Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification

Making a high-dimensional (e.g., 100K-dim) feature for face recognition seems not a good idea because it will bring difficulties on consequent training, computation, and storage. This prevents further exploration of the use of a high dimensional feature. In this paper, we study the performance of a...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3025 - 3032
Main Authors Dong Chen, Xudong Cao, Fang Wen, Jian Sun
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Accuracy
Face
Face Recognition
Feature extraction
High-dimensional LBP
Learning systems
Principal component analysis
Rotated Sparse Regression
Sparse matrices
Training
Online AccessGet full text

Cover

More Information
Summary:Making a high-dimensional (e.g., 100K-dim) feature for face recognition seems not a good idea because it will bring difficulties on consequent training, computation, and storage. This prevents further exploration of the use of a high dimensional feature. In this paper, we study the performance of a high dimensional feature. We first empirically show that high dimensionality is critical to high performance. A 100K-dim feature, based on a single-type Local Binary Pattern (LBP) descriptor, can achieve significant improvements over both its low-dimensional version and the state-of-the-art. We also make the high-dimensional feature practical. With our proposed sparse projection method, named rotated sparse regression, both computation and model storage can be reduced by over 100 times without sacrificing accuracy quality.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.389