使用正規化鑑別分析與AdaBoost演算法的臉部表情辨識之研究

Facial Expression Recognition by a novel Regularized discriminant analysis with AdaBoost

黃信笙(Shin-Sheng Huang)

指導教授 ： 李建誠

元智大學/電機通訊學院/通訊工程學系/碩士(2009年)

https://doi.org/10.6838/YZU.2009.00307

摘要

本論文中，我們提出一種全新的方法，來辨識人臉中的七種表情，其中包括生氣、噁心、害怕、開心、難過、驚訝及無情緒的表情。在特徵擷取方面，我們使用局部的Gabor filter來擷取分類的特徵以避免多餘的資訊。接著利用本論文提出的正規化鑑別分析 AdaBoost 演算法 (Regularized Discriminant Analysis-based AdaBoost, RDA-AB)來分類表情。 在RDA-AB中，正規化鑑別分析為在 boosting 程序中的分類器，藉由參數的調整成功地解決了高維度、低資料量及不適定解的問題。我們並利用粒子群最佳化演算法 (particle swarm optimization, PSO) 來尋找最佳的參數。最後，研究結果顯示本論文提出的RDA-AB在臉部表情辨識上有顯著的表現。

關鍵字

臉部表情 ； 鑑別分析

並列摘要

This paper presents a novel method for facial expression recognition including happy, disgust, fear, anger, sad, surprise and neutral. The proposed method utilizes a regularized discriminant analysis-based AdaBoost algorithm (RDA-AB) with local Gabor features to recognize the facial expressions. The RDA-AB uses RDA as a learner in the boosting algorithm. The RDA combines the strength of linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). It solves the small sample size and ill-posed problems suffered from QDA and LDA using a regularization technique. The proposed method also adopts the particle swarm optimization (PSO) algorithm to estimate optimal parameters in RDA. Experimental results show that the performance of the proposed method is excellent when it is compared with that of other facial expression recognition methods.

並列關鍵字

facial expression ； discriminant analysis ； AdaBoost

參考文獻

[1]. C. Darwin, The Expression of the Emotions in Man and Animals, J. Murray, reprinted by Univ. of Chicago Press., 1965, 1872.

[2]. Mehrabian, “Communication without words,” Psychology Today, vol. 2, no. 4, pp. 53-59, 1968.

[3]. P. Ekman and W. V. Friesen, “Constants across cultures in the face and emotion,” J. Personality Social Psychol. vol. 17, no. 2, pp. 124-129, 1971.

[5]. M. H. Yang, D. J. Kriegman, and N. Ahuja, “Detecting faces in images: A survey,” IEEE Trans. Pattern Anal. Machine Intell., vol. 24, pp. 34–58, Jan. 2002.

[6]. P. Viola and M. J. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, vol. 1, pp. 511-518.