Authors: Lei Tian Chunxiao Fan Yue Ming
Publish Date: 2016/07/12
Volume: 76, Issue: 11, Pages: 13271-13299
Abstract
Local feature descriptor has been widely used in computer vision field due to their excellent discriminative power and strong robustness However the forms of such local descriptors are predefined in the handcrafted way which requires strong domain knowledge to design them In this paper we propose a simple and efficient Spherical Hashing based Binary Codes SHBC feature learning method to learn a discriminative and robust binary face descriptor in the datadriven way Firstly we extract patchwise pixel difference vectors PDVs by computing the difference between center patch and its neighboring patches Then inspired by the fact that hypersphere provide much stronger power in defining a tighter closed region in the original data space than hyperplane we learn a hyperspherebased hashing function to map these PDVs into lowdimensional binary codes by an efficient iterative optimization process which achieves both balanced bits partitioning of data points and independence between hashing functions In order to better capture the semantic information of the dataset our SHBC also can be used with supervised data embedding method such as Canonical Correlation Analysis CCA namely SupervisedSHBC SSHBC Lastly we cluster and pool these learned binary codes into a histogrambased feature that describes the cooccurrence of binary codes And we consider the histogrambased feature as our final feature representation for each face image We investigate the performance of our SHBC and SSHBC on FERET CASPEALR1 LFW and PaSC databases Extensive experimental results demonstrate that our SHBC descriptor outperforms other stateoftheart face descriptorsThe work presented in this paper was supported by the National Natural Science Foundation of China Grants No NSFC61402046 NSFC61170176 Fund for Beijing University of Posts and Telecommunications No2013XZ10 2013XD04 Fund for the Doctoral Program of Higher Education of China Grants No20120005110002
Keywords: