article

A novel multiset integrated canonical correlation analysis framework and its application in feature fusion

Authors:

De-Shen XiaAuthors Info & Claims

Pattern Recognition, Volume 44, Issue 5

Pages 1031 - 1040

https://doi.org/10.1016/j.patcog.2010.11.004

Published: 01 May 2011 Publication History

Abstract

Multiset canonical correlation analysis (MCCA) is difficult to effectively express the integrated correlation among multiple feature vectors in feature fusion. Thus, this paper firstly presents a novel multiset integrated canonical correlation analysis (MICCA) framework. The MICCA establishes a discriminant correlation criterion function of multi-group variables based on generalized correlation coefficient. The criterion function can clearly depict the integrated correlation among multiple feature vectors. Then the paper presents a multiple feature fusion theory and algorithm using the MICCA method. The detailed process of the algorithm is as follows: firstly, extract multiple feature vectors from the same patterns by using different feature extraction methods; then extract multiset integrated canonical correlation features using MICCA; finally form effective discriminant feature vectors through two given feature fusion strategies for pattern classification. The multi-group feature fusion method based on MICCA not only achieves the aim of feature fusion, but also removes the redundancy between features. The experiment results on CENPARMI handwritten Arabic numerals and UCI multiple features database show that the MICCA method has better recognition rates and robustness than the fusion methods based on canonical correlation analysis (CCA) and MCCA.

References

[1]

Yun Fu, Liangliang Cao, Guodong Guo, Thomas S. Huang, Multiple feature fusion by subspace learning, ACM International Conference on Image and Video Retrieval (ACM CIVR), 2008, pp. 127-134.

[2]

Sun, Q.S., Zeng, S.G., Liu, Y., Heng, P.A. and Xia, D.S., A new method of feature fusion and its application in image recognition. Pattern Recognition. v38 i12. 2437-2448.

[3]

D.B. Carter, Analysis of multiresolution data fusion techniques, Blaeksburg Master Thesis, Virginia, 1998, pp. 8-15.

[4]

Truk, M. and Pentland, A., Eigenfaces for recognition. Journal of Cognitive Neuroscience. v3 i1. 71-86.

[5]

Pradhan, P.S., King, R.L. and Younan, N.H., Estimation of the number of decomposition levels for a wavelet-based multiresolution multisensor image fusion. IEEE Transactions on Geoscience and Remote Sensing. v44 i12. 3674-3686.

[6]

Chen, Y.H., Deng, L. and Li, J., A new wavelet-based image fusion method for remotely sensed data. International Journal of Remote Sensing. v27 i7. 1465-1476.

[7]

Moghaddam, B., Jebara, T. and Pentland, A., Bayesian face recognition. Pattern Recognition. v33 i11. 1771-1782.

[8]

Lawrence, S., Giles, C.L., Tsoi, A.C. and Back, A.D., Face recognition: a convolutional neural networks approach. IEEE Transactions on Neural Networks, Special Issue on Neural Networks and Pattern Recognition. v8 i1. 98-113.

[9]

Constantinidis, A.S., Fairhurst, M.C. and Rahman, A.F.R., A new multi-expert decision combination algorithm and its application to the detection of circumscribed masses in digital mammograms. Pattern Recognition. v34 i8. 1528-1537.

[10]

Jing, X.Y., Zhang, D. and Yang, Z.Y., Face recognition based on a group decision-making combination approach. Pattern Recognition. v36 i7. 1675-1678.

[11]

Liu, C.J. and Wechsler, H., A shape- and texture-based enhanced Fisher classifier for face recognition. IEEE Transactions on Image Processing. v10 i4. 598-608.

[12]

Yang, J. and Yang, J.Y., Generalized K-L transform based combined feature extraction. Pattern Recognition. v35 i1. 295-297.

[13]

Yang, J., Yang, J.Y., Zhang, D. and Lu, J.F., Feature fusion: parallel strategy vs. serial strategy. Pattern Recognition. v36 i6. 1369-1381.

[14]

Belhumeur, P.N., Hespanha, J.P. and Kriegman, D.J., Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence. v19 i7. 711-720.

[15]

Wang, Z.Q., Sun, X.H., Guo, L. and Yang, J.Y., Multifeature fusion based on Fisher discriminant criterion. Computer Engineering. v28 i3. 41-42.

[16]

Hotelling, H., Relations between two sets of variates. Biometrika. v28 i3-4. 321-377.

[17]

Sun, Quan-Sen, Liu, Zheng-Dong, Heng, Pheng-Ann and Xia, De-Sen, A theorem on the generalized canonical projective vectors. Pattern Recognition. v38 i3. 449-452.

[18]

Hong, Quan, Chen, Songchan and Ni, Xuelei, Sub-pattern canonical correlation analysis with application in face recognition. Acta Automatica Sinica. v34 i1. 21-30.

