Optimally Training a Cascade Classifier

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are a few reported methods addressing this requirement in the context of object detection, there is no a principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such an algorithm here. We show a special case of the biased minimax probability machine has the same formulation as the linear asymmetric classifier (LAC) of \cite{wu2005linear}. We then design a new boosting algorithm that directly optimizes the cost function of LAC. The resulting totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on object detection verify the effectiveness of the proposed boosting algorithm as a node classifier in cascade object detection, and show performance better than that of the current state-of-the-art.

[1]  Peter L. Bartlett,et al.  Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks , 2008, J. Mach. Learn. Res..

[2]  Marc Teboulle,et al.  Mirror descent and nonlinear projected subgradient methods for convex optimization , 2003, Oper. Res. Lett..

[3]  Stan Z. Li,et al.  FloatBoost learning and statistical face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jian Zhang,et al.  Face detection from few training examples , 2008, 2008 15th IEEE International Conference on Image Processing.

[5]  Murat Dundar,et al.  Joint Optimization of Cascaded Classifiers for Computer Aided Detection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[7]  Nick Barnes,et al.  Asymmetric Totally-Corrective Boosting for Real-Time Object Detection , 2010, ACCV.

[8]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Pietro Perona,et al.  Multiple Component Learning for Object Detection , 2008, ECCV.

[10]  Jian Zhang,et al.  Efficiently training a better visual detector with sparse eigenvectors , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Ramón López de Mántaras,et al.  Fast and robust object segmentation with the Integral Linear Classifier , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[13]  Nuno Vasconcelos,et al.  Asymmetric boosting , 2007, ICML '07.

[14]  Harry Shum,et al.  Kullback-Leibler boosting , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  Jian Zhang,et al.  Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  Ramakant Nevatia,et al.  Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Paul A. Viola,et al.  Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade , 2001, NIPS.

[18]  Hsuan-Tien Lin,et al.  One-sided Support Vector Regression for Multiclass Cost-sensitive Classification , 2010, ICML.

[19]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Chunhua Shen,et al.  On the Dual Formulation of Boosting Algorithms , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  James M. Rehg,et al.  On the Design of Cascades of Boosted Ensembles for Face Detection , 2008, International Journal of Computer Vision.

[23]  Paul A. Viola,et al.  Multiple Instance Boosting for Object Detection , 2005, NIPS.

[24]  Larry S. Davis,et al.  Multiple instance fFeature for robust part-based object detection , 2009, CVPR.

[25]  Jonathan Brandt,et al.  Robust object detection via soft cascade , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[26]  James M. Rehg,et al.  Learning a Rare Event Detection Cascade by Direct Feature Selection , 2003, NIPS.

[27]  Dariu Gavrila,et al.  Multi-cue pedestrian classification with partial occlusion handling , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Chunhua Shen,et al.  Pedestrian Detection Using Center-Symmetric Local Binary Patterns , 2010, International Conference on Information Photonics.

[29]  James M. Rehg,et al.  Fast Asymmetric Learning for Cascade Face Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[31]  Rong Xiao,et al.  Dynamic Cascades for Face Detection , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[32]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[33]  Tat-Jen Cham,et al.  Online Learning Asymmetric Boosted Classifiers for Object Detection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Michael I. Jordan,et al.  A Robust Minimax Approach to Classification , 2003, J. Mach. Learn. Res..

[35]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[36]  Chunhua Shen,et al.  LACBoost and FisherBoost: Optimally Building Cascade Classifiers , 2010, ECCV.

[37]  Tat-Jen Cham,et al.  Fast training and selection of Haar features using statistics in boosting-based face detection , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[38]  Weihong Wang,et al.  Improved human detection and classification in thermal images , 2010, 2010 IEEE International Conference on Image Processing.

[39]  Jian Zhang,et al.  Efficiently Learning a Detection Cascade With Sparse Eigenvectors , 2011, IEEE Transactions on Image Processing.

[40]  Shuicheng Yan,et al.  Discriminative local binary patterns for human detection in personal album , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Yaoliang Yu,et al.  A General Projection Property for Distribution Families , 2009, NIPS.

[42]  James M. Rehg,et al.  Linear Asymmetric Classifier for cascade detectors , 2005, ICML.

[43]  Lai-Wan Chan,et al.  The Minimum Error Minimax Probability Machine , 2004, J. Mach. Learn. Res..

[44]  Gunnar Rätsch,et al.  Constructing Boosting Algorithms from SVMs: An Application to One-Class Classification , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[46]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[47]  Jinbo Bi,et al.  Computer aided detection via asymmetric cascade of sparse hyperplane classifiers , 2006, KDD '06.

[48]  Tat-Jen Cham,et al.  Detection with multi-exit asymmetric boosting , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[49]  Ayhan Demiriz,et al.  Linear Programming Boosting via Column Generation , 2002, Machine Learning.