Reconstruction Network for single-face detection and landmark localization

This paper introduces Reconstruction Network to reconstruct the regions of interest of one or more objects within an optical image without time-consuming image segmentation or key-point descriptors calculation. We evaluate Reconstruction Network using face detection and facial landmark localization. Experiments show that new algorithm learns the structure of face and facial landmarks automatically and obtains state-of-the-art performance for face detection (almost 50% higher detection rates than widely used method) and facial land-mark localization (0.03 lower mean error of key point location than two recently published methods) while requiring only a fraction of the computing resources.

[1]  Frederick J. Kolb.  Annotated glossary of essential terms , 1991 .

[2]  Miroslav Frljak,et al.  Localizing Facial Landmark Points with Pixel Intensity Comparisons Organized in Decision Trees , 2014 .

[3]  L. Akarun,et al.  3D Facial Landmarking under Expression, Pose, and Occlusion Variations , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[4]  Raimondo Schettini,et al.  3D face detection using curvature analysis , 2006, Pattern Recognit..

[5]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[6]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[7]  Jean-Luc Dugelay,et al.  An Efficient LBP-Based Descriptor for Facial Depth Images Applied to Gender Recognition Using RGB-D Face Data , 2012, ACCV Workshops.

[8]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

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

[10]  Feng Zhou,et al.  Exemplar-Based Graph Matching for Robust Facial Landmark Localization , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[12]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Christine Chin,et al.  Learning in Science: A Comparison of Deep and Surface Approaches. , 2000 .

[14]  David J. Kriegman,et al.  Localizing Parts of Faces Using a Consensus of Exemplars , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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