Ying Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ying Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dengsheng Zhang
Institute of Innovation, Science and Sustainability, Federation University
1 shared publication - Guojun Lu
School of Science Engineering and Information Technology Federation University Gippsland Campus 3842 Churchill VIC Australia
1 shared publication Kengpang Lim
Xi’an University of Posts and Telecommunications
1 shared publicationNam Ling
Santa Clara University
1 shared publication- Priyabrata Karmakar
School of Information Technology, Deakin University, Australia
1 shared publication - Shyh Wei Teng
Federation University Australia
1 shared publication
Latest Publications
- 24 May 2018
- Published by Springer Nature in World Wide Web
- Vol. 22 (3) , 1313-1324
A novel image retrieval algorithm based on transfer learning and fusion features
- 24 May 2018
- Published by Springer Nature in World Wide Web
- Vol. 22 (3) , 1313-1324
A novel image retrieval algorithm based on transfer learning and fusion features
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Improved Tamura Features for Image Classification Using Kernel Based Descriptors
Tamura features are based on human visual perception and have huge potential in image representation. Conventional Tamura features only work on homogeneous texture images and perform poor on generic images. Therefore, many researchers attempt to improve Tamura features and most of the improvements are based on histogram based representation. Kernel descriptors have been shown to outperform existing histogram based local features as such descriptors do not require coarse quantization of pixel attributes. Instead, in kernel descriptor framework, each pixel equally participates in matching between two image patches. In this paper, we propose a set of kernel descriptors that are based on Tamura features. Additionally, the proposed descriptors are invariant to local rotations. Experimental results show that our proposed approach outperforms the conventional Tamura features significantly.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Improved Tamura Features for Image Classification Using Kernel Based Descriptors
Tamura features are based on human visual perception and have huge potential in image representation. Conventional Tamura features only work on homogeneous texture images and perform poor on generic images. Therefore, many researchers attempt to improve Tamura features and most of the improvements are based on histogram based representation. Kernel descriptors have been shown to outperform existing histogram based local features as such descriptors do not require coarse quantization of pixel attributes. Instead, in kernel descriptor framework, each pixel equally participates in matching between two image patches. In this paper, we propose a set of kernel descriptors that are based on Tamura features. Additionally, the proposed descriptors are invariant to local rotations. Experimental results show that our proposed approach outperforms the conventional Tamura features significantly.