MIQM: A novel Multi-view Images Quality Measure

Although several subjective and objective quality assessment methods have been proposed in the literature for images and videos from single cameras, no comparable effort has been devoted to the quality assessment for multi-camera images. With the increasing popularity of multi-view applications, quality assessment for multi-camera images and videos is becoming fundamental to the development of these applications. The quality of images, which are captured by a multi-view system, are affected by multiple factors such as camera configuration, number of cameras, and the calibration process. In the process of developing an objective metric specifically designed for multi-camera systems, we identified two types of visual distortions in multi-view images: photometric distortions and geometric distortions. In this paper, we show that in the presence of well defined reference these distortions can be translated into luminance, contrast, spatial motion and edge-based structure components. Then, we propose different index values that can quantify these components. We provide several examples to demonstrate the correlation between each of these components and the corresponding index metric. Then, we combine these indexes into one multi-view image quality measure (MIQM). The results and examples show that not only MIQM can capture the perceptual quality of multi-view images it also outperforms the structural similarity (SSIM) measure for single-view images quality assessment.