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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2013 IEEE Conference on Computer Vision and Pattern Recognition s. 3025 - 3032
Hlavní autoři: Dong Chen, Xudong Cao, Fang Wen, Jian Sun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2013
Témata:
Accuracy
Face
Face Recognition
Feature extraction
High-dimensional LBP
Learning systems
Principal component analysis
Rotated Sparse Regression
Sparse matrices
Training
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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