Regression Model With Modified Linear Discriminant Analysis Features For Bimodal Emotion Recognition

Now days recognizing the face accurately is becoming more challenging and essential task in the biometric authentication. Use of minimum facial features is important to reduce the complexity of designing the face recognition system. The performance of any emotion recognition system is mostly dependent on efficient design of face recognition system. Recently in the direction of emotion recognition a lot of the work is carried out. It is suggested by some researchers that use of only facial features or speech features are not sufficient to design emotion recognition system. Here in this paper the approach to extract the facial and speech features to recognize the emotion is proposed. Survey suggests that, combining both the features (facial features and speech features) to recognize the emotion improves the emotion state recognition accuracy. Proposed method uses extraction of facial features in both the directions (row and column) using maximum margin criteria with Modified Linear Discriminant Analysis (MLDA). The respective speech data signals are extracted using Mel-Frequency Cepstral Coefficients (MFCC) of the speech. The resultant features (facial features and speech features) are further integrated to construct an informative feature library. The constructed feature library provides a base for recognizing the emotions using advanced regression model, called as Incomplete Sparse Least Square Regression (ISLSR). After experimentation, the proposed approach is found to provide improved recognition accuracy of emotions than existing approaches.

REFERENCES

[1]. Davood Gharavian, Mehdi Bejani Mansour Sheikhan,"Audio-visual emotion recognition using FCBF feature selection method and particle swarm optimization for fuzzy ARTMAP neural networks",Multimedia Tools and Applications, vol. 76, no.2, pp. 2331-2352,January 2017.
[2]. M. Shamim Hossain,Ghulam Muhammad,"Audio-visual emotion recognition using multi-directional regression and Ridgelet transform,"Journal on Multimodal User Interfaces, vol.10, no.4, pp.325–333,December 2016.
[3]. S. Mariooryad and C. Busso, "Facial Expression Recognition in the Presence of Speech Using Blind Lexical Compensation,"IEEE Transactions on Affective Computing, vol. 7, no. 4, pp. 346-359, Oct.-Dec. 1 2016.
[4]. F. Shaw and B. J. Theobald, "Expressive Modulation of Neutral Visual Speech," IEEE Multimedia, vol. 23, no. 4, pp. 68-78, Oct.-Dec. 2016.
[5]. J. Yan, W. Zheng, Q. Xu, G. Lu, H. Li and B. Wang, "Sparse Kernel Reduced-Rank Regression for Bimodal Emotion Recognition From Facial Expression and Speech," IEEE Transactions on Multimedia, vol. 18, no. 7, pp. 1319-1329, July 2016
[6]. Wenming Zheng, Minghai Xin, Xiaolan Wang, and Bei Wang, “A Novel Speech Emotion Recognition Method via Incomplete Sparse Least Square Regression,” IEEE SIGNAL PROCESSING LETTERS, VOL. 21, NO. 5, MAY 2014.
[7]. G. Liu, Z. Lin, S. Yan, J. Sun, Y. Yu, and Y. Ma, “Robust recovery of subspace structures by low-rank representation,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 35, no. 1, pp. 172–184, 2013
[8]. Z. Qin and d. Goldfarb, “Structured sparsity via alternating direction methods,” J. Mach. Learn. Res., vol. 13, pp. 1333–1367, 2012
[9]. J. Yang, L. Zhang, Y. Xu, and J.-Y. Yang, “Beyond sparsity: The role of -optimizer in pattern classification,” Patt. Recognit., vol. 45, pp. 1104–1118, 2012
[10]. W.H. Yang, D. Q. Dai, Two-Dimensional Maximum Margin Feature Extraction for Face Recognition, IEEE Trans.Sys.Man.Cybern.vol-39, no-4, pp. 1002-1012, Aug-2009
[11]. Kiran P Gaikwad, V.M. Wadhai, Prasad S Halgaonkar, Santosh Kumar, “Design and Implementation of Robust 2D Face Recognition System for Illumination Variations,” International Journal of Computer Applications, Vol-10, No-3, November 2010.
[12]. I T. Jolliffe, “Principal Component Analysis,” New York: Springer-Verlag, 1986.
