Integrating Visual Saliency Information into Objective Quality Assessment of Tone-Mapped Images

Abstract

Abstract. Tone-mapped images are the low dynamic range (LDR) images converted from high dynamic range (HDR) images. Recently, the objective quality assessment of tone-mapped images is becoming a challenging problem. However, there is no mature algorithm to deal with this issue until the tone-mapped image quality index (TMQI) was proposed recently, which is tone-mapped image quality index (TMQI). Unfortunately, the pooling method of the structural fidelity map in TMQI is the simple "mean", which makes the result unsatisfying. On the other hand, recent studies have found that different locations of an image may have different contributions to the quality perception of the human visual system. The significance of a local image region can be well characterized by a visual saliency (VS) model. Inspired by this insight, in this paper, we propose a VS-based pooling strategy for the objective quality assessment of tone-mapped images. The experimental results clearly demonstrate the efficacy of our proposed method.Keywords: Tone-mapped images, high dynamic range images, objective quality assessment, visual saliency. IntroductionRecently, researchers have shown a growing interest in high dynamic range (HDR) images. Compared to the low dynamic range (LDR) images, the range of intensity levels of HDR images is largely wider, thus enjoying advantages. Specifically, the range of intensity level of HDR images could be on the order of 10000 to 1, which allows for accurate representations of luminance variations in real scenes, ranging from direct sunlight to faint starlight [1], while the LDR images only have 256 intensity levels. However, General displays are designed for displaying LDR images, so we must use tone-mapping operators (TMOs) to create the corresponding LDR images for the visualization of HDR images. As the reduction in dynamic range, the LDR images converted from HDR images cannot preserve all the information. With an increasing number of TMOs being developed, a question appears, that is which TMO has a better performance? This question drives us to develop an index to compare them, and then utilize the index for optimizing parameters in TMOs.

Image Quality Assessment of Tone Mapped Images

“…We compare the performance of the proposed method, Yeganeh and Wang's objective evaluation methods [18], [19], and Liu et al's method [25]. Cadik et al's subjective evaluation data [5], in which 11 observers evaluated three HDR scenes with 14 tone mapping algorithms, is used to verify the performance of the proposed method.…”

“…Fig. 7 shows performance comparison of four quality measures in terms of the SRCC and KRCC: Q, overall quality in [18], [19], and the best performance result Q V in [25] with Zhang et al's visual saliency method [34]. The overall quality of Yeganeh and Wang's methods additionally evaluate global brightness and contrast of a tone mapped image and Figure 6.…”

“…Table 2. Comparison of the performance of structural fidelity in terms of the rank order correlation coefficient SRCC KRCC Proposed structural fidelity 0.8969 0.8143 Structural fidelity [18] 0.7934 0.6044 Overall quality in [18] 0.8759 0.7808 Overall quality in [19] 0.8197 0.7179 Overall quality in [25] 0.8144 0.6484 Table 3 shows computation times of Yeganeh and Wang's method, Liu et al's method, and the proposed method with 600×450 image. The computation time is measured by the average of five runs with 14 tone mapped images on a 2.67GHz CPU, 4GB RAM desktop.…”

“…Also, they measured naturallooking quality of tone mapped images as global contrast and brightness with their own naturalness model. Visual attention models have been widely used in image and video quality assessment to reduce the complexity of scene analysis and to correlate with the HVS [20]- [25]. Visual attention measures local stimuli of images and computes guide perceptual difference between the reference and tone mapped images using perceptual image structure information [20].…”

“…Thus, objective quality measurement over the entire image can give wrong estimation results. Liu et al studied extension of SSIM of tone mapped images [19] using several visual saliency methods [25], which shows the effectiveness of visual attention in image quality methods. The proposed method integrates visual attention method to increase awareness of the HVS to image quality assessment of tone mapped image.…”