Force work induced metric for face verification

Authors:
Jianjun Qian;Jian Yang;Zhangjing Yang;Weilan Wang
Affiliations:
School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Computer Science, Nanjing University of Science and Technology, Nanjing, China;School of Mathematics and Computer Science, Northwest University for Nationalities, Lanzhou, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 7
Cited 0

Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Description with Local Binary Patterns: Application to Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Enhanced local texture feature sets for face recognition under difficult lighting conditions

IEEE Transactions on Image Processing
Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

IEEE Transactions on Pattern Analysis and Machine Intelligence
Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition by Exploring Information Jointly in Space, Scale and Orientation

IEEE Transactions on Image Processing
Face Verification Using the LARK Representation

IEEE Transactions on Information Forensics and Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a robust and simple metric approach named Force Work Induced Metric (FWIM) according to a Physical model. A novel image local descriptor based on FWIM (FWIM-LD) is then introduced for face verification. FWIM-LD captures the local structure information between central pixel and its neighbors effectively. PCA thus is used to obtain the low-dimensional and significant features. Subsequently, we employ the binary-like face representation method to further improve the face verification rate. Experimental results on the challenging benchmark "Labeled Faces in the Wild" (LFW) dataset demonstrate that the proposed method achieves better performance than the state-of-the-art algorithms.