Localization of Just Noticeable Difference for Image Compression
This work addresses the need for large-scale subjective data to improve image compression algorithms for consumers, but it is incremental as it builds on existing JND concepts with a new data collection method.
The paper tackles the problem of identifying just noticeable difference (JND)-critical regions in images for compression by proposing a crowdsourcing framework to collect subjective assessments, resulting in a novel dataset (KonJND++) with 300 source images and an average of 43 PJND ratings and 129 region locations per image.
The just noticeable difference (JND) is the minimal difference between stimuli that can be detected by a person. The picture-wise just noticeable difference (PJND) for a given reference image and a compression algorithm represents the minimal level of compression that causes noticeable differences in the reconstruction. These differences can only be observed in some specific regions within the image, dubbed as JND-critical regions. Identifying these regions can improve the development of image compression algorithms. Due to the fact that visual perception varies among individuals, determining the PJND values and JND-critical regions for a target population of consumers requires subjective assessment experiments involving a sufficiently large number of observers. In this paper, we propose a novel framework for conducting such experiments using crowdsourcing. By applying this framework, we created a novel PJND dataset, KonJND++, consisting of 300 source images, compressed versions thereof under JPEG or BPG compression, and an average of 43 ratings of PJND and 129 self-reported locations of JND-critical regions for each source image. Our experiments demonstrate the effectiveness and reliability of our proposed framework, which is easy to be adapted for collecting a large-scale dataset. The source code and dataset are available at https://github.com/angchen-dev/LocJND.