[13]. M. A. Turk and A. P. Pentland, “Eigenfaces for recognition,” J. Cogn. Neurosci., vol. 3, no. 1, pp. 71–86, 1991.
[14]. P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 711 720, Jul. 1997
[15]. S. J. Raudys and A. K. Jain, “Small sample size effects in statistical pattern recognition: Recommendations for practitioners,” IEEE Trans.Pattern Anal. Mach. Intell., vol. 13, no. 3, pp. 252–264, Mar. 1991.
[16]. W. J. Krzanowski, P. Jonathan, W. V. McCarthy,and M. R. Thomas, “Discriminant analysis with singular covariance matrices: Methods and applications to spectroscopic data,” Appl. Stat., vol. 44, no. 1, pp. 101–115, 1995.
[17]. S. Raudys and R. P. W. Duin, “Expected classification error of the Fisher linear classifier with pseudo-inverse covariance matrix,” Pattern Recognit. Lett., vol. 19, no. 5/6, pp. 385–392, Apr. 1998.
[18]. L. Chen, H. Liao, M. Ko, J. Lin, and G. Yu, “A new LDA-based face recognition system which can solve the small sample size problem,” Pattern Recognit., vol. 33, no. 10, pp. 1713–1726, Oct. 2000.
[19]. H. Yu and J. Yang, “A direct LDA algorithm for high-dimensional data - With application to face recognition,” Pattern Recognit., vol. 34, no. 10, pp. 2067–2070, Oct. 2001.
[20]. D. Q. Dai and P. C. Yuen, “Regularized discriminant analysis and its application to face recognition,” Pattern Recognit., vol. 36, no. 3, pp. 845–847, Mar. 2003.
[21]. X. S. Zhuang and D. Q. Dai, “Inverse Fisher discriminate criteria for small sample size problem and its application to face recognition,” Pattern Recognit., vol. 38, no. 11, pp. 2192–2194, Nov. 2005.
[22]. H. Li, T. Jiang, and K. Zhang, “Efficient and robust feature extraction by maximum margin criterion,” IEEE Trans. Neural Netw., vol. 17, no. 1, pp. 157– 165, Jan. 2006
[23]. M. Kyperountas, A. Tefas, and I. Pitas, “Weighted piecewise LDA for solving the small sample size problem in face verification,” IEEE Trans. Neural Netw., vol. 18, no. 2, pp. 506–519, Mar. 2007.
[24]. P. Howland, J. Wang, and H. Park, “Solving the small sample size problem in face recognition using generalized discriminant analysis,” Pattern Recognit., vol. 39, no. 2, pp. 277–287, Feb. 2006.
[25]. J. Yang, D. Zhang, A. F. Frangi, and J. Y. Yang, “Two-dimensional PCA: A new approach to appearance-based face representation and recognition,” IEEE Trans. Pattern Anal.Mach. Intell., vol. 26, no. 1, pp. 131–137, Jan. 2004.
[26]. M. Li and B. Yuan, “2D-LDA: A statistical linear discriminant analysis for image matrix,” Pattern Recognit. Lett., vol. 26, no. 5, pp. 527–532, Apr. 2005.
[27]. D. Zhang and Z. H. Zhou, “(2D)2PCA: Two directional two-dimensional PCA for efficient face representation and recognition,” Neuro-computing, vol. 69, no. 1–3, pp. 224–231, Dec. 2005.
[28]. S. Noushath, G. Hemantha Kumar, and P.Shivakumara, “(2D)2LDA: An efficient approach for face recognition,” Pattern Recognit., vol. 39, no. 7, pp. 1396–1400, Jul. 2006.
[29]. X. S. Zhuang and D. Q. Dai, “Improved discriminate analysis for high-dimensional data and its application to face recognition,” Pattern Recognit., vol. 40, no. 5, pp. 1570–1578, May 2007.
[30]. D. Q. Dai and P. C. Yuen, “Face recognition by regularized discriminant analysis,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 37, no. 4, pp. 1080–1085, Aug. 2007.
[31]. M. E. Ayadi, M. S. Kamel, and F. Karray, “Survey on speech emotion recognition: Features, classification schemes, and databases,” Patt. Recognit., vol. 44, pp. 572–587, 2011
[32]. C. M. Bishop, Pattern Recognition, and Machine Learning. Berlin, Germany: Springer, 2006
[33]. Gaikwad Kiran P., C. M. Sheela Rani , Mahajan S. B., Sanjeevikumar P. “Dimensionality Reduction of Facial Features to recognize Emotion State,” Ist Springer International Conference (ETAEERE-2016), Sikkim
[34]. Maged M.M.Fahmy, "Palmprint recognition based on Mel frequency Cepstral coefficients feature extraction", Ain Shams Engineering Journal, vol.1, no.1, pp.39-47, September 2010.