iccv iccv2013 iccv2013-157 iccv2013-157-reference knowledge-graph by maker-knowledge-mining

157 iccv-2013-Fast Face Detector Training Using Tailored Views


Source: pdf

Author: Kristina Scherbaum, James Petterson, Rogerio S. Feris, Volker Blanz, Hans-Peter Seidel

Abstract: Face detection is an important task in computer vision and often serves as the first step for a variety of applications. State-of-the-art approaches use efficient learning algorithms and train on large amounts of manually labeled imagery. Acquiring appropriate training images, however, is very time-consuming and does not guarantee that the collected training data is representative in terms of data variability. Moreover, available data sets are often acquired under controlled settings, restricting, for example, scene illumination or 3D head pose to a narrow range. This paper takes a look into the automated generation of adaptive training samples from a 3D morphable face model. Using statistical insights, the tailored training data guarantees full data variability and is enriched by arbitrary facial attributes such as age or body weight. Moreover, it can automatically adapt to environmental constraints, such as illumination or viewing angle of recorded video footage from surveillance cameras. We use the tailored imagery to train a new many-core imple- mentation of Viola Jones ’ AdaBoost object detection framework. The new implementation is not only faster but also enables the use of multiple feature channels such as color features at training time. In our experiments we trained seven view-dependent face detectors and evaluate these on the Face Detection Data Set and Benchmark (FDDB). Our experiments show that the use of tailored training imagery outperforms state-of-the-art approaches on this challenging dataset.


reference text

[1] V. Jain and E. Learned-Miller, “FDDB: A benchmark for face detection in unconstrained settings,” Univ. of Massachusetts, Amherst, Tech. Rep., 2010.

[2] V. Blanz and T. Vetter, “A morphable model for the synthesis of 3D faces,” ACM Transactions on Graphics (SIGGRAPH’99), pp. 187–194, 1999.

[3] K. Scherbaum, M. Sunkel, H.-P. Seidel, and V. Blanz, “Prediction of Individual Non-Linear Aging Trajectories of Faces,” Comput. Graphics Forum (EUROGRAPHICS’07).

[4] P. Viola and M. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” IEEE Conf. on Comput. Vision and Pattern Recog. (CVPR’01), p. 511, 2001.

[5] M.-H. Yang, D. J. Kriegman, and N. Ahuja, “Detecting faces in images: a survey,” IEEE Trans. Pattern Anal. Mach. Intell. (PAMI’02), pp. 34–58, 2002.

[6] C. Zhang and Z. Zhengyou, “A survey of recent advances in face detection,” Microsoft Research, Tech. Report MSR-TR2010-66, 2010.

[7] P. Viola and M. Jones, “Robust real-time face detection,” Intl. J. Comput. Vision (IJCV’04), pp. 137–154, 2004.

[8] J. Kong and Y. Deng, “GPU accelerated face detection,” Intl. Conf. on Intell. Control and Inf. Process. (ICICIP’10), ’ 10. 2854

[9] “A software-based dynamic-warp scheduling approach for load-balancing the Viola-Jones face detection algorithm on GPUs,” J. Parallel and Distrib. Comput., 2013.

[10] B. Sharma, R. Thota, N. Vydyanathan, and A. Kale, “Towards a robust, real-time face processing system using CUDAenabled GPUs,” Intl. Conf. on High Performance Comput. (HiPC’09), pp. 368–377, 2009.

[11] G. Wei and C. Ming, “The face detection system based on GPU+CPU desktop cluster,” Intl. Conf. on Multimedia Technol. (ICMT’11), pp. 3735–3738, 2011.

[12] S. L. H. Chuang Jan Chang, “LSO-AdaBoost Based Face Detection for IP-CAM Video,” Applied Mechanics and Mater., pp. 3543–3548, 2013.

[13] J. Cho, B. Benson, S. Mirzaei, and R. Kastner, “Parallelized Architecture of Multiple Classifiers for Face Detection,” IEEE Intl. Conf. on Application-specific Syst., Architectures and Processors (ASAP’09), pp. 75–82, 2009.