[19]

Sun, Tingkai and Chen, Songcan, Locality preserving CCA with applications to data visualization and pose estimation. Image and Vision Computing. v25 i5. 531-543.

[20]

Zhang, Raoting and Fang, Kaitai, Multivariate Statistical Analysis Introduction. 1999. Science Press, Beijing.

[21]

Hu, Guoding and Zhang, Runchu, Multivariate Data Analysis Method: Pure Algebraic Treatment. 1990. Press of Nankai University, Tianjin.

[22]

Q.S. Sun, M.L. Yang, P.A. Heng, D.S. Xia, Improvements on CCA model with application to face recognition, in: Proceedings of the International Conference on Intelligent Information Process (ICIIP), Springer-Verlag, Heidelberg, Berlin, 2004, pp. 125-135.

[23]

Kim, T.-K., Kittler, J. and Cippola, R., Discriminative learning and recognition of image set classes using canonical correlations. IEEE Transactions on Pattern Analysis and Machine Intelligence. v29 i6. 1005-1018.

[24]

M. Borga, Learning multidimensional signal processing, Linköping studies in science and technology, vol. 531, Dissertations, Department of Electrical Engineering, Linköping University, Linköping, Sweden, 1998.

[25]

Melzer, T., Reiter, M. and Bischof, H., Appearance models based on kernel canonical correlation analysis. Pattern Recognition. v36 i9. 1961-1971.

[26]

Q.S. Sun, Z. Jin, P.A. Heng, D.S. Xia. A. Novel, Feature fusion method based on partial least squares regression, The third International Conference on Advances in Pattern Recognition, Bath, UK, Lecture Notes in Computer Science, vol. 3686, Springer-Verlag, Heidelberg, Berlin, 2005, pp. 268-277.

[27]

Barker, M. and Rayens, W., Partial least squares for discrimination. Journal of Chemometrics. v17 i3. 166-173.

[28]

Robert, G.D., Steel. Minimum generalized variance for a set of linear function. Annals of Mathematical Statististics. v22 i3. 456-460.

[29]

Horst, P., Generalized canonical correlations and their applications to experimental data. Journal of Clinical Psychology. v17 i14. 331-347.

[30]

Kettenring, J.R., Canonical analysis of several sets of variables. Biometrika. v58 i3. 433-451.

[31]

Nielsen., A.A., Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data. IEEE Transactions on Image Processing. v11 i3. 293-305.

[32]

Bryan Thompson, Jered Cartmill, et al., A multichannel canonical correlation analysis feature extraction with application to buried underwater target classification, International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada, 2006, pp. 4413-4420.

[33]

Bach, Francis R. and Jordan, Michael I., Kernel independent component analysis. Journal of Machine Learning Research. v3 iJuly. 1-48.

[34]

Sun, Jiguang, An algorithm for the solution of multi-parameter eigenvalue problems(II). Journal of Computational Mathematics. v4. 354-363.

[35]

Lian-hua Xu, The numerical method for the multivariate eigenvalueproblem, M.S. Dissertation, Ocean University of China, Qingdao, 2008.

[36]

Hu, Z.S., Lou, Z., Yang, J.Y., Liu, K. and Sun, J.Y., Handwritten digit recognition basis on multi-classifier combination. Chinese Journal of Computers. v22 i4. 369-374.

[37]

Quan-sen Sun, Research on feature extraction and image recognition based on correlation projection analysis, Ph.D. Dissertation, Nanjing University of Science and Technology, Nanjing, 2006.

[38]

Jain, A.K., Duin, R.P.W. and Mao, J., Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence. v22 i1. 4-37.

[39]

Baghshah, M.S. and Shouraki, S.B., Non-linear metric learning using pairwise similarity and dissimilarity constraints and the geometrical structure of data. Pattern Recognition. v43 i8. 2982-2992.

[40]

Yeung, D.Y. and Chang, H., A kernel approach for semi-supervised metric learning. IEEE Transactions on Neural Networks. v18 i1. 141-149.

[41]

Chang, H., Yeung, D.Y. and Cheung, W.K., Relaxational metric adaptation and its application to semi-supervised clustering and content-based image retrieval. Pattern Recognition. v39 i10. 1905-1917.

