Metric Learning Based False Positives Filtering for Face Detection

Face detection in the wild is a challenging task within the field of computer vision. Many face detectors fail to distinguish face images and non-face images because intra-class variations surpass inter-class variations. To overcome it, we propose a metric learning based false positives filtering for face detection. With 8 average faces as standard face, we apply metric learning to seek a linear transformation to reduce the distance between face images and standard faces while enlarge the distance between non-face images and standard faces. To solve our defining objective function for metric learning, we adopt a batch-stochastic gradient descent scheme, with which we can get stable solution fast. The results on FDDB and our self-collected dataset show a good performance of our method for improving Viola-Jones face detectors.

[1]  Rüdiger Dillmann,et al.  Incremental Learning of Task Sequences with Information-Theoretic Metrics , 2006, EUROS.

[2]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Deva Ramanan,et al.  Face detection, pose estimation, and landmark localization in the wild , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Kernel Machines , 2012, ArXiv.

[6]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[7]  Samy Bengio,et al.  Large Scale Online Learning of Image Similarity Through Ranking , 2009, J. Mach. Learn. Res..

[8]  Ying Wu,et al.  Detecting and Aligning Faces by Image Retrieval , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Erik Learned-Miller,et al.  FDDB: A benchmark for face detection in unconstrained settings , 2010 .

[10]  Gang Hua,et al.  Efficient Boosted Exemplar-Based Face Detection , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Jian Sun,et al.  Joint Cascade Face Detection and Alignment , 2014, ECCV.

[12]  Gang Hua,et al.  A convolutional neural network cascade for face detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Tao Wang,et al.  Face detection using SURF cascade , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[14]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[16]  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.