Texture Classification in Extreme Scale Variations Using GANet

Li Liu*, Jie Chen, Guoying Zhao, Paul Fieguth, Xilin Chen, Matti Pietikainen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

26 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number8663448
Pages (from-to)3910-3922
Number of pages13
JournalIEEE Transactions on Image Processing
Volume28
Issue number8
DOIs
Publication statusPublished - Aug 2019
Externally publishedYes

Keywords

  • feature extraction
  • local binary pattern (LBP)
  • rotation invariance
  • texture analysis
  • Texture descriptors

Fingerprint

Dive into the research topics of 'Texture Classification in Extreme Scale Variations Using GANet'. Together they form a unique fingerprint.

Cite this