JP2K

AcronymDefinition
JP2KJpeg 2000
References in periodicals archive ?
It is the same with JP2K and GB, where they cause low frequency component increase and edge being unclear.
SSIM SURF GLD-SR CLR BIFS LCSIM JPEG 0.9614 0.9760 0.9827 0.9784 0.9810 0.9818 JP2K 0.9764 0.9560 0.9730 0.9768 0.9840 0.9721 WN 0.9694 0.9800 0.9861 0.9777 0.9910 0.9873 GB 0.9517 0.9510 0.9499 0.9737 0.9550 0.9589 FF 0.9556 0.9510 0.9541 0.9662 0.9320 0.9694 w.a.
Compared to other no-reference image quality assessment methods, our method has the best performance on the three distortion types, JP2K, WN, and FF.
SROCC JP2K JPEG WN BLUR ff ALL PSNR 0.870 0.885 0.942 0.763 0.874 0.866 SSIM 0.939 0.946 0.964 0.907 0.941 0.913 fsim 0.970 0.981 0.967 0.972 0.949 0.964 DIIVINE 0.913 0.910 0.984 0.921 0.863 0.916 BLIINDS-II 0.929 0.942 0.969 0.923 0.889 0.931 BRISQUE 0.914 0.965 0.979 0.951 0.877 0.940 CORAIN 0.943 0.955 0.976 0.969 0.906 0.942 CNN 0.952 0.977 0.978 0.962 0.908 0.956 Proposed 0.967 0.968 0.986 0.962 0.931 0.962 Table 3: Median LCC across 100 train-test iterations on the LIVE database.
The LIVE database contains 29 reference images and 779 distorted images with five kinds of distortions: JPEG compression, JPEG2000 compression (JP2K), additive Gaussian white noise (WN), Gaussian blur (GB) and Fast Fading Rayleigh (FF).
Metric JP2K JPEG WN GB BIQI [17] 0.9270 0.9631 0.9928 0.9613 DIIVINE [18] 0.9267 0.8041 0.9913 0.9600 BLIINDS-II [19] 0.9352 0.9471 0.9654 0.9175 BRISQUE [20] 0.9553 0.9866 0.9926 0.9720 NIQE [21] 0.9261 0.9514 0.9763 0.9433 SSEQ [22] 0.9222 0.9460 0.9812 0.9376 CORNIA [23] 0.9684 0.9750 0.9823 0.9856 QAC [36] 0.8648 0.9435 0.9180 0.9105 GRID 0.9736 0.9834 0.9933 0.9771 Metric FF All BIQI [17] 0.8197 0.9219 DIIVINE [18] 0.8741 0.8443 BLIINDS-II [19] 0.8453 0.9144 BRISQUE [20] 0.9352 0.9670 NIQE [21] 0.8792 0.9020 SSEQ [22] 0.8704 0.8925 CORNIA [23] 0.9545 0.9691 QAC [36] 0.8248 0.8625 GRID 0.9455 0.9735 Table 7.
Five types of distortions, JPEG, JP2K, Gblur, WN, and H.264, are symmetrically applied to the left and right reference stereoscopic images at various levels.
Resultados de validacion del esquema propuesto Metodo Clasico Distorsion e [d.sub.1] m s m s Fast Fading 0.07 0.01 4.40 2.31 Ruido blanco 0.08 0.00 0.90 1.19 JPEG 0.07 0.01 1.10 1.85 JP2K 0.08 0.01 3.70 3.30 Blurring 0.08 0.00 1.00 2.00 Distorsion [d.sub.2] m s Fast Fading 18.20 1.39 Ruido blanco 21.90 1.96 JPEG 21.50 2.41 JP2K 19.90 3.10 Blurring 22.20 2.57 Metodo Propuesto Distorsion e [d.sub.1] m s m s Fast Fading 0.08 0.00 0.50 1.08 Ruido blanco 0.08 0.01 1.70 1.70 JPEG 0.08 0.01 2.30 2.00 JP2K 0.08 0.02 3.00 4.50 Blurring 0.07 0.00 0.20 0.42 Distorsion [d.sub.2] m s Fast Fading 22.20 2.04 Ruido blanco 21.20 2.34 JPEG 21.00 3.52 JP2K 21.30 2.62 Blurring 20.50 2.46
Figure 3 shows the effect of saliency-assisted enhancement, (a) is the reference image "bikes," (b) is its distortion version contaminated by JPEG 2000 compression (JP2K), both taken from the LIVE database [18], (c) is the saliency map computed based on the intensity of the reference image (a), and (d) and (e) are the enhanced reference and distorted images.