Weighted Feature Correlation and Fusion Saliency

In this paper, we propose a novel feature correlation and fusion approach for multiple visual focuses content associational problem. Integrating various visual attention models to extract the visual focus of the image in the visual database, a weighted fusion of visual focuses will be obtained in good accuracy and the corresponding visual focus set will also be built subsequently. Then, the correlation matrix based on normalized mutual information and structural similarity index measurement will be computed within visual focus set. Through scanning correlation matrix in turn, the corresponding focus fusion process will be carried on and we use the weighted saliency model to compute visual focus of fusion focus. Compared with the state-of-the-art methods such as Itti, IS, GBVS, IF, NCS, MS and ISRW, higher robustness and accuracy rate are the main outstanding advantages of the presented approach. Experimental results on high noise interference confirm the validity of our approach.

[1]  Xuelong Li,et al.  Visual saliency detection using information divergence , 2013, Pattern Recognit..

[2]  Guangming Shi,et al.  Nonlocal center-surround reconstruction-based bottom-up saliency estimation , 2015, Pattern Recognit..

[3]  Hyun Seung Yang,et al.  Non-uniform image compression using a biologically motivated selective attention model , 2005, Neurocomputing.

[4]  Gangyi Jiang,et al.  A depth perception and visual comfort guided computational model for stereoscopic 3D visual saliency , 2015, Signal Process. Image Commun..

[5]  Zhe-Ming Lu,et al.  Video abstraction based on the visual attention model and online clustering , 2013, Signal Process. Image Commun..

[6]  Xudong Jiang,et al.  Learning LBP structure by maximizing the conditional mutual information , 2015, Pattern Recognit..

[7]  Radek Ptak,et al.  The role of visual saliency for the allocation of attention: Evidence from spatial neglect and hemianopia , 2015, Neuropsychologia.

[8]  Sinan Kalkan,et al.  An iterative adaptive multi-modal stereo-vision method using mutual information , 2015, J. Vis. Commun. Image Represent..

[9]  Ju Liu,et al.  Image Adaptation and Dynamic Browsing Based on Two-Layer Saliency Combination , 2013, IEEE Transactions on Broadcasting.

[10]  Santanu Chaudhury,et al.  Visual saliency guided video compression algorithm , 2013, Signal Process. Image Commun..

[11]  Xiangyang Wang,et al.  An effective image retrieval scheme using color, texture and shape features , 2011, Comput. Stand. Interfaces.

[12]  Nikos Paragios,et al.  DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting , 2009, IPMI.

[13]  Xin He,et al.  Saliency detection based on integrated features , 2014, Neurocomputing.

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Ali Borji,et al.  State-of-the-Art in Visual Attention Modeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Christof Koch,et al.  Image Signature: Highlighting Sparse Salient Regions , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[18]  Shu Fang,et al.  Image saliency estimation via random walk guided by informativeness and latent signal correlations , 2015, Signal Process. Image Commun..