HMM-Based Framework to Measure the Visual Fidelity of Tone Mapping Operators

Abstract

Recent advancements in the image capturing techniques and post processing software generate High Dynamic Range (HDR) images. Such images retain maximum information of the scene by capturing more realistic visual contents, which are often missed in traditional image capturing techniques. In this regard, tone mapping operators (TMOs) play a significant role in displaying HDR image contents on a traditional Low Dynamic Range (LDR) display. These operators tend to introduce artifacts in the original HDR image to change its brightness and contrast in such a way that it can destroy the important textures and information of the image. The assessment of these TMOs is a challenging topic to select best the best technique considering different perceptual and quality dimensions. In this paper, we propose to compare TMOs through their impact on visual behavior in comparison with HDR condition. This study is the first of its kind to utilize hidden markov model (HMM) as a similarity measure to evaluate perceived quality of TMO. The findings suggest that the proposed HMM-based method which emphasizes on temporal information produce better evaluation metric than the traditional approaches which are based only on visual spatial information.

A review on high dynamic range (HDR) image quality assessment

“…In the study of Ellahi et al (2020), the hidden Markov model (HMM) as a test of similarity to assess TMO perceived quality is proposed. The findings suggest that the proposed HMM-based method that emphasizes temporal information yields better evaluation metrics than traditional approaches based solely on visual-spatial information.…”

A machine-learning framework to predict TMO preference based on image and visual attention features

“…1) Visual attention similarity: As it has been shown that TMOs can impact both visual saliency and visual behavior in images, different similarity metrics based either on the comparison of saliency maps [14], either on the comparison of scanpaths in two tone-mapped images [15] are used.…”

“…This metric is based on a HMM-based framework to measure the similarity of visual behavior between two conditions of experiment [15]. This method uses a HMM to model the sequence of eye movements of one observer [20], [21].…”

“…Secondly our paper investigates the interest of VA features for the prediction of the preference label. The influence of TMO on visual behavior has already been studied showing specific effects on visual saliency [14] and scanpath [15]. The use of VA for improving quality assessment is not new but it is mainly based on the weight of the visible distortion from saliency information [16], [17].…”

Evaluation of the Bubble view Metaphor for the Crowdsourcing Study of Visual Attention Deployment in Tone-Mapped Images

“…Tone mapping consists in the compression of the dynamic range of an image to match the characteristics of the displays, preserving the aesthetic visual quality of the represented scene and the artistic intention. Previous works based on ET experiments showed that tone mapping operators can significantly impact the fixation behavior highlighting the strong effect on contrast in VA [12]. For these reasons, tone mapping is a good representative use case of QoE applications.…”