簡易檢索 / 詳目顯示

回結果列表
研究生： 毛璽樹
Mao, Hsi-Shu
論文名稱： 多種不同性別辨識方法之評估
Evaluation of Different Gender Classification Methods
指導教授： 連震杰
Lien, Jenn-Jier James
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2009
畢業學年度： 97
語文別： 英文
論文頁數： 33
中文關鍵詞： 性別辨識
外文關鍵詞： Gender, Classification, SVM, AdaBoost, Identification, Support Vector Machine, Neural Network
相關次數： 點閱：94  下載：5 
分享至:
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

    • 性別辨識可應用於多種層面，如監視系統，針對性別之廣告系統，標籤網路圖片等等。本篇論文對於現存的數種不同性別辨識方法作評估。目前在性別辨識上最常使用的有三種：AdaBoost，Support Vector Machine (SVM)以及Neural Network (類神經網路)。我們在多個面向上比較並分析此三種方法，例如：辨識率，方法之彈性度，等等。SVM有較其他兩者高的辨識率，而AdaBoost與類神經網路略低於SVM。但針對相對於訓練資料屬於未校正之測試資料時，AdaBoost與的表現比SVM以及類神經網路好。當考量辨識速度時，由於AdaBoost有較低的計算花費，因此速度較快。對於此三種方法之變異我們亦做介紹。此外我們提出一針對AdaBoost方法之改良並與AdaBoost以及SVM做實驗結果的比較。

    Gender classification (identification) could be applied in many categories, e.g. surveillance system, commercial advertisement system, internet data labeling, etc. This paper presents a study on several existing methods for gender classification. The most commonly used methods are AdaBoost, Support Vector Machine (SVM) and Neural Network. We compared these methods in many categories, e.g. performance, flexibility, etc., and analyze them. SVM achieves the highest detection rate, with AdaBoost and Neural Network slightly behind. But when encountering non-rectified testing data, AdaBoost out-performed the other two methods. When considering the classification speed, AdaBoost also has a lower computational cost than the other two, therefore it is a better choice in such condition. A brief introduction to some variations of these three methods is also presented. We also implemented a variation of AdaBoost proposed by us to compare the results with AdaBoost and SVM.

    LIST OF TABLES............................................V LIST OF FIGURES..........................................VI CHAPTER 1. INTRODUCTION...................................1 CHAPTER 2. STUDY OF RELATED WORKS.........................2 2.1. ADABOOST.............................................2 2.2. SVM..................................................6 2.3. NEURAL NETWORK.......................................8 2.4. DISCUSSION..........................................10 2.4.1. ADABOOST..........................................10 2.4.2. SVM...............................................11 2.4.3. NUERAL NETWORK....................................12 CHAPTER 3. AN IMPLEMENTATION USING ADABOOST..............13 3.1. ADABOOST IN GENDER CLASSIFICATION...................13 3.1.1. THE ADABOOST ALGORITHM............................13 3.1.2. FAST FEATURE......................................16 3.2. TRAINING PROCESS....................................18 3.3. TESTING PROCESS.....................................21 CHAPTER 4. EXPERIMENTS AND RESULTS.......................25 4.1. TRAINING AND TESTING IMAGES.........................25 4.2. THE ADABOOST CLASSIFIER NUMBER......................26 4.3. RESULTS AND DISCUSSION..............................27 CHAPTER 5. CONCLUSIONS AND FUTURE WORK...................30 REFERENCE................................................32

    [1] S. Baluja and H. Rowley, “Boosting sex identification performance,” in Internatinal Journal of Computer Vision (IJCV), vol. 71, no. 1, pp. 111-119, 2007.
    [2] C. BenAbdelkader and P. Griffin, “A local region-based approach to gender classification from face images,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 52-52, 2005.
    [3] R. Brunelli and T. Poggio, “HyperBF networks for gender classification,” in Proceedings of the DARPA Image Understanding Workshop, pp. 311-314, 1992.
    [4] G. Cottrell, “EMPATH: face, emotion, and gender recognition using holons,” in Advances in Neural Information Processing Systems, pp. 564-571, 1991.
    [5] Y. Freund and R. Schapire, “A short introduction to boosting,” in Journal of Japanese Society for Artificial Intelligence, vol. 14, no. 5, pp. 771-780, 1999.
    [6] Y. Freund and R. Schapire, “Experiments with a new boosting algorithm,” in Proceedings of the Thirteenth International Conference on Machine Learning, pp. 148-156, 1996.
    [7] B. Golomb, D. Lawrence, and T. Sejnowski, “SEXNET: a neural network identifies sex from human faces,” in Advances in Neural Information Processing Systems, pp. 572-577, 1991.
    [8] S. Gutta, H. Wechsler, and P. J. Phillips, “Gender and ethnic classification,” in International Conference on Face & Gesture Recognition (FG), pp. 194-199, 1998.
    [9] H.-C. Lian and B.-L. Lu, “Multi-view gender classification using local binary patterns and support vector machines,” in Third International Symposium on Neural Networks (ISNN), vol. 2, pp. 202-209, 2006.
    [10] R. Lienhart and J. Maydt, “An extended set of Haar-like features for rapid object detection,” in International Conference on Image Processing (ICIP), pp. 900-903, 2002.
    [11] H. Lu, Y. Huang, and Y. Chen, “Automatic gender recognition based on pixel-pattern-based texture feature,” in J Real-Time Proc., pp. 109-116, 2008.
    [12] E. Mäkinen and R. Raisamo, “Evaluation of gender classification methods with automatically detected and aligned faces,” in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 30, no. 3, pp. 541-547, 2008.
    [13] B. Moghaddam and M.-H. Yang, “Gender classification with support vector machines,” in IEEE International Conference on Automatic Face and Gesture Recognition (FG), pp. 306-313, 2000.
    [14] G. Shakhnarovich, P. Viola, and B. Moghaddam, “A unified learning framework for real time face detection and classification,” in IEEE International Conference on Automatic Face and Gesture Recognition (FGR), pp. 16-26, 2002.
    [15] Z. Sun, G. Bebis, X. Yuan, and S. J. Louis, “Genetic feature subset selection for gender classification: a comparison study,” in IEEE Workshop on Applications of Computer Vision (WACV), pp. 165-170, 2002.
    [16] S.Tamura, H.Kawai, and H. Mitsumoto, “Male/female identification from 8x6 very low resolution face images by neural network,” in Pattern Recognition, vol. 29, no. 2, pp. 331-335, 1996.
    [17] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 511-518, 2001.
    [18] L. Wiskott, J.-M. Fellous, N. Krüger, and C. von der Malsburg, “Face recognition and gender determination,” in Proceedings of the International Workshop on Automatic Face and Gesture Recognition (FG), pp. 92-97, 1995.
    [19] B. Wu, H. Ai, and C. Huang, “Real-time gender classification,” in Third International Symposium on Multispectral Image Processing and Pattern Recognition, vol. 5286, pp. 498-503, 2003.
    [20] “OpenCV 1.0, open source computer vision library,” 2006. [Online]. Available” http://www.intel.com/technology/computing/opencv/

    下載圖示 校內：2010-08-27公開
    校外：2010-08-27公開
    QR CODE