Contrast Weighted Perceptual Structural Similarity Index for Image Quality Assessment

Perceptual image quality assessment metric using mutual information of Gabor features

“…The larger value of CC as well as the smaller value of RMSE gives better performance of the IQA metrics. In order to further provide more extensive and convincing statistical quantitative comparisons, the proposed metric MIGF is compared with other state-of-art FR IQA approaches including PSNR, MSE, SSIM [8], PSSIM [11], IW-SSIM [12], MSVD [14], IFC [2] and VIF [15]. The performance comparison with the state-of-the-art methods in terms of CC and RMSE is shown in Table 1, in which the best results for each data set are highlighted with boldface.…”

“…And in recent years, to improve the performance of SSIM, some extensive methods were proposed [9,10]. Moreover, since images are naturally multi-scale in HVS, to evaluate the image quality at multiple resolutions cohering with human perception, weighted multi-scale methods were explored [11,12]. In essence, a common drawback of these indices is their high sensitivity to geometric and scale distortions [13].…”

Image Quality Assessment Based on Joint Quality-Aware Representation Construction in Multiple Domains

“…For example, the well-known method is visual information fidelity (VIF) [14] which incorporates the HVS model into information fidelity criterion (IFC) [15]. Since images are naturally multiscale in HVS perception, some weighted multiscale methods at multiple resolutions cohering with human perception are explored [16,17]. Furthermore, it has been found that Gabor filters have excellent properties and the shapes of Gabor wavelets are similar to the receptive fields of simple cells in the primary visual cortex.…”

Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification

“…Visual signal-to-noise ratio (VSNR) quantifies the visual fidelity based on near-threshold and supra-threshold properties of human vision [15]. Weighted multi-scale methods are explored to evaluate the image quality at multiple resolutions cohering with human perception [16], [17]. A four-stage perceptual approach is proposed in which visual features are extracted by 2-D Gabor filter and postprocessed by a divisive normalization transform to reflect the nonlinear mechanism of HVS [18].…”

“…State-of-the-art methods turn to the other direction that manages to capture the statistical properties (features) from an image and map them to the perceptual quality [3], [7], Copyright c 2017 The Institute of Electronics, Information and Communication Engineers [16], [17]. Such feature-based methods are inclined to effectively extract quality-aware features and have achieved notable success [4], [5], [13].…”