A hierarchical learning network for face detection with in-plane rotation

This paper presents a scale and rotation invariant face detection system. The system employs a hierarchical neural network, called SICoNNet, whose processing elements are governed by the nonlinear mechanism of shunting inhibition. The neural network is used as a face/nonface classifier that can handle in-plane rotated patterns. To train the network as a rotation invariant face classifier, an enhanced bootstrap training technique is developed, which prevents bias towards the nonface class. Furthermore, a multiresolution processing is employed for scale invariance: an image pyramid is formed through sub-sampling and face detection is performed at each scale of the pyramid using an adaptive threshold. Evaluated on the benchmark CMU rotated face database, the proposed face detection system outperforms some of the existing rotation invariant face detectors; it has fewer false positives and higher detection accuracy.

[1]  Steve McLaughlin,et al.  Comparative study of textural analysis techniques to characterise tissue from intravascular ultrasound , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[2]  Roland T. Chin,et al.  On Image Analysis by the Methods of Moments , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Etienne Barnard,et al.  Invariance and neural nets , 1991, IEEE Trans. Neural Networks.

[4]  S. Grossberg.  Neural Networks and Natural Intelligence , 1988 .

[5]  Bo Wu,et al.  Fast rotation invariant multi-view face detection based on real Adaboost , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[6]  Abdesselam Bouzerdoum,et al.  Application of shunting inhibitory artificial neural networks to medical diagnosis , 2001, The Seventh Australian and New Zealand Intelligent Information Systems Conference, 2001.

[7]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Abdesselam Bouzerdoum,et al.  Efficient training algorithms for a class of shunting inhibitory convolutional neural networks , 2005, IEEE Transactions on Neural Networks.

[10]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  Chee-Way Chong,et al.  Translation invariants of Zernike moments , 2003, Pattern Recognit..

[12]  L. Spirkovska,et al.  Rapid training of higher-order neural networks for invariant pattern recognition , 1989, International 1989 Joint Conference on Neural Networks.

[13]  R. Darnell.  Translation , 1873, The Indian medical gazette.

[14]  Narendra Ahuja,et al.  A SNoW-Based Face Detector , 1999, NIPS.

[15]  A. Bouzerdoum,et al.  A face detection system using shunting inhibitory convolutional neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[16]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[17]  R. Pfeifer,et al.  Connectionism in Perspective , 1989 .

[18]  Juergen Luettin,et al.  Fast Face Detection using MLP and FFT , 1999 .

[19]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

[20]  Peter Secretan.  Learning , 1965, Mental Health.

[21]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[22]  Reiner Lenz,et al.  Group invariant pattern recognition , 1990, Pattern Recognit..

[23]  Paul A. Viola,et al.  Fast Multi-view Face Detection , 2003 .

[24]  Sang Uk Lee,et al.  Rotation invariant face detection using a model-based clustering algorithm , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[25]  Erik Hjelmås,et al.  Face Detection: A Survey , 2001, Comput. Vis. Image Underst..

[26]  Abdesselam Bouzerdoum.  Classification and function approximation using feed-forward shunting inhibitory artificial neural networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[27]  Ruye Wang,et al.  A hybrid learning network for shift-invariant recognition , 2001, Neural Networks.

[28]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[29]  Xiuwen Liu,et al.  Rotation Invariant Face Detection using Spectral Histograms and Support Vector Machines , 2006, 2006 International Conference on Image Processing.

[30]  JEFFREY WOOD,et al.  Invariant pattern recognition: A review , 1996, Pattern Recognit..

[31]  Abdesselam Bouzerdoum,et al.  A Shunting Inhibitory Convolutional Neural Network for Gender Classification , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[32]  Takeo Kanade,et al.  Rotation Invariant Neural Network-Based Face Detection , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[33]  Stavros J. Perantonis,et al.  Two highly efficient second-order algorithms for training feedforward networks , 2002, IEEE Trans. Neural Networks.

[34]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[35]  Beat Fasel,et al.  Rotation-Invariant Neoperceptron , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[36]  Abdesselam Bouzerdoum,et al.  A Gender Recognition System using Shunting Inhibitory Convolutional Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[37]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[38]  Abdesselam Bouzerdoum,et al.  Rotation Invariant Face Detection Using Convolutional Neural Networks , 2006, ICONIP.

[39]  Abdesselam Bouzerdoum,et al.  Skin segmentation using color pixel classification: analysis and comparison , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  M. Rodrigues.  Invariants for pattern recognition and classification , 2000 .

[41]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[42]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[43]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[44]  Alireza Khotanzad,et al.  Classification of invariant image representations using a neural network , 1990, IEEE Trans. Acoust. Speech Signal Process..

[45]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[46]  Christophe Garcia,et al.  Convolutional face finder: a neural architecture for fast and robust face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Shunji Satoh,et al.  Recognition of Rotated Patterns Using Neocognitron , 1999, ICONIP.

[48]  Abdesselam Bouzerdoum.  A new class of high-order neural networks with nonlinear decision boundaries , 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

[49]  Matthias Gruber,et al.  Moment-Based Image Normalization With High Noise-Tolerance , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[51]  Paulo J. G. Lisboa,et al.  Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.

[52]  Minoru Fukumi,et al.  Rotation-invariant neural pattern recognition system with application to coin recognition , 1992, IEEE Trans. Neural Networks.

[53]  Xilin Chen,et al.  Combining Skin Color Model and Neural Network for Rotation Invariant Face Detection , 2000, ICMI.

[54]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[55]  Anthony Watson,et al.  Naive Bayes face-nonface classifier: a study of preprocessing and feature extraction techniques , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[56]  A. Bouzerdoum,et al.  Texture Classification using Convolutional Neural Networks , 2006, TENCON 2006 - 2006 IEEE Region 10 Conference.

[57]  M. Teague.  Image analysis via the general theory of moments , 1980 .

[58]  Abdesselam Bouzerdoum,et al.  Application of SiCONnets to Handwritten Digit Recognition , 2006, Int. J. Comput. Intell. Appl..

[59]  Xiaoqing Ding,et al.  Real-time rotation invariant face detection based on cost-sensitive AdaBoost , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[60]  Abdesselam Bouzerdoum,et al.  A Nonlinear Feature Extractor for Texture Segmentation , 2007, 2007 IEEE International Conference on Image Processing.