No-reference stereoscopic image quality assessment

A full-reference stereoscopic image quality metric based on binocular energy and regression analysis

“…SSIMAvg [14], SSIMDdl [12], BEQM [5] and NoReferenceMetric [15] are used for above comparison. PCC indices of the proposed and state-of-the-art metrics are illustrated in Fig.…”

Objective No-reference Stereo Video Quality Assessment Research

“…In recent years Tianjin University, Ningbo University and other schools have puts forward some reference stereoscopic video evaluation methods. In [7] a three-dimensional objective evaluation model combined of human visual perception characteristics of visual sensitivity, sensitivity function and direction in the wavelet domain is proposed. The model respectively from the left and right viewpoint and the depth perception evaluation analysis, concluded that the overall image quality evaluation and the subjective sense of consistency, but respectively in the left and right viewpoint and depth perception evaluation model is not very good.…”

“…Although, the impact of coding distortions on the perceived stereoscopic image quality of an asymmetric image pair depends on the visual appearance of the artifact, where blockiness appears to be much more disturbing than other factors [12].That is to say, the extent of blockiness can be used as a main evaluation indicator of image distortion. In [7], firstly a differencing signal along each horizontal line is calculated. They estimate blockiness in spatial domain based on segmented local features.…”

Objective Image Quality Evaluation Model for JPEG2000 Coded Images Based on Edge Information Measures

“…In this work, a simple block-based segmentation algorithm which is proposed in [15] is used to classify the edge and non-edge areas of an image. At first, a simple pixel classification algorithm is employed to classify every pixel of the image into either edge or non-edge pixel is established.…”

“…For simplicity, only the luminance component is considered to make quality prediction of the color images, though this should not be considered generally true for color image quality assessment. In this model the original images are first segmented into edge and non-edge blocks using the block based segmentation algorithm [15]. For edge information measure, the zero crossing rate of edge and non-edge areas are calculated and then the histogram measure is evaluated both for horizontal and vertical direction.…”