Robust Face Detection Based on Knowledge-Directed Specification of Bottom-Up Saliency

ETRI Journal

关键词: bottom-up saliency;    knowledge-directed specification;    goal-specific visual attention;    Face detection;   

Others  :  1186085
DOI  :  10.4218/etrij.11.1510.0123

【 摘 要 】

This paper presents a novel approach to face detection by localizing faces as the goal-specific saliencies in a scene, using the framework of selective visual attention of a human with a particular goal in mind. The proposed approach aims at achieving human-like robustness as well as efficiency in face detection under large scene variations. The key is to establish how the specific knowledge relevant to the goal interacts with the bottom-up process of external visual stimuli for saliency detection. We propose a direct incorporation of the goal-related knowledge into the specification and/or modification of the internal process of a general bottom-up saliency detection framework. More specifically, prior knowledge of the human face, such as its size, skin color, and shape, is directly set to the window size and color signature for computing the center of difference, as well as to modify the importance weight, as a means of transforming into a goal-specific saliency detection. The experimental evaluation shows that the proposed method reaches a detection rate of 93.4% with a false positive rate of 7.1%, indicating the robustness against a wide variation of scale and rotation.

   

【 参考文献 】

• [1]L. Paletta, E. Rome, and H. Buxton, "Attention Architectures for Machine Vision and Mobile Robots," Neurobiology of Attention, New York: Academic Press, 2005, pp. 642-648.
• [2]L. Itti and C. Koch, "Computational Modeling of Visual Attention," Nat. Rev. Neurosci., vol. 2, no. 3, 2001, pp. 194-203.
• [3]L. Itti, C. Koch, and E. Niebur, "A Model of Saliency Based Visual Attention for Rapid Scene Analysis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 1, 1998, pp. 1254-1259.
• [4]L. Itti and C. Koch, "A Saliency-Based Search Mechanism for Overt and Covert Shifts of Visual Attention," Vis. Res., vol. 40, 2000, pp. 1489-1506.
• [5]L. Itti and P. Baldi, "Bayesian Surprise Attracts Human Attention," Proc. NIPS, 2005, pp. 547-554.
• [6]D. Walther and C. Koch, "Modeling Attention to Salient Proto-objects," Neural Netw., vol. 19, 2006, pp. 1395-1407.
• [7]D. Walther et al., "Attentional Selection for Object Recognition–A Gentle Way," Lect. Notes Comput. Sci., vol. 2525, no. 1, 2002, pp. 472-479.
• [8]S. Frintrop, VOCUS: A Visual Attention System for Object Detection and Goal Directed Search, PhD thesis, University of Bonn, Germany, 2005.
• [9]D. Gao, V. Mahadevan, and N. Vasconcelos, "The Discriminant Centersurround Hypothesis for Bottom-Up Saliency," NIPS, 2007.
• [10]V. Navalpakkam and L. Itti, "An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed," Proc. IEEE CVPR, vol. 2, 2006, pp. 2049-2056.
• [11]C. Papageorgiou and T. Poggio, "A Trainable System for Object Detection," Int. J. Comput. Vision, vol. 38, no. 1, 2000, pp. 15-33.
• [12]H.A. Rowley, S. Baluja, and T. Kanade, "Neural Network Based Face Detection," IEEE Trans. PAMI, vol. 20, no. 1, 1998, pp. 23-38.
• [13]H. Schneiderman and T. Kanade, "A Statistical Method for 3D Object Detection Applied to Faces and Cars," Proc. IEEE CVPR, 2000, pp. 746-751.
• [14]P. Viola and M.J. Jones, "Robust Real-Time Face Detection," Int. J. Computer Vision, vol. 57, no. 2, 2004, pp. 137-154.
• [15]P. Viola, M.J. Jones, and D. Snow, "Detecting Pedestrians Using Patterns of Motion and Appearance," Int. J. Comput. Vision, vol. 63, no. 2, 2005, pp. 153-161.
• [16]V. Navalpakkam and L. Itti, "Sharing Resources: Buy Attention, Get Recognition," Proc. Int. Workshop Attention Performance Comput. Vision, 2003.
• [17]O. Ramström and H. Christensen, "Object Detection Using Background Context," Proc. Int. Conf. Pattern Recognition, 2004, pp. 45-48.
• [18]S. Choi, S. Ban, and M. Lee, "Biologically Motivated Visual Attention System Using Bottom-Up Saliency Map and Top Down Inhibition," Neural Info. Process.-Lett. Review, vol. 2, no. 1, 2004, pp. 19-25.
• [19]K. Lee, H. Buxton, and J. Feng, "Selective Attention for Cue Guided Search Using a Spiking Neural Network," Proc. Workshop Attention Performance Comput. Vision, 2003, pp. 55-63.
• [20]S.W. Ban, M. Lee, and H.S. Yang, "A Face Detection Using Biologically Motivated Bottom-Up Saliency Map Model and Top-Down Perception Model," Neuro Comput., vol. 56, 2004, pp. 475- 480.
• [21]N. Habili, C.C. Lim, and A. Moini, "Segmentation of the Face and Hands in Sign Language Video Sequences Using Color and Motion Cues," IEEE Trans. Circ. Syst. Video Technol., vol. 14, no. 8, 2004, pp. 1086-1097.
• [22]Intel Corporation. OpenCV: Open Source Computer Vision Library, http://www.intel.com/research/mrl/research/opencv/
• [23]R. Lienhart and J. Maydt, "An Extended Set of Haar-Like Features for Rapid Object Detection," IEEE Conf. Image Process., vol. 1, 2002, pp. 900-903.
• [24]D. Bradley, "Profile Face Detection," Intel Research Award Contest, 2003.
• [25]L. Feng and G. Michael, "Region Enhanced Scale-Invariant Saliency Detection," IEEE Int. Conf. Multimedia Expo, 2006, pp. 1477-1480.
• [26]H. Li and K.N. Ngan, "Saliency Model Based Face Segmentation and Tracking in Head-and-Shoulder Video Sequences," J. Visual Commun. Image Representation, vol. 19, no. 5, 2008, pp. 320-333.
• [27]V. Govindaraju, "Locating Human Faces in Photographs," Int. J. Comput. Vision, vol. 19, no. 2, 1996, pp. 129-146.