University of Oulu

L. Liu, J. Chen, G. Zhao, P. Fieguth, X. Chen and M. Pietikäinen, "Texture Classification in Extreme Scale Variations Using GANet," in IEEE Transactions on Image Processing, vol. 28, no. 8, pp. 3910-3922, Aug. 2019. doi: 10.1109/TIP.2019.2903300

Texture classification in extreme scale variations using GANet

Saved in:
Author: Liu, Li1; Chen, Jie2; Zhao, Guoying2;
Organizations: 1College of System Engineering, National University of Defense Technology, Changsha, China
2Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
3Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada
4Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
5Peng Cheng Laboratory, Shenzhen, China
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2019
Publish Date: 2019-09-18


Research in texture recognition often concentrates on recognizing textures with intraclass variations, such as illumination, rotation, viewpoint, and small-scale changes. In contrast, in real-world applications, a change in scale can have a dramatic impact on texture appearance to the point of changing completely from one texture category to another. As a result, texture variations due to changes in scale are among the hardest to handle. In this paper, we conduct the first study of classifying textures with extreme variations in scale. To address this issue, we first propose and then reduce scale proposals on the basis of dominant texture patterns. Motivated by the challenges posed by this problem, we propose a new GANet network where we use a genetic algorithm to change the filters in the hidden layers during network training in order to promote the learning of more informative semantic texture patterns. Finally, we adopt a Fisher vector pooling of a convolutional neural network filter bank feature encoder for global texture representation. Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding, we are developing a new dataset, the extreme scale variation textures (ESVaT), to test the performance of our framework. It is demonstrated that the proposed framework significantly outperforms the gold-standard texture features by more than 10% on ESVaT. We also test the performance of our proposed approach on the KTHTIPS2b and OS datasets and a further dataset synthetically derived from Forrest, showing the superior performance compared with the state-of-the-art.

see all

Series: IEEE transactions on image processing
ISSN: 1057-7149
ISSN-E: 1941-0042
ISSN-L: 1057-7149
Volume: 28
Issue: 8
Pages: 3910 - 3922
DOI: 10.1109/TIP.2019.2903300
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Copyright information: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.