No-Reference Quality Assessment of Night-Time Images Via the Analysis of Local and Global Features

Abstract

This paper focuses on the quality assessment of the nighttime images, which is technically vulnerable to diverse and sophisticated visual distortions, and proposes an effective noreference image quality assessment method through comprehensive analysis of local and global image attributes. Several quality-aware features are extracted through the study of image brightness, contrast, structure and color. Specifically, the features related to brightness and contrast are extracted through the analysis of local information, while the others are extracted through the analysis of global information. The quality assessment model for night-time images is built by mapping the selected features into subjective ratings via the support vector regression. Extensive experiments conducted on public night-time image database demonstrates the superiority of the proposed method.

Study of Subjective and Objective Quality Assessment of Night-Time Videos

“…Song et al extracted several quality-aware features through the study of image brightness, contrast, structure and color. Specifically, the features related to brightness and contrast are extracted through the analysis of local information, while the others are extracted through the analysis of global information [43]. He et al measured the night-time image quality by investigating the fundamental image properties, such as the brightness, saturation, sharpness, noisiness, contrast and the semantics.…”

“…Xiang et al conducted a large-scale natural nighttime image database (NNID) [25]. Based on the work, several night-time image quality assessment (IQA) methods have been proposed by analyzing the characteristic of weak luminance information [42][43][44][45][46][47]. Da et al built a real-world night-time video quality assessment database (NVQA), and proposed a blind night-time video quality assessment model based on feature fusion [48].…”