Image quality assessment databases
DIBR_Images Subjectives scores for DIBR algorithms using ACR-HR & Pair comparison
This database evaluate DIBR algorithmes to create synthetized view from real one. Seven DIBR algorithms processed three 1024x768 videos sequences to generate for each sequence, 4 new viewpoints. From these videos, 96 still images are extracted and rated by 43 observers with ACR-HR and Pair comparison methods. Read more.
Intentionally_Blurred_Background_Images Eye-tracking saliency maps and importance maps for blurred images
This image database contains 72 images. There are 6 versions of each content : the original and 5 power of blur. The database also contains eye-tracking data of 18 observers for these images. Read more.
IRCCyN_IVC_Toyama_LCD Subjective quality experiment on LCD still images from a database done on CRT
This database completes the MICT database with different protocol, different type of display device and different populations. The IRCCyN/IVC subjective scores on the Toyama database is composed to 14 original images and 182 distorted images in JPEG and JPEG2000 coding. ACR methodology is used with 27 observers. Read more.
JPEG_HDR_Images JPEG compression on HDR images
10 different still image contents were used. 7 JPEG compression are choosen with different bitrates optimized to used the full range of the quality scale. These 7 bitrates are used with the 2 versions of optimization (SSIM and MSE) to generate 14 different degradations. For each content, the reference and the degradations were subjectively evaluated with the ACR-HR method and 26 observers. Read more.
PairCompTMO Pair Comparison between TMO images
The database contains 100 images in FullHD (1920x1080 pixels) resolution. 10 High Dynamic Range (HDR) images were processed with 9 sets of parameter of Tone Mapper Operators to produce 90 LDR images. The HDR contents were displayed like a reference for the half of participants. 40 observers compare these images with the Pair Comparison method. Read more.
Subjective_Database Distorted Images and theirs subjective evaluations (DSIS)
10 original images were used. 235 distorted images were generated from 4 different processing: JPEG, JPEG2000, LAR coding, Blurring. Then, 15 observers use Double Stimulus Impairment Scale method to rate these images. Read more.