Salient object detection using octonion with Bayesian inference

A novel computational model for detecting salient regions in color images is proposed, based on a two-stage coarse-to-fine framework. Firstly, different early visual feature maps - including the edge intensity; the black-white, red-green, and blue-yellow color opponents; and the Gabor features with...

Full description

Saved in:
Bibliographic Details
Published inProceedings - International Conference on Image Processing pp. 3292 - 3296
Main Authors Hong-Yun Gao, Kin-Man Lam
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Analytical models
Bayes methods
Bayesian inference
Fourier transforms
Image color analysis
Image segmentation
mean-shift segmentation
octonion image
Quaternions
Salient object detection
spectral normalization
Visualization
Online AccessGet full text

Cover

More Information
Summary:A novel computational model for detecting salient regions in color images is proposed, based on a two-stage coarse-to-fine framework. Firstly, different early visual feature maps - including the edge intensity; the black-white, red-green, and blue-yellow color opponents; and the Gabor features with four directions - are incorporated into the eight channels of an octonion image. Spectral normalization is achieved with the octonion Fourier transform by preserving the phase information of the octonion image. Then, with mean-shift segmentation, the saliency values in each segment are averaged to form a coarse saliency map. Finally, the coarse saliency map is subject to Bayesian inference to further refine the salient regions. The integration of frequency normalization, spatial segmentation and Bayesian inference exploits the benefits from both the spectral domain and the spatial domain. Experimental results show the superiority of the proposed method compared to several existing methods.
ISSN:1522-4880
DOI:10.1109/ICIP.2014.7025666