[1] Yu Weiwei, Teng Xiaolong, Liu Chongqing,. Feature fusing in face recognition [J]. Journal of Southeast University (English Edition), 2005, 21 (4): 427-431. [doi:10.3969/j.issn.1003-7985.2005.04.010]
Copy
Feature fusing in face recognition(
)
用于人脸识别的特征融合
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 21
- Issue:
- 2005 4
- Page:
- 427-431
- Research Field:
- Computer Science and Engineering
- Publishing date:
- 2005-12-30
Info
- Title:
- Feature fusing in face recognition
- 用于人脸识别的特征融合
- Author(s):
- Yu Weiwei, Teng Xiaolong, Liu Chongqing
- School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai 200030, China
- Keywords:
- face recognition; feature fusion; global features; local features
- PACS:
- TP391
- DOI:
- 10.3969/j.issn.1003-7985.2005.04.010
- Abstract:
- With the aim of extracting the features of face images in face recognition, a new method of face recognition by fusing global features and local features is presented.The global features are extracted using principal component analysis(PCA).Active appearance model(AAM)locates 58 facial fiducial points, from which 17 points are characterized as local features using the Gabor wavelet transform(GWT).Normalized global match degree(local match degree)can be obtained by global features(local features)of the probe image and each gallery image.After the fusion of normalized global match degree and normalized local match degree, the recognition result is the class that included the gallery image corresponding to the largest fused match degree.The method is evaluated by the recognition rates over two face image databases(AR and SJTU-IPPR). The experimental results show that the method outperforms PCA and elastic bunch graph matching(EBGM).Moreover, it is effective and robust to expression, illumination and pose variation in some degree.
- 针对人脸识别中人脸图像的特征提取问题, 提出了一种将全局特征与局部特征相融合的人脸识别方法.全局特征的提取采用主成分分析算法.主动外观模型定位58个特征点, 在其中17个特征点处进行Gabor小波变换则可提取局部特征.归一化的全局匹配度(局部匹配度)可由测试图像和训练图像的全局特征(局部特征)得到.对归一化的全局匹配度和局部匹配度进行融合后, 融合匹配度最大的训练图像所属的类即为识别结果.实验利用2个人脸图像数据库(AR和SJTU-IPPR)测试该方法的识别率, 结果表明该方法要优于PCA 和EBGM, 并且在一定的表情、光照和姿态变化的条件下是有效、稳健的.
References:
[1] Givens G, Beveridge J R, Draper B A, et al.How features of the human face affect recognition:a statistical comparison of three face recognition algorithms [A]. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition [C]. Washington, DC, 2004, 2:381-388.
[2] Zhang Pengfei, Li Desheng, Wang Qi.A novel iris recognition method based on feature fusion [A].In:Proceedings of 2004 International Conference on Machine Learning and Cybernetics [C].Shanghai, 2004, 6:3661-3665.
[3] Turk M, Pentland A.Eigenfaces for recognition [J].Journal of Cognitive Neuroscience, 1991, 3(1):71-86.
[4] Belhumeur P N, Hespanda J, Kriegeman D.Eigenfaces vs.Fisherfaces:recognition using class specific linear projection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):711-720.
[5] Moghaddam B.Principle manifolds and probabilistic subspace for visual recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(6):780-788.
[6] Wiskott L, Fellous J M, Kruger N, et al.Face recognition by elastic bunch graph matching [A].In:International Conference on Image Processing [C].Washington, DC, 1997, 1:129-132.
[7] Arca Stefano, Campadelli Paola, Lanzarotti Raffaella.A face recognition system based on local feature analysis [A].In:4th International Conference on Audio-and Video-Based Biometrie Person Authentication [C].Guildford, UK, 2003.182-189.
[8] Cootes T F, Edwards G J, Taylor C J.Active appearance models [A].In:European Conference on Computer Vision [C].Berlin, 1998, 2:484-498.
[9] Lee Tai Sing.Image representation using 2D Gabor wavelets [J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996, 18(10):959-971.
[10] Liu Chengjun.Gabor-based kernel PCA with fractional power polynomial models for face recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(5):572-581.
[11] Snelick R, Uludag U, Mink A, et al.Large scale evaluation of multimodal biometric authentication using state-of-the-art systems [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3):450-455.
[12] Hua Xiansheng, Zhang Hongjiang.An attention-based decision fusion scheme for multimedia information retrieval [A].In: The Fifth Pacific-Rim Conference on Multimedia [C].Tokyo, Japan, 2004.1001-1010.
[13] Martinez A M, Benavente R.The AR face database [EB/OL].http://rvl1.ecn.purdue.edu/~aleix/aleix-face-DB.html, 2003/2005-04-01.
[14] Lienhart Rainer, Kuranov Alexander, Pisarevsky Vadim.Empirical analysis of detection cascades of boosted classifiers for rapid object detection [A].In: Proc 25th German Pattern Recognition Symposium [C].Magdeburg, 2003.297-304.
[15] Loy Gareth, Zelinsky Alexander.A fast radial symmetry transform for detecting points of interest [A].In:European Conference on Computer Vision [C].Copenhagen, 2002.358-368.
Memo
- Memo:
- Biographies: Yu Weiwei(1978—), female, graduate;Liu Chongqing(corresponding author), male, professor, liuchqing@263.net.