基於模糊邏輯之臉部表情辨識

Facial Expression Recognition based on Fuzzy Logic

鐘仁厚(REN- HOU JHONG)

指導教授 ： 王文俊

國立中央大學/資訊電機學院/電機工程學系/碩士(2008年)

摘要

本論文主要是建立一套可以自動分析人臉表情的系統。研究的主要內容由三個部份所組成，包含人臉偵測（face detection）、特徵擷取（feature extraction）以及表情辨識（facial expression）。
在人臉偵測部份，主要利用膚色偵測等影像處理技術將臉部區塊從複雜背景中取出。在特徵擷取部份，主要利用唇色偵測、邊緣偵測、眼睛偵測等影像處理技術從臉部區塊中取出嘴巴、眼睛、鼻子、皺眉、抬頭紋等特徵，然後從取得的特徵中求得開口特徵值、嘴型特徵值、嘴角特徵值、皺眉特徵值與抬頭紋特徵值，作為判斷表情的依據。在表情辨識部份，本論文採用Takagi–Sugeno–Kang（TSK）模糊系統，將上述求得的特徵值分析處理後，判斷是屬於以下何種表情：驚訝、生氣、悲傷、高興、噁心及正常表情。
本論文採用自行拍攝的影像做為資料庫，並藉此資料庫來測試本系統表情辨識的成功率。最後將實驗結果進行分析與描述。

關鍵字

表情辨識 ； 特徵擷取 ； TSK模糊系統

並列摘要

The goal of this thesis is to build a system which can analyze the facial expression. In this study, the major contents are composed of the “face detection”, “feature extraction” and “facial expression recognition”.
At the part of face detection, we use the skin detection to pick up the facial region from the complicated background. Through the technique of “lip detection”, “edge detection” and “eyes detection”, we can find out the characteristics of the degree of opening month, the shape of month, the corner of the month, the frown and the wrinkles on the forehead. However those characteristics will be regard as the factors of the facial expression recognition. Moreover this thesis can determine the facial expression by Takagi-Sugeno-Kang (TSK) fuzzy system after analyzing the characteristics. Finally the system can recognize many facial expressions such as surprise, anger, sadness, happiness, disgust and normal expression.
In order to measure the accuracy of the recognition, we establish a database with facial images and describe the experiment result in the end.

並列關鍵字

facial expression ； feature extraction ； TSK fuzzy

參考文獻

[1] C. C. Chiang, W. K. Tai, M. T. Yang, Y. T. Huang and C. J. Huang, “A novel method for detecting lips, eyes and faces in real time,” Real–Time Imaging, vol. 9, no. 4, pp. 277–287, August 2003.

[4] M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, “Adaptive skin color modeling using the skin locus for selecting training pixels,” Pattern Recognition, vol. 36, no. 3, pp. 681–690, March 2003.

[5] C. Garcia and G. tzirita, “Face detection using quantized skin color region merging and wavelet packet analysis,“ IEEE Trans. on Multimedia, vol. 1, no. 3, pp. 264-277, September 1999.

[6] E. Osuna, R. Freund and F. Girosi, “ Training support vector machines : an application to face detection,“IEEE Conf. on Computer Vision and Pattern Recognition, pp. 130-136, June 1997.

[7] J. Lu., X. Yuan and T. Yahaqi , “A Method of Face Recognition Based on Fuzzy c–Means Clustering and Associated Sub–NNs,” IEEE Trans. on Neural Networks, vol. 18, no. 1, pp. 150–160, January 2007.