Skip to main content

Table 1 Summary of point and mask-based RR perceptual quality assessment metrics values with respect to the distortion types (i.e., JPEG, JPEG2000)

From: Reduced reference image and video quality assessments: review of methods

Domain Multimedia Resolution Distortion type Quality parameter Parameter value
Point Image 512 × 512 JPEG, PSNR [50] 0.918,
512 × 512 JPEG2000 PSNR [50] 0.924
512 × 512 JPEG, PSNR [54] 0.532
512 × 512 JPEG2000 PSNR [54] 0.553
512 × 512 JPEG PSNR [55] 0.732
482 × 512 JPEG2000 PSNR [57] 0.872
512 × 512 JPG PSNR [61] 0.902
512 × 512 JPEG, SSIM [62] 0.773
512 × 512 JPEG2000 SSIM [62] 0.791
Video 360 × 288 MS-MPEG-4 Blockiness [21] 0.748
Mask Image 768 × 512 JPEG2000 EHD [64] 0.792
512 × 512 JPEG MS-SSIM [64] 0.952
512 × 512 JPEG2000 MSE [53] 0.913
512 × 512 White noise PSNR [53] 0.892
480 × 720 JPEG, W-SCM [53] 0.714
512 × 512 JPEG, PSNR [66] 0.688
512 × 512 JPEG2000 PSNR [66] 0.724
512 × 512 JPEG SSIM [67] 0.731
372 × 512 JPEG, PSNR [69] 0.795
372 × 512 JPEG2000 PSNR [69] 0.716
Video 32 × 32(FFT) VQEG MSE [70] 0.821
768 × 512 H.263 SSIM [73] 0.737
768 × 512 H.264/AVC EPSNR [21] 0.858
486 × 720 MPEG-2 VQM [50] 0.923
486 × 720 MPEG-2 PSNR Winkler Metric [73] 0.779
32 × 32(FFT) MPEG-2 Winkler Metric [71] 0.784
32 × 32(FFT) MPEG-2 Winkler Metric [74] 0.713
  1. Resolution represents the image/video resolution. Distortion type represents their method used on different distortion types with respect to quality estimations. Quality parameter represents the evaluation parameters used by authors in their work.
  2. Note: Parameter value represents performance values of the RR technique applying on particular distortion type. These values measure the amount of distorted introduced in the multimedia content. For example, if the distortion is due to the JPEG compression and someone want to measures the value by using PSNR with respect to a particular RR-based method. We convert and scale the parameter values in range from 0-1 used by authors in their RR-based method. If the parameter value is high, we can argue that the multimedia quality is less (i.e., highly degraded) and better will be the RR-based technique. The authors used these distortions types for RR technique to measure the metrics values (i.e., PSNR, SSIM)