Cited By

Alamgir FAlam M(2023)Hybrid multi-modal emotion recognition framework based on InceptionV3DenseNetMultimedia Tools and Applications10.1007/s11042-023-15066-w82:26(40375-40402)Online publication date: 27-Mar-2023
https://dl.acm.org/doi/10.1007/s11042-023-15066-w
Deshmukh SAbhyankar AKelkar S(2022)DCCA and DMCCA framework for multimodal biometric systemMultimedia Tools and Applications10.1007/s11042-022-12435-981:17(24477-24491)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1007/s11042-022-12435-9
Attique Khan MSharif MAkram TKadry SHsu C(2022)A two‐stream deep neural network‐based intelligent system for complex skin cancer types classificationInternational Journal of Intelligent Systems10.1002/int.2269137:12(10621-10649)Online publication date: 29-Dec-2022
https://dl.acm.org/doi/10.1002/int.22691
Show More Cited By

A novel multiset integrated canonical correlation analysis framework and its application in feature fusion
1. Computing methodologies
  1. Machine learning
    1. Machine learning algorithms

Recommendations

Fractional-order embedding multiset canonical correlations with applications to multi-feature fusion and recognition

The sample covariance matrices in multiset canonical correlation analysis (MCCA) usually deviate from the true ones owing to noise and the limited number of training samples. In this paper, we thus re-estimate the covariance matrices by using the idea ...
Multiple-rank supervised canonical correlation analysis for feature extraction, fusion and recognition

A supervised two-dimensional CCA method is proposed for feature extraction.By further exploration another supervised framework is also presented.Experimental results of our methods superior/comparable to the literature. The traditional CCA and 2D-CCA ...
A novel supervised correlation analysis based on partial differential equations for multi-feature extraction and fusion
Abstract
In high dimensional data analysis, canonical correlation analysis (CCA) mainly studies the linear correlation between two sets of features and it is an effective two-view feature extraction method. However, CCA cannot extract the features that are ...

Comments

Information & Contributors

Information

Published In

cover image Pattern Recognition

Pattern Recognition Volume 44, Issue 5

May, 2011

157 pages

ISSN:0031-3203

Issue’s Table of Contents

Copyright © Elsevier Ltd © 2010.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 May 2011

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

25
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Alamgir FAlam M(2023)Hybrid multi-modal emotion recognition framework based on InceptionV3DenseNetMultimedia Tools and Applications10.1007/s11042-023-15066-w82:26(40375-40402)Online publication date: 27-Mar-2023
https://dl.acm.org/doi/10.1007/s11042-023-15066-w
Deshmukh SAbhyankar AKelkar S(2022)DCCA and DMCCA framework for multimodal biometric systemMultimedia Tools and Applications10.1007/s11042-022-12435-981:17(24477-24491)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1007/s11042-022-12435-9
Attique Khan MSharif MAkram TKadry SHsu C(2022)A two‐stream deep neural network‐based intelligent system for complex skin cancer types classificationInternational Journal of Intelligent Systems10.1002/int.2269137:12(10621-10649)Online publication date: 29-Dec-2022
https://dl.acm.org/doi/10.1002/int.22691
Purohit HAjmera P(2021)Optimal feature level fusion for secured human authentication in multimodal biometric systemMachine Vision and Applications10.1007/s00138-020-01146-632:1Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1007/s00138-020-01146-6
Yuan YZhang HLi YQiang JGou JGao GLi B(2019)Fuzzy Bilinear Latent Canonical Correlation Projection for Feature LearningNeural Information Processing10.1007/978-3-030-36708-4_55(670-678)Online publication date: 12-Dec-2019
https://dl.acm.org/doi/10.1007/978-3-030-36708-4_55
Joshi GVig RSingh S(2018)DCA‐based unimodal feature‐level fusion of orthogonal moments for Indian sign language datasetIET Computer Vision10.1049/iet-cvi.2017.039412:5(570-577)Online publication date: 28-Feb-2018
https://dl.acm.org/doi/10.1049/iet-cvi.2017.0394
Liu WYang XTao DCheng JTang Y(2018)Multiview dimension reduction via Hessian multiset canonical correlationsInformation Fusion10.1016/j.inffus.2017.09.00141:C(119-128)Online publication date: 1-May-2018
https://dl.acm.org/doi/10.1016/j.inffus.2017.09.001
Su SGe HTong Y(2018)Multi-graph embedding discriminative correlation feature learning for image recognitionImage Communication10.1016/j.image.2017.10.00560:C(173-182)Online publication date: 1-Feb-2018
https://dl.acm.org/doi/10.1016/j.image.2017.10.005
Yuan YLi YQiang JLi BZheng YJi HGou L(2018)Generalized Multiview Discriminative Projections with Spectral ReconstructionIntelligence Science and Big Data Engineering10.1007/978-3-030-02698-1_40(454-462)Online publication date: 18-Aug-2018
https://dl.acm.org/doi/10.1007/978-3-030-02698-1_40
Uurtio VMonteiro JKandola JShawe-Taylor JFernandez-Reyes DRousu J(2017)A Tutorial on Canonical Correlation MethodsACM Computing Surveys10.1145/313662450:6(1-33)Online publication date: 22-Nov-2017
https://dl.acm.org/doi/10.1145/3136624
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents