Extreme learning machine with multi-scale local receptive fields for texture classification

Texture classification is a challenging task due to the wide range of natural texture types and large intra-class variations in texture images, such as different rotations, scales, positions and lighting conditions. Many existing methods for extracting texture features are designed carefully by user...

Full description

Saved in:
Bibliographic Details
Published inMultidimensional systems and signal processing Vol. 28; no. 3; pp. 995 - 1011
Main Authors Huang, Jinghong, Yu, Zhu Liang, Cai, Zhaoquan, Gu, Zhenghui, Cai, Zhiyin, Gao, Wei, Yu, Shengfeng, Du, Qianyun
Format Journal Article
LanguageEnglish
Published New York Springer US 01.07.2017
Springer Nature B.V
Subjects
Algorithms
Artificial Intelligence
Circuits and Systems
Classification
Design engineering
Electrical Engineering
Engineering
Feature extraction
Illumination
Learning
Lighting
Methods
Multiscale analysis
Neural networks
Signal,Image and Speech Processing
State of the art
Support vector machines
Surface layers
Texture
Extreme learning machine
Multi-scale local receptive fields
Texture classification
Online AccessGet full text

Cover

More Information
Summary:Texture classification is a challenging task due to the wide range of natural texture types and large intra-class variations in texture images, such as different rotations, scales, positions and lighting conditions. Many existing methods for extracting texture features are designed carefully by user for specific applications. The extracted texture features are then used as input to various classification methods, such as support vector machines, to classify the textures. The system performance greatly depends on the feature extractor. Unfortunately, there is no systematic approach for feature extractor design. In this paper, we propose a method called extreme learning machine with multi-scale local receptive fields (ELM-MSLRF) to achieve feature learning and classification simultaneously for texture classification. In contrast to traditional methods, the proposed method learns the features by the network itself and can be applied to more general applications. Additionally, it is fast and requires few computations. Experiments on the ALOT texture dataset demonstrate the attractive performance of ELM-MSLRF even compared with the state-of-the-art algorithms. Moreover, the proposed ELM-MSLRF achieves the best performance on the NORB dataset.
ISSN:0923-6082
1573-0824
DOI:10.1007/s11045-016-0414-3