Qing Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Qing Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Dagan Feng
Biomedical and Multimedia Information Technology Research Group, School of Computer Science, The University of Sydney, Sydney, NSW, Australia
1 shared publication - Ju Jia Zou
School of Engineering, Faculty of Engineering, Computing and Science, Western Sydney University, Penrith, Australia
1 shared publication - Weidong Cai
School of Computer Science, The University of Sydney
1 shared publication - Yang Song
University of New South Wales
1 shared publication
Latest Publications
- Open Access
- 15 November 2016
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 2 (4) , 367-377
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 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.
- 15 November 2016
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 2 (4) , 367-377
Open AccessTexture 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 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.