本篇論文基於一種機器學習演算法在即時人臉偵測中，使用高伯特徵方式截取不同角度的人臉進行影像處理後，以掃描的步驟利用積分影像快速偵測人臉的矩形特徵點，產生大量的弱分類器，選擇其中最佳的弱分類器組合成一個強分類器，將強分類器串聯成一組層疊分類器，可排除大部分非人臉影像，實現最佳效能，同時也降低誤判機率。此方法除了實現迅速，能有效增強影像中人臉的角度，也能夠有效擷取人臉高準確度外，在針對布斯特演算法來加強偵測人臉，最終可以得到相當滿意的實驗結果，與傳統的偵測法相比，誤判率將可大大的降低25%。

This paper describes a Real-time Face Detection method based on a machine learning algorithm for select Gabor feature to choose the best classifier. We have trained a classifier using Adaboost algorithm with a set of Gabor feature extracted from images. The integral image of a rectangle features can be computed very quickly which selects a simple and efficient classifier to build a very large number of weak learners. This method can be combined into a cascade that is called the strong classifiers, it is contained the combination of the best weak learner classifiers. We used those series of cascade to discard the non-face patterns, this method can be reduced false positive rate and minimized false negative rate. Our classifier can be achieved high computation performance and effectively enhanced the image of human face angle, compared to the conventional detection methods, the false positive rate will be greatly reduced 25%.

[1]M. Lades, J. C. Vorbruggen, J. Buhmann, J. Lange, C. Vandermalsburg, R. P. Wurtz, and W. Konen, “Distortion invariant object recognition in the Dynamic Link Architecture”, IEEE Transactions on Computers, vol. 42, no. 3, pp. 300-311, 1993.
[2]L. Wiskott, J. M. Fellous, N. Kruger, and C. vonderMalsburg, “Face recognition by elastic bunch graph matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 775-779, 1997.
[3]L. Shen and L. Bai, “Face recognition based on Gabor features using kernel methods,” in Proc. Of the 6th IEEE Conference on Face and Gesture Recognition Korea: 2004, pp. 170-175.
[4]Y. Freund and R. Schapire, “A short introduction to boosting,” Journal of Japanese Society for Artifical Intelligence, vol. 14, no. 5, pp. 771-780, 1999.
[5]Yoav Freund and Robert E. Schapire. “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, 55(1):119–139, August 1997.
[6]P. Viola, M. Jones, “Robust real-time face detection”, International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.
[7]Lienhart R., Liang L. and Kuranov A., “A Detector Tree of Boosted Classifiers for Real-time Object Detection and Tracking”, Microcomputer Research Labs, Intel Corperation, Santa Clara, CA., vol. 2, pp.II-277-80, 2003.
[8]V. Kyrki J. K. Kamarainen, and H Kalviainen, “Simple Gabor feature space for invariant object recognition,” Patter Recognition Letters, vol. 25, no. 3, pp. 311-318, 2004.
[9]P. J. Phillips, H. Moon, S. A. Rizvi, and P. J. Rauss, “The FERET evaluation methodology for face-recognition algorithms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1090-1104, 2000.
[10]C. J. Liu and H. Wechsler, “Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition,” IEEE Transactions on Image Processing, vol. 11, no. 4, pp. 467-476, 2002.
[11]Kamarainen, J.-K.; Kyrki, V.; “Invariance properties of Gabor filter-based features overview and applications”, Image Processing, IEEE Transactions on, vol. 15,No.5, pp. 1088-1099, 2006.
[12]Jensen, O. H., “Implementing the Viola-Jones face detection algorithm”, MSc thesis, Technical University of Denmark, 2008.
[13]Erik Hjelmås and Boon Kee Low, “Face Detection: A survey”, Computer Vision and Image Understanding, vol. 83(3), pp. 236-274, 2001.
[14]M.-H. Yang, D. J. Kriegman and N. Ahuja, “Detecting Faces in Images: A Survey”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24(I), pp. 34 – 58, 2002.
[15]J. Kovac, P. Peer, F. Solina, “Human skin color clustering for face detection”, EUROCON2003, 2003.
[16]R. Chellappa, C. L. Wilson, and S. Sirohey. “Human and machine recognition of faces: A survey”, Proc. IEEE 83, 5, 1995.
[17]A. Yuille, P. Hallinan, and D. Cohen, “Feature Extraction from Faces Using Deformable Templates”, Int’l J. Computer Vision, vol. 8, no. 2, pp. 99-111, 1992.
[18]Nefian A.V., Hayes M.H., “Maximum likelihood training of the embedded HMM for face detection and recognition”, Proc. IEEE Conf. Image Processing, vol.1, pp. 33-36, 2000.
[19]J. J de Dios, N. Garcia, “Face detection based on a new color space YCgCr”, ICIP03, vol.2, pp III-909-12, 2003
[20] P. Deng and M. Pei, “Multi view Face Detection Based on AdaBoost and skin color,” IEEE First International Conference on Intelligent Networks and Intelligent Systems (ICINIS), pp. 457-460, 2008.
[21]K. N. Plataniotis, A . N. Venetsanopoulus, “Color Image Processing and Application”, Springer 2000.
[22]http://www.mathworks.com
[23]Ben Jemaa, Y.; Khanfir, S.; “Automatic Gabor Features Extraction for Face Recognition using Neural Networks”, Image Processing Theory, Tools & Application, IPTA 2008
[24]Linlin Shen, Li Bai, Daniel Bardsley, Yangsheng Wang, “Gabor Feature Selection for Face Recognition using Improved AdaBoost Learning”, Proceedings of International Workshop on Biometric Recognition System, in conjunction with ICCV’05
[25]LinLin Shen, Li Bai, “Adaboost Gabor feature selection for classification”, School of CS & IT, University of Nottingham, UK. 2004
[26]S. A. Inalou and S. Kasaei, "AdaBoost-Based Face Detection in Color Images with Low False Alarm,” Second International Conference on Computer Modeling and Simulation, vol. 2, pp. 107-111, 2010.
[27]Cheol Hun Han, Kwee-Bo Sim; “Real-Time Face Detection Using AdaBoot Algorithm,” International Conference on Control, Automation and Systems 2008