BROWSE

Related Researcher

Author's Photo

Choi, Jaesik
Statistical Artificial Intelligence Lab
Research Interests
  • Artificial intelligence, machine learning, deep learning, robotics, automatic statistician, semantic segmentation, fault detection

ITEM VIEW & DOWNLOAD

Semi-Local Structure Patterns for Robust Face Detection

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Semi-Local Structure Patterns for Robust Face Detection
Author
Choi, JaesikJang, Gil-JinJeong, Kyungjoong
Issue Date
2015-09
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation
IEEE SIGNAL PROCESSING LETTERS, v.22, no.9, pp.1400 - 1403
Abstract
In many image processing and computer vision problems, including face detection, local structure patterns such as local binary patterns (LBP) and modified census transform (MCT) have been adopted in widespread applications due to their robustness against illumination changes. However, being reliant on the local differences between neighboring pixels, they are inevitably sensitive to noise. To overcome the problem of noise-vulnerability of the conventional local structure patterns, we propose semi-local structure patterns (SLSP), a novel feature extraction method based on local region-based differences. The SLSP is robust to illumination variations, distortion, and sparse noise because it encodes the relative sizes of the central region with locally neighboring regions into a binary code. The principle of SLSP leads noise-robust expansions of LBP and MCT feature extraction frameworks. In a statistical analysis, we find that the proposed methods transform a substantial amount of random noise patterns in face images into more meaningful uniform patterns. The empirical results on the MIT+CMU dataset and FDDB (face detection dataset and benchmark) show that the proposed semi-local patterns applied to LBP and MCT feature extraction frameworks outperform the conventional LBP and MCT features in AdaBoost-based face detectors, with much higher detection rates.
URI
https://scholarworks.unist.ac.kr/handle/201301/9787
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6963353
DOI
10.1109/LSP.2014.2372762
ISSN
1070-9908
Appears in Collections:
EE_Journal Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU