|
SIAT
Picture-level Just Noticeable Difference-based Asymmetric Stereoscopic Image Database
Chunling Fan, Yun Zhang, Raouf Hamzaoui, and Qingshan Jiang
Introduction We develop a Picture-level Just Noticeable Difference (PJND) based Symmetric Stereoscopic image datasets named SIAT-JASI, which includes ten source images, respectively. Each source image was compressed with JPEG2000 and H.265 intra coding, separately. A total of 50 subjects participated in the experiment. Each source image was tested by 35-36 subjects. The Picture-level JND (PJND) including PJNDPRI and PJNDDRI are provided. PJNDPRI reveals the minimum distortion against a pristine image. PJNDDRI reveals the minimum distortion against a distorted image.
Keywords: Picture-level Just Noticeable Distortion (PJND), Stereoscopic
image, Image quality assessment, Subjective quality assessment. |
|
Publications |
|
1. Chunling Fan, Yun Zhang, Raouf Hamzaoui, and Qingshan Jiang, Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images, in: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019. |
|
|
|
Fig.1. Ten Stereoscopic Images used in SIAT-JASI database. |
|
Ten stereoscopic images, as shown in Fig. 1, are used in our experiment. There are seven semantic categories: people, building, plant, fruit, volleyball, computer, and basketball. Five images (People, Treebranches, Flower, Pavilion, and Building) are outdoor and the other five (Basketball, NewsReport, Computer, Volleyball, and Fruit Store) are indoor. |
|
The input stereoscopic image pairs were encoded with H.265 intra coding and JPEG2000, separately. HM-16.7-00 and FFMpeg-n3.2.8 for standard H.265 were adopted to encode each view of the stereoscopic images in intra-frame mode separately. FFMpeg-n3.2.8 was used to encode/decode between BMP and YUV. HM-16.7-00 was used to encode YUV into bit stream. The QPs were varied from 1 to 51 for both the left and right views. For JPEG2000 compression, we used MATLAB code “imwrite (image, imageName, ‘CompressionRatio’, CR)”, and CR ranges from 1 to 300. |
|
The experiment is conducted in two parts. There were a total of 50 non-expert subjects participated in the experiment and each test stereoscopic image was evaluated by 35 subjects. The quality scores assigned by each subject should be normalized per person before computing PJND. All subjects taking part in the experiment are graduate students. Every subject had been told the procedure of the test and had watched a training sequence before starting the experiment. |
|
SIAT-JASI Database Downloads |
|
|
