Improving alignment of faces for recognition

Face recognition systems for uncontrolled environments often work through an alignment, feature extraction, and recognition pipeline. Effective alignment of faces is thus crucial as can be an entry point in the process and poor alignments can greatly affect recognition performance. The task of alignment is particularly difficult when a face comes from highly unconstrained environments or so called faces in the wild. A lot of recent research activity has focused on faces in the wild and even simple similarity or affine transformations have proven both effective and essential to achieving state of the art performance. In this paper we explore a straightforward, fast and effective approach to aligning faces based on detecting facial landmarks using Haar-like image features and a cascade of boosted classifiers. Our approach is reminiscent of widely used face detection approaches, but focused on much more detailed features of a face such eye centres, the nose tip and corners of the mouth. This process generates multiple candidates for each landmark and we present a fast and effective filtering strategy allowing us to find sets of landmarks that are consistent. Our experiments show that this approach can outperform contemporary methods and easily fits into popular processing pipelines for faces in the wild.

[1]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[2]  Erik G. Learned-Miller,et al.  Data driven image models through continuous joint alignment , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Erik G. Learned-Miller,et al.  Unsupervised Joint Alignment of Complex Images , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[4]  Adam Schmidt,et al.  The put face database , 2008 .

[5]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[6]  Yaniv Taigman,et al.  Descriptor Based Methods in the Wild , 2008 .

[7]  Adam Schmidt,et al.  The architecture and performance of the face and eyes detection system based on the Haar cascade classifiers , 2009, Pattern Analysis and Applications.

[8]  Tal Hassner,et al.  Similarity Scores Based on Background Samples , 2009, ACCV.

[9]  Li Bai,et al.  Cosine Similarity Metric Learning for Face Verification , 2010, ACCV.

[10]  Matthijs C. Dorst Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[11]  Umar Mohammed,et al.  Probabilistic Models for Inference about Identity , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.