Saliency structure stereoscopic image quality assessment method

Abstract Stereoscopic image quality assessment (SIQA) plays a crucial role in the development of 3D imaging system. In this paper, an objective SIQA model named saliency structure stereoscopic image quality assessment method (3SIQA) is built, based on the fact that human is selectively sensitive to various structure. Structural similarity image index (SSIM) is generally used to calculate the structure similarity between the reference image and the distorted image, and the selective sensitivity of human vision system is described on two aspects: saliency and texture. The former aspect performs through giving different weights to the image pixel value and its saliency map, and the latter one is represented by dividing SSIM map into three parts (edge, smooth and texture zone) and summing these parts with different weights. Moreover, the experimental results demonstrate its promise.

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

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

[3]  Mei Yu,et al.  Stereoscopic image quality assessment model with three-component weighted structure similarity , 2010, 2010 International Conference on Audio, Language and Image Processing.

[4]  Paul S. Fisher,et al.  Image quality measures and their performance , 1995, IEEE Trans. Commun..

[5]  Liang-Tien Chia,et al.  Adaptive local context suppression of multiple cues for salient visual attention detection , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[6]  Gustavo de Veciana,et al.  An information fidelity criterion for image quality assessment using natural scene statistics , 2005, IEEE Transactions on Image Processing.

[7]  Touradj Ebrahimi,et al.  Impact of Acquisition Distortion on the Quality of Stereoscopic Images , 2010 .

[8]  Fred Stentiford.  Attention-based image similarity measure with application to content-based information retrieval , 2003, IS&T/SPIE Electronic Imaging.

[9]  Pin Xu,et al.  Objective Quality Assessment of Noised Stereoscopic Images , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.

[10]  M. von Grunau,et al.  Visual selection: facilitation due to stimulus saliency , 1996, Proceedings II Workshop on Cybernetic Vision.

[11]  Chaofeng Li,et al.  Three-component weighted structural similarity index , 2009, Electronic Imaging.

[12]  R. Parasuraman.  The attentive brain , 1998 .

[13]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[14]  Zheru Chi,et al.  Image coding quality assessment using fuzzy integrals with a three-component image model , 2004, IEEE Transactions on Fuzzy Systems.

[15]  Alan C. Bovik,et al.  Image information and visual quality , 2006, IEEE Trans. Image Process..

[16]  David Zhang,et al.  FSIM: A Feature Similarity Index for Image Quality Assessment , 2011, IEEE Transactions on Image Processing.

[17]  Wilson S. Geisler,et al.  Image quality assessment based on a degradation model , 2000, IEEE Trans. Image Process..

[18]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Marta Mrak,et al.  Reliability of Objective Picture Quality Measures , 2004 .

[20]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[21]  Sheila S. Hemami,et al.  VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images , 2007, IEEE Transactions on Image Processing.