透過您的圖書館登入
IP:3.138.204.208
  • 學位論文

粒子群演算法應用在臉部表情辨識分類器之最佳化

Optimization of Facial Expression Recognition Classifier by PSO Algorithm

指導教授 : 許志宇
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


本論文提出一種八種臉部表情的影像辨識方法,其中八種臉部表情是由兩個眼睛與嘴唇的開閉組合而成,本方法利用活動基模型(Active Basis Model, ABM),對眼睛及嘴唇影像區塊分別建構變形樣板與基礎樣板,再利用基礎樣版之特徵用來進行分類。本論文流程方法首先將測試影像進行左眼、右眼及嘴唇的區塊裁切,再將左眼開與閉、右眼開與閉及嘴唇開與閉的八種影像區塊分別利用活動基模型建構樣板,活動基模型利用所有影像訓練而先建構一個變形樣板,再利用變形樣板對每張影像的特徵差異在不同角度作些微的擾動以改變位置及方向,並以線性組合成基礎樣板。基礎樣板訓練完成後,利用與變形樣扁之向量特徵差異作為三組支撐向量機(Support Vector Machine,SVM)的輸入,並利用粒子群演算法(Particle Swarm Optimization,PSO)分別搜尋每一組支撐向量機的最佳參數,提高分類結果的準確率,最後訓練分類器,將其重新命名為粒子群支撐向量機(PSO-SVM)。實驗中,攝影收集了50張臉部影像,進行區塊影像裁切後,分別為左眼開影像200張、左眼閉影像200張,右眼開影像200張、右眼閉影像200張,嘴唇開影像200張、嘴唇閉影像200張,共1200張影像。實驗個別針對左眼400影像、右眼400張影像及嘴唇400張影像個別進行訓練及測試。分別利用100張影像進行訓練,300張影像進行測試,最後並訓練三個支撐向量機分類器,包含左眼、右眼及嘴唇。最後,300張測試影像個別進行左眼、右眼及嘴唇影像開與閉的狀態進行測試,分類完成後將其分類結果結合,進行完整臉部辨識的正確率計算,結果可高達90.33%。使用了粒子群演算法最佳化支撐向量機參數進行分類,結果可達99%以上。

並列摘要


This paper proposed an image recognition method for distinguishing eight facial expressions. When the eyes and the mouth of a person are open or closed, there are eight possible facial expressions to be distinguished. The Active Basis Model is used to construct basis templates and deformation templates for the eyes and mouth. The characteristics of the basis template are used as features for training the Support Vector Machines. The eye and mouth areas of the test images are extracted and used to generate the basis and deformation template. After three Support Vector Machines were trained, And join the PSO search Support Vector Machines parameters to optimize, improve the classificationaccuracy, eight facial expressions can be classified due to the statuses of two eyes and mouth. The accuracy of facial expression recognition is 90.33% for testing 100 facial images. The results show the proposed method for facial expression recognition is very effective.

參考文獻


[1]陳建霖,以 Java 為平台建構布袋戲網路戲院,碩士論文,朝陽科技大學資訊與通訊系,台中,2009。
[2]P. Viola, and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, 2004, Vol. 52, No. 2, pp. 137-154.
[4]J.S. Ju, Y.H. Shin, E.Y. Kim, (2009),” Vision based interface system for hands free control of an intelligent Wheelchair,” Journal of Neuro Engineering and Rehabilitation.
[5]W. S. Yanbor, B. A. Draper, J. R. Beveridge, (2002), “Analyzing PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures,” In Empirical Evaluation Methods in Computer Vision. World Scientific Press.
[6]Z. Jin, Z. Lou, J. Yang, and Q. Sun, (2007), “Face detection using template matching and skin-color information,” Neurocomputing, vol. 70, no. 4-6, pp. 794-800.

延伸閱讀