[14] N. Zhang, “Working towards efficient parallel computing of integral images on multi-core processors,” Intl. Conf. on Comput. Eng. and Technol. (ICCET’10), pp. 30–34, 2010.

[15] M.-T. Pham, Y. Gao, V. Hoang, and T.-J. Cham, “Fast polygonal integration and its application in extending haar-like features to improve object detection,” IEEE Conf. on Comput. Vision and Pattern Recog. (CVPR’10), pp. 942–949, 2010.

[16] C.-H. Chiang, C.-H. Kao, G.-R. Li, and B.-C. Lai, “Multilevel parallelism analysis of face detection on a shared memory multi-core system,” Intl. Symp. on VLSI Design, Automation and Test (VLSI-DAT’11), pp. 1–4, 2011.

[17] Y.-T. Wu, Y.-T. Wu, C.-Y. Cho, S.-Y. Tseng, C.-N. Liu, and C.-T. King, “Parallel Integral Image Generation Algorithm on Multi-core System,” IEEE Intl. Symp. on Parallel and Distrib. Process. with Applications (ISPA ’11), pp. 3 1–35, 2011.

[18] B.-C. C. Lai, C.-H. Chiang, and G.-R. Li, “Data locality optimization for a parallel object detection on embedded multicore systems,” IEEE Intl. Conf. on Software Eng. and Service Science, pp. 576–579, 2011.

[19] M. Everingham, A. Zisserman, C. Williams, L. V. Gool, M. Allan, C. Bishop, O. Chapelle, N. Dalal, T. Deselaers, G. Dorko, S. Duffner, J. Eichhorn, J. Farquhar, M. Fritz, C. Garcia, T. Griffiths, F. Jurie, D. Keysers, M. Koskela, J. Laaksonen, D. Larlus, B. Leibe, H. Meng, H. Ney, B. Schiele, C. Schmid, E. Seemann, J. Shawe-Taylor, A. Storkey, S. Szedmak, B. Triggs, I. Ulusoy, V. Viitaniemi, and J. Zhang, “The’05 pascal visual object classes challenge,” in 1st PASCAL Challenges Workshop, 2005.

[20] B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman, “LabelMe: A Database and Web-Based Tool for Image Annotation,” pp. 157–173, 2008.

[21] A. Torralba, R. Fergus, and W. Freeman, “80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition,” IEEE Trans. Pattern Anal. Mach. Intell. (PAMI’08), pp. 1958–1970, 2008.

[22] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” Conf. on Comput. Vision and Pattern Recog. (CVPR’09), 2009.

[23] R. Fergus, L. Fei-Fei, P. Perona, and A. Zisserman, “Learning Object Categories from Google’s Image Search,” IEEE Intl. Conf. on Comput. Vision (ICCV’05), pp. 1816–1823, 2005.

[24] J. Jeon, V. Lavrenko, R. Manmatha, “Automatic image annotation & retrieval using cross-media relevance models” 2003.

[25] J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman, “Discovering objects and their location in images,” IEEE Intl. Conf. on Comput. Vision (ICCV’05).

[26] A. Makadia, V. Pavlovic, and S. Kumar, “Baselines for Image Annotation,” Intl. J. Comput. Vision, pp. 88–105, 2010.

[27] D. Tsai, Y. Jing, Y. Liu, H. Rowley, S. Ioffe, and J. Rehg, “Large-scale image annotation using visual synset,” IEEE Intl. Conf. on Comput. Vision (ICCV’11), pp. 611–618, 2011.

[28] L. Denoyer and P. Gallinari, “A Ranking Based Model for Automatic Image Annotation in a Social Network,” Intl. AAAI Conf. on Weblogs and Social Media (ICWSM’10), 2010.

