IEICE TRANSACTIONS on Information
RBM-LBP: Joint Distribution of Multiple Local Binary Patterns for Texture Classification
Summary :
In this letter, we propose a novel framework to estimate the joint distribution of multiple Local Binary Patterns (LBPs). Multiple LBPs extracted from the same central pixel are first encoded using handcrafted encoding schemes to achieve rotation invariance, and the outputs are further encoded through a pre-trained Restricted Boltzmann Machine (RBM) to reduce the dimension of features. RBM has been successfully used as binary feature detectors and the binary-valued units of RBM seamlessly adapt to LBP. The proposed feature is called RBM-LBP. Experiments on the CUReT and Outex databases show that RBM-LBP is superior to conventional handcrafted encodings and more powerful in estimating the joint distribution of multiple LBPs.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.11 pp.2828-2831
- Publication Date
- 2016/11/01
- Publicized
- 2016/08/19
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2016EDL8072
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Chao LIANG
Tsinghua University,Shenzhen Key Laboratory of Information Science and Technology,Visual Information Processing Lab, Tsinghua-PolyU Biometrics Joint Lab
Wenming YANG
Tsinghua University,Shenzhen Key Laboratory of Information Science and Technology,Visual Information Processing Lab, Tsinghua-PolyU Biometrics Joint Lab
Fei ZHOU
Tsinghua University,Shenzhen Key Laboratory of Information Science and Technology,Visual Information Processing Lab, Tsinghua-PolyU Biometrics Joint Lab
Qingmin LIAO
Tsinghua University,Shenzhen Key Laboratory of Information Science and Technology,Visual Information Processing Lab, Tsinghua-PolyU Biometrics Joint Lab
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chao LIANG, Wenming YANG, Fei ZHOU, Qingmin LIAO, "RBM-LBP: Joint Distribution of Multiple Local Binary Patterns for Texture Classification" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 11, pp. 2828-2831, November 2016, doi: 10.1587/transinf.2016EDL8072.
Abstract: In this letter, we propose a novel framework to estimate the joint distribution of multiple Local Binary Patterns (LBPs). Multiple LBPs extracted from the same central pixel are first encoded using handcrafted encoding schemes to achieve rotation invariance, and the outputs are further encoded through a pre-trained Restricted Boltzmann Machine (RBM) to reduce the dimension of features. RBM has been successfully used as binary feature detectors and the binary-valued units of RBM seamlessly adapt to LBP. The proposed feature is called RBM-LBP. Experiments on the CUReT and Outex databases show that RBM-LBP is superior to conventional handcrafted encodings and more powerful in estimating the joint distribution of multiple LBPs.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8072/_p
Copy
@ARTICLE{e99-d_11_2828,
author={Chao LIANG, Wenming YANG, Fei ZHOU, Qingmin LIAO, },
journal={IEICE TRANSACTIONS on Information},
title={RBM-LBP: Joint Distribution of Multiple Local Binary Patterns for Texture Classification},
year={2016},
volume={E99-D},
number={11},
pages={2828-2831},
abstract={In this letter, we propose a novel framework to estimate the joint distribution of multiple Local Binary Patterns (LBPs). Multiple LBPs extracted from the same central pixel are first encoded using handcrafted encoding schemes to achieve rotation invariance, and the outputs are further encoded through a pre-trained Restricted Boltzmann Machine (RBM) to reduce the dimension of features. RBM has been successfully used as binary feature detectors and the binary-valued units of RBM seamlessly adapt to LBP. The proposed feature is called RBM-LBP. Experiments on the CUReT and Outex databases show that RBM-LBP is superior to conventional handcrafted encodings and more powerful in estimating the joint distribution of multiple LBPs.},
keywords={},
doi={10.1587/transinf.2016EDL8072},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - RBM-LBP: Joint Distribution of Multiple Local Binary Patterns for Texture Classification
T2 - IEICE TRANSACTIONS on Information
SP - 2828
EP - 2831
AU - Chao LIANG
AU - Wenming YANG
AU - Fei ZHOU
AU - Qingmin LIAO
PY - 2016
DO - 10.1587/transinf.2016EDL8072
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2016
AB - In this letter, we propose a novel framework to estimate the joint distribution of multiple Local Binary Patterns (LBPs). Multiple LBPs extracted from the same central pixel are first encoded using handcrafted encoding schemes to achieve rotation invariance, and the outputs are further encoded through a pre-trained Restricted Boltzmann Machine (RBM) to reduce the dimension of features. RBM has been successfully used as binary feature detectors and the binary-valued units of RBM seamlessly adapt to LBP. The proposed feature is called RBM-LBP. Experiments on the CUReT and Outex databases show that RBM-LBP is superior to conventional handcrafted encodings and more powerful in estimating the joint distribution of multiple LBPs.
ER -
English
