Texture image classification with discriminative neural networks

Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks (CNN) have emerged as the state-of-the-art: CNN-based features provid...

Full description

Saved in:
Bibliographic Details
Published inComputational visual media (Beijing) Vol. 2; no. 4; pp. 367 - 377
Main Authors Song, Yang, Li, Qing, Feng, Dagan, Zou, Ju Jia, Cai, Weidong
Format Journal Article
LanguageEnglish
Published Beijing Tsinghua University Press 01.12.2016
Springer Nature B.V
Subjects
Artificial Intelligence
Artificial neural networks
Classification
Computer Graphics
Computer Science
Computer vision
Image classification
Image enhancement
Image Processing and Computer Vision
Machine learning
Neural networks
Research Article
Texture
User Interfaces and Human Computer Interaction
feature learning
feature transformation
texture classification
neural networks
Online AccessGet full text

Cover

More Information
Summary:Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks (CNN) have emerged as the state-of-the-art: CNN-based features provide a significant performance improvement over previous handcrafted features. In this study, we demonstrate that we can further improve the discriminative power of CNN-based features and achieve more accurate classification of texture images. In particular, we have designed a discriminative neural network-based feature transformation (NFT) method, with which the CNN-based features are transformed to lower dimensionality descriptors based on an ensemble of neural networks optimized for the classification objective. For evaluation, we used three standard benchmark datasets (KTH-TIPS2, FMD, and DTD) for texture image classification. Our experimental results show enhanced classification performance over the state-of-the-art.
ISSN:2096-0433
2096-0662
DOI:10.1007/s41095-016-0060-6