Learning perceptual texture similarity and relative attributes from computational features

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 non-linear 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.

[1]  Iasonas Kokkinos,et al.  Describing Textures in the Wild , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Jiehua Zhu,et al.  National Natural Science Foundation of China (NSFC) , 2013 .

[3]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

[5]  Wee Kheng Leow,et al.  PERCEPTUAL TEXTURE SPACE FOR CONTENT-BASED IMAGE RETRIEVAL , 2000 .

[6]  Xinghui Dong,et al.  Perceptual texture similarity estimation , 2014 .

[7]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Lei Wang,et al.  Learning Texture Similarity with Perceptual Pairwise Distance , 2005 .

[9]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[10]  Matti Pietikäinen,et al.  Outex - new framework for empirical evaluation of texture analysis algorithms , 2002, Object recognition supported by user interaction for service robots.

[11]  Mark S. Nixon,et al.  Enriching Texture Analysis with Semantic Data , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Mike J. Chantler,et al.  Perceptual Similarity: A Texture Challenge , 2011, BMVC.

[13]  Edward H. Adelson,et al.  Recognizing Materials Using Perceptually Inspired Features , 2013, International Journal of Computer Vision.

[14]  Kristen Grauman,et al.  Relative attributes , 2011, 2011 International Conference on Computer Vision.

[15]  C. Heaps,et al.  Similarity and Features of Natural Textures , 1999 .

[16]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[17]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[18]  HeikkilaMarko,et al.  A Texture-Based Method for Modeling the Background and Detecting Moving Objects , 2006 .

[19]  William H. Press,et al.  Numerical Recipes 3rd Edition: The Art of Scientific Computing , 2007 .

[20]  Fraser Halley,et al.  Perceptually relevant browsing environments for large texture databases , 2012 .

[21]  Junyu Dong,et al.  Visual Perception of Procedural Textures: Identifying Perceptual Dimensions and Predicting Generation Models , 2015, PloS one.

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Wee Kheng Leow,et al.  Perceptual Texture Space Improves Perceptual Consistency of Computational Features , 2001, IJCAI.

[26]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[27]  Marko Heikkilä,et al.  A texture-based method for modeling the background and detecting moving objects , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  R. Shepard.  The analysis of proximities: Multidimensional scaling with an unknown distance function. II , 1962 .

[29]  Wee Kheng Leow,et al.  A hybrid model for invariant and perceptual texture mapping , 2002, Object recognition supported by user interaction for service robots.

[30]  Mike J. Chantler,et al.  Does Free-sorting Provide a Good Estimate of Visual Similarity , 2012 .

[31]  Gerald L. Lohse,et al.  Towards a texture naming system: Identifying relevant dimensions of texture , 1993, Vision Research.

[32]  Subhransu Maji,et al.  Deep filter banks for texture recognition and segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).