Blind quality index for tone-mapped images based on luminance partition. (May 2019)

• Record Type: Journal Article
• Authors: Chen, Pengfei; Li, Leida; Zhang, Xinfeng; Wang, Shanshe; Tan, Allen
• Is Part Of: Pattern recognition. Volume 89(2019:May)
• Page Start: 108
• Page End: 118
• Publication Date: 2019-05
• Subjects: Tone-mapping operators -- Tone-mapped image -- Human visual system -- Luminance partition -- Multi-resolution representation -- Random forest regression; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.01.010
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: This paper proposes an improved luminance partition model to divide TMIs into areas with different brightness levels. The partition method is highly consistent with the characteristics of the HVS in luminance perception. This paper proposes to extract different quality-aware features from areas with different luminance levels. This paper takes advantage of combining the effects of salient local distortion and global quality degradation for feature extraction. Abstract: Tone-mapping operators (TMOs), which are designed to convert high dynamic range (HDR) images to standard low dynamic range (LDR) images for displaying on conventional devices, have gained extensive attention recently. The quality of tone-mapped images generated by different TMOs varies significantly, which depend upon the image contents and the parameter settings. A quality index that can accurately evaluate the performances of TMOs is thus highly needed. With this motivation, this paper presents a blind quality index based on luminance partition for tone-mapped images. It is based on the fact that the Human Visual System (HVS) has different sensitivities to image regions with different luminance levels. Specifically, two adaptive thresholds are first employed to segment an image into the dark, bright and normal areas. Then, we calculate the quality-aware features from different luminance areas: 1) local entropy feature is extracted from the dark and bright areas to measure the information loss due to the overexposure or underexposure during the tone mapping process; 2) local colorfulness feature is extracted from the normal area to evaluate the reproduction of colors. With the consideration that the perception of image quality depends on the combined effects of the salient local distortion and global quality degradation, the global contrast feature is also calculated and integrated for better evaluation performance. Moreover, to take advantage of the hierarchical characteristic of the HVS, all features are calculated under a multi-resolution framework. Eventually, the extracted features are mapped into an objective quality score based on the random forest regression. The proposed metric is shown to outperform those state-of-the-art metrics according to extensive experiments conducted on two publicly available databases.