CYCLOP: A stereo color image quality assessment metric

Abstract

Abstract-In this work, a reduced reference (RR) perceptual quality metric for color stereoscopic images is presented. Given a reference stereo pair of images and their "distorted" version, we first compute the disparity map of both the reference and the distorted stereoscopic images. To this end, we define a method for color image disparity estimation based on the structure tensors properties and eigenvalues/eigenvectors analysis. Then, we compute the cyclopean images of both the reference and the distorted pairs. Thereafter, we apply a multispectral wavelet decomposition to the two cyclopean color images in order to describe the different channels in the human visual system (HVS). Then, contrast sensitivity function (CSF) filtering is performed to obtain the same visual sensitivity information within the original and the distorted cyclopean images. Thereafter, based on the properties of the human visual system (HVS), rational sensitivity thresholding is performed to obtain the sensitivity coefficients of the cyclopean images. Finally, RR stereo color image quality assessment (SCIQA) is performed by comparing the sensitivity coefficients of the cyclopean images and studying the coherence between the disparity maps of the reference and the distorted pairs. Experiments performed on color stereoscopic images indicate that the objective scores obtained by the proposed metric agree well with the subjective assessment scores.Keywords-Stereo quality assessment, cyclopean image, 2D multi-valued wavelet, disparity field.

Oriented Correlation Models of Distorted Natural Images With Application to Natural Stereopair Quality Evaluation

“…Towards this end, several recent researchers have attempted to evaluate perceptual quality by synthesizing an intermediate image that more-or-less agrees with cyclopean perception. Maalouf et al [55] proposed a reduced-reference quality metric that compares the sensitivity coefficients [56] extracted from the two cyclopean images synthesized from the reference and distorted stereopairs. Chen et al [57] proposed a full-reference S3D IQA algorithm exploiting a perceptually synthesized cyclopean image to account for binocular rivalry.…”

“…Assuming the disparity map is computed using the left image as reference to match the right image, the synthesized cyclopean image may be generated as [55], [57], [58]:…”

Visual Quality Assessment of Stereoscopic Image and Video: Challenges, Advances, and Future Trends

“…Maalouf et al [59] proposed a reduced-reference quality metric by comparing the sensitivity coefficients [24] extracted from the two cyclopean images formed by the reference and distorted stereopairs. The cyclopean image is computed using Eq.…”

Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment

“…For 3D RR IQA metrics, image features including the distortion driven features such as binary edge mask [49,50], and HVS features such as contrast sensitivity index [51], are extracted and compared for quality analysis, which correlate with HVS perception and image statistical properties. The marginal distributions of disparity [52] subband coefficients can be well fitted by the GGD model, which is similar to the luminance images.…”