即時多角度人臉偵測｜國立清華大學博碩士論文庫

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳曉瑩 Hsiao-Ying Chen
論文名稱：	即時多角度人臉偵測 Real-time Multi-pose Face Detection
指導教授：	黃仲陵 Chung-Lin Huang
口試委員:
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2006
畢業學年度：	94
語文別：	中文
論文頁數：	54
中文關鍵詞：	人臉偵測、多角度、即時系統、表情辨識
外文關鍵詞：	face detection, multi-pose, real-time system, Gabor feature, Haar-like feature, Adaboost
相關次數：	點閱：3 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

在此篇論文中，我們提出了一個新的混合式特徵，此特徵是由Gabor特徵與Haar-like特徵所組成的。此篇論文的目標是要建立一個自動人臉偵測系統，在頭部移動與不同角度(左右轉、上下轉)時都能準確的偵測。我們人臉偵測系統主要份成兩個部份，第一個部份是利用膚色偵測與切割找出潛在人臉區域，在偵測到的膚色區域中，利用不同的掃描視窗對整張影像做掃描，當膚色區域大於某一特定值，才作辨識的工作；第二個部份是在掃描的區域中找出重要的特徵點，將這些特徵點結合出最後的分類結果，即為我們的偵測結果。我們的系統在不同大小、不同角度、不同表情和失焦的人臉上，都可以準確偵測出來。從實驗的結果也可以發現，利用我們所提出的混合特徵所做出來的系統，整體表現都比僅僅使用Gabor特徵或是Haar-like特徵來得好。我們所做出來的人臉偵測系統，可以偵測出從-90˚ 到 90˚ 的人臉，準確率也高達93%-95%，除此之外，在臉部表情辨識上，也一樣有很好的準確率。另外，在使用AMD 3000+ (約等於2.0 GHz)處理器下，我們處理320*240大小的圖片，大約需要300~350 ms去偵測出人臉位置，50~60 ms去追蹤加表情辨識，整體來說，系統執行速度大約為10-20Hz。我們的系統不僅可以做即時的處理而且可以偵測到更大角度的人臉，因此，我們相信此系統可以被更廣泛的運用。

In the thesis, a new feature set which is composed with Gabor feature and Haar-like feature named hybrid feature set is proposed. The goal of this thesis is to create an automatic face detection system which is robust to pose and head motion. Our face detection system consists of two modules. The first module searches the potential face regions by using skin color detection and segmentation procedures. The second module selects the features of the scanned image. This system can be used in different sizes, varying poses, different expressions, and defocus problems. From the experimental results, we find that we can have a better system performance comparing with the classifier using only single type weak classifier. Our face detection system can detect the faces with rotation angles from -90˚ to 90˚ with an average correction rate about 93%-95%. Our system can also be applied for facial expression recognition with high correction rate. We also do the real-time test of the system by using AMD 3000+ CPU and the image size is 320*240 pixels. It requires 300~350 ms to detect a face and 50~60 ms for tracking. Therefore, our system is more robust than other proposed face detection system and can be widely used.

CONTENTS
CONTENTS……………………………………………………………II
LIST OF FIGURES…………………………………………………IV
LIST OF TABLES……………………………………………………VI
CHAPTER 1  INTRODUCTION………………………..………1
1    Motivation  1
2    Related Works  1
2.1    Face detection problem  2
2.2    Feature extraction problem  3
3    Overview of the Thesis  5
4    Organization of the Thesis  6
CHAPTER 2  SEGMENTATION OF POTENTIAL FACE REGIONS……………………………………..…..7
1    Introduction  7
2    Skin color detection  7
3    Image compensation  10
4    Experiment results and discussions  11
CHAPTER 3  HYBRID FEATURE SELECTION ………………..14
1    Introduction  14
2    Hybrid Feature Pool  15
2.1    Normalization of input images  15
2.2    Gabor feature set  16
2.3    Haar-like feature set  17
3    Hybrid feature based Look-Up-Table (LUT) Weak Classifiers 19
CHAPTER 4  POSE CLASSIFICATION AND EXPRESSION   RECONGNITION BY USING ADABOOST
              ………………………………………………………..25
1    Introduction  25
2    The Multi-class Adaboost Learning Algorithm  26
3    Poses Classification  28
3.1    FERET face database  28
3.2    Normalization of the input image  29
3.3    Calculate the strong classifier  31
4    Facial Expression Recognition  34
4.1    Cohn and Kanade Facial Expression Database  35
4.2    Normalization of the input image  35
4.3    Calculate the strong classifier  36
CHAPTER 5  EXPERIMENTAL RESULTS AND DISCUSSIONS
             ………………………………………………………....37
1    Experimental Results with Training Database 35
2    Comparison between Hybrid feature and Single feature 37
3    Testing on Real-life Photos and Discussions  41
4    Comparison with Other Real-Time Detector  44
5    Facial expression recognition  48
CHAPTER 6  CONCLUSIONS AND FEATURE WORKS………52
REFERENCES………………………………………………………...53

