Learning perceptual texture similarity and relative attributes from computational features

Jianwen Lou, Lin Qi, Junyu Dong, Hui Yu, Guoqiang Zhong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

232 Downloads (Pure)

Abstract

Previous work has shown that perceptual texture similarity and relative attributes cannot be well described by computational features. In this paper, we propose to predict human’s visual perception of texture images by learning a nonlinear
mapping from computational feature space to perceptual space. Hand-crafted features and deep features, which were successfully applied in texture classification tasks, were extracted and used to train Random Forest and rankSVM models against perceptual data from psychophysical experiments. Three texture datasets were used to test our proposed method and the experiments show that the predictions of such learnt models are in high correlation with human’s results.
Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks (IJCNN)
PublisherIEEE
Pages2540-2546
Number of pages7
ISBN (Electronic)978-1-5090-0620-5
ISBN (Print)978-1-5090-0621-2
DOIs
Publication statusPublished - 3 Nov 2016
Event2016 IEEE World Congress on Computational Intelligence - Vancouver, Canada
Duration: 25 Jul 201629 Jul 2016

Publication series

Name
ISSN (Electronic)2161-4407

Conference

Conference2016 IEEE World Congress on Computational Intelligence
Abbreviated titleIEEE WCCI
Country/TerritoryCanada
CityVancouver
Period25/07/1629/07/16

Keywords

  • feature extraction
  • correlation
  • semantics
  • somputational modeling
  • neural networks
  • manifolds
  • symmetric matrices

Fingerprint

Dive into the research topics of 'Learning perceptual texture similarity and relative attributes from computational features'. Together they form a unique fingerprint.

Cite this