[29] Y.-Y. Chen, W. H. Hsu, and H.-Y. M. Liao, “Learning facial attributes by crowdsourcing in social media,” Intl. Conf.

[30] [3 1]

[32]

[33]

[34]

[35]

[36]

[37]

[38]

[39]

[40] Companion on World Wide Web (WWW’11), 2011. R. Gross, “Face Databases,” Handbook of Face Recogn. 2005. M. Grgic, http://www.face-rec.org/databases/, last checked: 04/2013, Face Recognition Homepage. R. Frischholz, http://www.facedetection.com/facedetection/ datasets.htm, last checked: 04/2013, The Face Detection Homepage. P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, and W. Worek, “Overview of the Face Recognition Grand Challenge,” Proc. of the IEEE Conf. on Comput. Vision and Pattern Recog. (CVPR’05), pp. 947–954, 2005. G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments,” Univ. of Massachusetts, Amherst, Tech. Rep., 2007. Y.-M. Li, J. Chen, L.-Y. Qing, B.-C. Yin, and W. Gao, “Face detection under variable lighting based on resample by face relighting,” Intl. Conf. on Machine Learn. and Cybern. (ICMLC’04), pp. 3775–3780, 2004. D. Zhou, D. Petrovska-Delacre´taz, and B. Dorizzi, “3D Active Shape Model for Automatic Facial Landmark Location Trained with Automatically Generated Landmark Points,” Intl. Conf. on Pattern Recog. (ICPR’10), pp. 3801–3805, 2010. V. Blanz, P. Grother, P. Phillips, and T. Vetter, “Face recognition based on frontal views generated from non-frontal images,” IEEE Conf. on Comput. Vision and Pattern Recog. (CVPR’05), 2005. A. Rama and F. Tarres, “P2CA: a new face recognition scheme combining 2D and 3D information,” IEEE Intl. Conf. on Image Process. (ICIP’05), pp. 776–9, 2005. M. Toews and T. Arbel, “Detecting and Localizing 3D Object Classes using Viewpoint Invariant Reference Frames,” IEEE Intl. Conf. on Comput. Vision (ICCV’07), pp. 1–8, 2007. L. Wang, L. Ding, X. Ding, and C. Fang, “Improved 3D assisted pose-invariant face recognition,” IEEE Intl. Conf. on Acoustics, Speech and Signal Process. (ICASSP’09).

[41] A. Ansari, M. Mahoor, and M. Abdel-Mottaleb, “Normalized 3D to 2D model-based facial image synthesis for 2D modelbased face recognition,” IEEE GCC Conf. and Exhibition (GCC’11),, pp. 178–181, 2011.

[42] K. Bowyer, K. Chang, and P. Flynn, “A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition,” Comput. Vision and Img. Understanding, 2006.

[43] L. Pishchulin, T. Thorma¨hlen, and C. Wojek, “Learning People Detection Models from Few Training Samples,” IEEE Conf. on Comput. Vision and Pattern Recog. (CVPR ’10).

[44] B. Weyrauch, B. Heisele, J. Huang, and V. Blanz, “Component-Based Face Recognition with 3D Morphable Models,” Comput. Vision and Pattern Recog. Workshop (CVPRW’04), p. 85, 2004.

[45] A. Frome, G. Cheung, A. Abdulkader, M. Zennaro, B. Wu, A. Bissacco, H. Adam, H. Neven, and L. Vincent, “Largescale privacy protection in google street view,” IEEE Intl. Conf. on Comput. Vision (ICCV’09), pp. 2373–2380, 2009.

[46] J.-C. Terrillon, H. Fukamachi, S. Akamatsu, and M. N. Shirazi, “Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images,” IEEE Intl. Conf. on Autom. Face and Gesture Recog. (FG’00), pp. 54–63, 2000.

[47] C. Huang, H. Ai, Y. Li, and S. Lao, “Vector boosting for rotation invariant multi-view face detection,” IEEE Intl. Conf. on Comput. Vision (ICCV’05). 2855