臺灣博碩士論文加值系統

在這篇論文中,我們提出了一個自動從影像當中找出人臉,並且準確偵測人臉特徵點的方法.利用大量的人臉影像訓練資料,我們可以得到一些統計的資訊:包括了人臉樣板(face templates),人臉特徵點影像的統計模型,以及人臉特徵點相對位置的統計模型.本篇論文包含了兩個主要部分:人臉偵測演算法,以及人臉特徵點選取演算法.
在人臉偵測演算法中,我們先將人臉影像的訓練資料分成幾個類別,並求取每個類別的平均值以得到人臉樣板.然後將求得的這些人臉樣板經過一些2D幾何轉換產生出大量用來搜尋比對人臉的影像資料.我們利用這些影像之間彼此的相似度建立一個階層式的架構,如此測試影像便不需與全部的影像資料比對而達到加速比對的目的.
這篇論文的第二部分是偵測人臉特徵點的演算法,我們所設定要尋找的人臉特徵點包括眼角以及嘴角.透過主成份分析(principal component analysis ,PCA)技巧的運用,可以得到特徵點影像以及人臉特徵點分佈位置的統計模型.我們會先在每個特徵點各自的小範圍搜尋區域內找出最類似眼角(或嘴角)的幾個候選點,然後分析這些特徵候選點的組合是否為合理的人臉特徵點的分佈位置.最後再以權值分析(weighted sum)的方式考慮特徵點影像的相似度以及分佈位置的合理性兩項因素來決定最佳的一組解.

In this thesis, we propose a novel algorithm to automatically extract facial feature points from image. Our approach is base on the statistical models computed from a large number of training images. There are two parts in this thesis, namely face detection and facial feature points extraction. To extract facial features from images, we have to locate the human face first. Our face detection algorithm is based on the multi-templates matching method. The face templates are computed from the collected face images. A hierarchical nearest neighbor network is applied to store the transformed face templates and it can accelerate the matching process between the test image blocks and face templates.
The second part in this thesis is the facial feature points extraction, including the corners of eyes and the corners of mouth. We apply the technique of principal component analysis (PCA) to calculate the statistical models for the feature images and facial configurations. We first locate several candidate feature points in each local area on face. Then we consider each combination of these candidate feature points to see whether it is a reasonable facial configuration. Finally, we use the weighted sum of image similarity measure and face shape approximation error to determine the best combination of the candidate feature points.

CHAPTER 1. INTRODUCTION
CHAPTER 2. REVIEW OF PREVIOUS WORKS
2.1 RELATED WORKS OF FACE DETECTION
2.2 RELATED WORKS OF FACIAL FEATURE EXTRACTION
CHAPTER 3. FACE DETECTION ALGORITHM
3.1 TRAINING PHASE
3.1.1 Getting the training face data
3.1.2 Estimating face features
3.1.3 Classifying the feature vector
3.1.4 Hierarchical Nearest Neighbor Network For Face Image
3.1.5 Hierarchical Nearest Neighbor Network For Non-Face
Examples
3.2 EXECUTION PHASE
CHAPTER 4. FACIAL FEATURES EXTRACTION ALGORITHM
4.1 TRAINING PHASE
4.1.1 Construction of the statistical face shape model
4.1.2 Constructing the local facial feature templates
4.2 EXECUTION PHASE
CHAPTER 5. EXPERIMENTAL RESULTS FOR FACE DETECTION ALGORITHM
CHAPTER 6. EXPERIMENTAL RESULTS FOR FACIAL FEATURE EXTRACTION
ALGORITHM
CHAPTER 7. CONCLUSION
REFERENCES

[1] T. F. Cootes, G. J. Edwards, and C. J. Taylor. “Active
appearance model.” In Proc. European Conf. on Computer
Vision, volume 2, pages 484-498. Springer, 1998.
[2] Ming-Hsuan Yang, David Kriegman, and Narendra Ahuja.
Detecting Faces in Images: A Survey.
[3] G. Yang and T. S. Huang, “Human face detection in complex
background,” Pattern Recognition, vol. 27, no. 1, pp. 53-
63, 1994.
[4] A. Lanitis, C. J. Taylor, and T. F. Cootes, “An automatic
face identification system using flexible appearance
models,” Image and Vision Computing, vol. 13, no. 5, pp.
393-401, 1995.
[5] Q. Chen, H. Wu, and M. Yachida, “Face detection by fuzzy
matching,” in Proceedings of the International Conference
on Computer Vision, pp. 591-596, 1995.
[6] Haiyuan Wu, T. Yokoyama, D. Pramadihanto, and M. Yachida,
“Face and facial feature extraction from color image,” in
Proceedings of the Second International Conference on
Automatic Face and Gesture Recognition, pp.345-350, 1996.
[7] J. Sobottka and I. Pitas, “Segmentation and tracking of
faces in color images,” in Proceedings of the Second
International Conference on Automatic Face and Gesture
Recognition, pp. 236-241, 1996.
[8] Alan L. Yuille, Peter W. Hallinan, and David S. Cohen.
“Feature Extraction from Faces Using Deformable
Templates.” International Journal of Computer Vision, 8:2,
pages 99-111, 1992.
[9] T. F. Cootes, G. J. Edwards, and C. J. Taylor. “Active
appearance models,” IEEE Trans. on Pattern Recognition and
Machine Intelligence, 23(6):681-685, 2001.
[10] Mikkel B. Stegmann. “Object Tracking Using Statistical
models of Appearance.” Tech Report. Informatics and
Mathematical Modeling, Technical University of Denmark.
[11] M. B. Stegmann, R. Fisker, B. K. Ersboll, H. H. Thodberg,
and L. Hyldstrup. “Active Appearance Models: Theory and
Cases.” Tech. Report. Department of Mathematical Modeling,
Technical University of Denmark.
[12] S.-H. Lai and M. Fang, "Robust and efficient image
alignment with spatially-varying illumination models'',
Proceedings of IEEE Conference on Computer Vision & Pattern
Recognition, Vol. 2, pp. 167-172, Fort Collins, Colorado,
June 23-25, 1999.
[13] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham.
“Active Shape Models-Their Training and Application.”
Computer Vision and Image Understanding, Vol. 61, No. 1,
January, pp. 38-59, 1995.
[14] Matthew Turk and Alex Pentland. “Eigenfaces for
Recognition.” Vision and Modeling Group, The Media
Laboratory, Massachusetts Institute of Technology.