Tiny and Blurred Face Alignment for Long DistanceFace Recognition

ETRI Journal

关键词: human robot interaction;    face recognition;    face detection;    Face alignment;   

Others  :  1186139
DOI  :  10.4218/etrij.11.1510.0022

【 摘 要 】

Applying face alignment after face detection exerts a heavy influence on face recognition. Many researchers have recently investigated face alignment using databases collected from images taken at close distances and with low magnification. However, in the cases of home-service robots, captured images generally are of low resolution and low quality. Therefore, previous face alignment research, such as eye detection, is not appropriate for robot environments. The main purpose of this paper is to provide a new and effective approach in the alignment of small and blurred faces. We propose a face alignment method using the confidence value of Real-AdaBoost with a modified census transform feature. We also evaluate the face recognition system to compare the proposed face alignment module with those of other systems. Experimental results show that the proposed method has a high recognition rate, higher than face alignment methods using a manually-marked eye position.

   

【 参考文献 】

• [1]L. Aryananda, "Recognizing and Remembering Individuals: Online and Unsupervised Face Recognition for Humanoid Robot," IEEE/RSJ Int. Conf. Intell. Robots Syst., Sept. 2002, pp. 1202-1207.
• [2]M. Turk and A. Pentland, "Eigenfaces for Recognition," J. Cog. Neuroscience, vol. 3, no. 1, 1991, pp. 71-86.
• [3]D. Hansen and Q. Ji, "In the Eye of the Beholder: A Survey of Models for Eyes and Gaze," IEEE Trans. Pattern Anal. Mach. Intell. (submitted).
• [4]H. Kim and W. Kim, "Eye Detection in Facial Images Using Zernike Moments with SVM," ETRI J., vol. 30, no. 2, Apr. 2008, pp. 335-337.
• [5]M. Zhao and T. Chua, "Markovian Mixture Face Recognition with Discriminative Face Alignment," IEEE Int. Conf. Autom. Face Gesture Recog., Sept. 2008, pp. 1-6.
• [6]L. Wang, X. Ding, and C. Fang, "Generic Face Alignment using an Improved Active Shape Model," Int. Conf. Audio, Language, Image Process., July 2008, pp. 317-321.
• [7]F. Kahraman and M. Gokmen, "Illumination Invariant Three-Stage Approach for Face Alignment," IEEE Intl. Conf. Image Process., Oct. 2006, pp. 2073-2076.
• [8]Y. Su, H. Ai, and S. Lao, "Real-Time Face Alignment with Tracking in Video," IEEE Int. Conf. Image Process., Oct. 2008, pp. 1632-1635.
• [9]Y. Zhou et al., "A Bayesian Mixture Model for Multi-View Face Alignment," IEEE Computer Society Conf. Computer Vision Pattern Recog., vol. 2, June 2005, pp. 741-746.
• [10]K. Choi, J. Ahn, and H. Byun, "Face Alignment Using Segmentation and a Combined AAM in a PTZ Camera," Int. Conf. Pattern Recog., vol. 3, Sept. 2006, pp. 1191-1194.
• [11]X. Liu, "Generic Face Alignment Using Boosted Appearance Model," IEEE Conf. Computer Vision Pattern Recog., June 2007, pp. 1-8.
• [12]Y. Huang et al., "Face Alignment under Variable Illumination," IEEE Int. Conf. Autom. Face Gesture Recog., May 2004, pp. 85-90.
• [13]P. Wang, L. Tran, and Q. Ji, "Improving Face Recognition by Online Image Alignment," Int. Conf. Pattern Recog., vol. 1, Sept. 2006, pp. 311-314.
• [14]F. Kahraman, B. Kurt, and M. Gokmen, "Robust Face Alignment for Illumination and Pose Invariant Face Recognition," IEEE Conf. Computer Vision Pattern Recog., June 2007, pp. 1-7.
• [15]P. Wang et al., "Automatic Eye Detection and its Validation," IEEE Computer Soc. Conf. Computer Vision Pattern Recog., June 2005, pp. 164-164.
• [16]T. F. Cootes, G. J. Edwards, and C. J. Taylor, "Active Appearance Models," IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, no. 6, June 2001, pp. 681-685.
• [17]Y. Freund and R.E. Shapire, "A Short Introduction to Boosting," J. Japanese Society for Art. Intell., no. 14, Sept. 1999, pp. 771-780.
• [18]J. Friedman, T. Hastie, and R. Tibshirani, "Additive Logistic Regression: a Statistical View of Boosting," Annals of Statistics, vol. 38, no. 2, Apr. 2000, pp. 337-374.
• [19]B. Fröba and A. Ernst, "Face Detection with the Modified Census Transform," Int. Conf. Autom. Face Gesture Recog., 2004, pp. 91-96.
• [20]B. Jun and D. Kim, "Robust Real-Time Face Detection Using Face Certainty Map," Intl. Conf. Biometrics, vol. 4642, no. 125, Aug. 2007, pp. 29-38.
• [21]P. Viola and M. Jones, "Robust Real Time Object Detection," IEEE ICCV Workshop Statistical Computational Theories of Vision, July 2001, pp. 1-25.
• [22]M. Castrillón Santana et al., "Face and Face Feature Detection Evaluation - Performance Evaluation of Public Domain Haar Detectors for Face and Face Feature Detection," VISAPP. vol. 2, 2008, pp. 167-172.
• [23]Ho-Sub Yoon et al., "Face Component Detection on the Natural Office Scene," Intl. Conf. Adv. Intell. Mechatronics, 1997, p. 28.
• [24]D. Kim et al., "A Non-Cooperative User Authentication System in Robot Environments," IEEE Trans. Consum. Electron., vol. 53, no. 2, May 2007, pp. 804-811.
• [25]Intel. Open Source Computer Vision Library (OpenCV). Available at: http://sourceforge.net/projects/opencvlibrary/