报,2008,20(2): 253-258)
[9] Mei Jianqiang,Liu Zhengguang. Face Recognition Based on Locality Preserving Projections and Radial Basis Function Network. Journal of Tianjin University,2008,41(4): 419-422 (in Chinese)
(梅健强,刘正光.基于局部保留映射与径向基网络的人脸识别方法.天津大学学报,2008,41(4): 419-422)
[10] Kim C,Oh J Y,Choi C H. Combined Subspace Method Using Global and Local Features for Face Recognition // Proc of the IEEE International Joint Conference on Neural Networks. Montreal,Canada,2005: 2030-2035
[11] Lin Dahua,Tang Xiaoou. Recognize High Resolution Faces: From Macrocosm to Microcosm // Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. New York,USA,2006,II: 1355-1362
[12] Wang Yunhong,Fan Wei,Tan Tieniu. Face Recognition Based on Information Fusion. Chinese Journal of Computers,2005,28(10): 1657-1663 (in Chinese)
(王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法.计算机学报,2005,28(10):1657-1663)
[13] Deng Jianxun,Xiong Zhongyan,Zeng Daimin. Face Recognition Based on Improved Fast EMD-MIL Framework and Information Fusion. Journal of Sichuan University: Engineering Science Edition,2012,2(44): 99-104 (in Chinese)
(邓剑勋,熊忠阳,曾代敏.基于EMD的融合特征快速多示例人脸识别算法.四川大学学报:工程科学版,2012,2(44): 99-104)
[14] Li Enke,Liu Shangqian,Ma Yanxuan,et al. Novel Algorithm for Adaptive Image Segmentation of Moving Targets. Journal of Xidian University,2008,35(3): 490-494 (in Chinese)
(李恩科,刘上乾,麻彦轩,等.一种新的运动目标自适应图像分割算法.西安电子科技大学学报,2008,35(3): 490-494)
[15] Du Ping,Zhang Yankun,Liu Chongqing. A Face Recognition Method Based on Moment Invariants. Computer Simulation,2002,19(3): 78-81 (in Chinese)
(杜平,张燕昆,刘重庆.基于不变矩的人脸识别方法的研究.计算机仿真,2002,19(3): 78-81)