                                

REFERENCES
[1] P. Viola and M. Jones,“Rapid Object Detection using a Boosted Cascade of Simple Features,”CVPR, pp. 511-518, 2001.
[2] M. Jones and P. Viola,“Fast Multi-view Face Detection,”Tech. Rep. TR2003-96, Mitsubishi Electric Research Laboratories, July 2003.
[3] H. Gu and Q. Ji,“Information Extraction from Image Sequences of Real-world Facial Expressions”Machine Vision and Applications, pp.105-115, 2005
[4] P. Moreno, A. Bernardino, and J. Santos-Victor,“Gabor Parameter Selection for Local Feature Detection,” IbPRIA 2005, LNCS 3522, pp. 11-19, 2005.
[5] D. Datcu and L. J. M. Rothkrantz,“ Facial Expression Recognition With Relevance Vector Machines,”ICME, 2005.
[6] M. E. Tipping,“Sparse Bayesian Learning and the Relevance Vector Machine,”Machine Learning, pp. 211-244, 2001.
[7] W. M. Yu, T. Du, and K. B. Lim,“Comparison of the Support Vector Machine and Relevant Vector Machine in Regression and Classification Problems,” ICARCV, Dec. 2004.
[8] G. Guo and H. J. Zhang,“Boosting for Fast Face Recognition,”Tech. Rep. MSR-TR-2001-16, Feb. 2001.
[9] Y. Wang, H. Ai, B. Wu, and C. Huang,“Real Time Facial Expression Recognition with Adaboost,”ICPR, 2004.
[10] S. U. Jung, D.H. Kim, K. H. An, and M. J. Chung,“Efficient Rectangle Feature Extraction for Real-time Facial Expression Recognition based on Adaboost,”IROS, 2005.
[11] C. Huang, H. Ai, Y. Li, and S. Lao,“Vector Boosting for Rotation Invariant Multi-View Face Detection,”ICCV, 2005.
[12] Stan Z. Li and Z. Q. Zhang,“FloatBoost Learning and Statistical Face Detection,” IEEE Trans. PAMI, vol. 26, pp .1112-1123, Sep. 2004.
[13] M. S. Bartlett, G. Littlewort, M. Frank, C. Lainscsek, I. Fasel, and J. Movellan,“Recognizing Facial Expression：Machine Learning and Application to Spontaneous Behavior,”CVPR, pp. 568-573, 2005.
[14] Y. Y. Lin and T. L. Liu, “Robust Face Detection with Multi-Class Boosting,”CVPR, 2005
[15] Rafael C. Gonzalez and Richard E. Woods, “Digital Image Processing,” Addison- Wesley Publishing Company, 1992.
[16] P. J. Phillips, H. J. Moon, S. A. Rizvi, and P. J. Rauss, “The feret evaluation methodology for face recognition algorithms”, PAMI, 22(10), 1090–1104, October 2000.
[17] Rainer Lienhart and Jochen Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection,” Submitted to ICIP2002.
[18] Intel. Open source computer vision library, 2000.
[19] Machine Perception Toolbox (MPT) http://mplab.ucsd.edu/grants/project1/free-software/MPTWebSite/API/.
[20] T. Kanade, J.F. Cohn, and Y. Tian. Comprehensive database for facial expression analysis. In Proceedings of the fourth IEEE International conference on automatic face and gesture recognition (FG’00), pages 46–53, Grenoble, France, 2000.

全文公開日期本全文未授權公開 (校內網路)
全文公開日期本全文未授權公開 (校外網路)

簡易檢索 / 詳目顯示

相關論文