Statistical Textural Distinctiveness for Salient Region Detection in Natural Images

Christian Scharfenberger, Alexander Wong, Khalil Fergani, John S. Zelek, David A. Clausi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 979-986

Abstract


A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is proposed. Rotational-invariant neighborhood-based textural representations are extracted and used to learn a set of representative texture atoms for defining a sparse texture model for the image. Based on the learnt sparse texture model, a weighted graphical model is constructed to characterize the statistical textural distinctiveness between all representative texture atom pairs. Finally, the saliency of each pixel in the image is computed based on the probability of occurrence of the representative texture atoms, their respective statistical textural distinctiveness based on the constructed graphical model, and general visual attentive constraints. Experimental results using a public natural image dataset and a variety of performance evaluation metrics show that the proposed approach provides interesting and promising results when compared to existing saliency detection methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Scharfenberger_2013_CVPR,
author = {Scharfenberger, Christian and Wong, Alexander and Fergani, Khalil and Zelek, John S. and Clausi, David A.},
title = {Statistical Textural Distinctiveness for Salient Region Detection in Natural Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}