No-reference stereoscopic image quality assessment based on saliency-guided binocular feature consolidation

作者：Xu, Xiaogang; Zhao, Yang; Ding, Yong^*

来源：Electronics Letters, 2017, 53(22): 1468-1469.

DOI：10.1049/el.2017.2501

• visual perception
• stereo image processing
• feature extraction
• image representation
• entropy
• learning (artificial intelligence)
• support vector machines
• regression analysis
• no-reference stereoscopic image quality assessment
• saliency-guided binocular feature consolidation
• intermediate cyclopean view construction
• saliency-guided multiscale feature consolidation
• quality representation
• global natural statistics feature
• local spatial entropy feature
• spectral entropy feature
• kurtosis

Different from traditional methods depending on the procedure of intermediate cyclopean' view construction, a novel framework based on saliency-guided multi-scale feature consolidation for stereoscopic image quality assessment is proposed. For quality representation, the underlying features are extracted from three aspects: (i) global natural statistics features, (ii) local spatial and spectral entropy features and (iii) the kurtosis and skew of disparity distribution. Then the binocular features are consolidated by a saliency-guided weighted process. Finally, a machine learning technique of support vector regression is used for objective quality mapping. Experimental results demonstrate the promising performance of the proposed method.

• 出版日期2017-10-26
• 单位浙江大学