Computer vision systems become deployed in diverse real time systems hence robustness is a major area of concern. As a vast majority of the AI enabled systems are based on convolutional neural networks based models which use 3-channel RGB images as input. It has been shown that the performance of AI systems, such as those used in classification, is impacted by distortions in the images. To date most work has been carried out on distortions such as noise, blur, compression. However, color related changes to images could also impact the performance. Therefore, the goal of this paper is to study the robustness of these models under different hue shifts.
Translucency is an important appearance attribute. The caustic patterns that are cast by translucent objects onto another surface encapsulate information about subsurface light transport properties of a material. A previous study demonstrated that objects placed on a white surface are considered more translucent by human observers than identical objects placed on a black surface. The authors propose the lack of caustics as a potential explanation for these discrepancies -since a perfectly black surface, unlike its white counterpart, does not permit observation of the caustics. We hypothesize that caustics are salient image cues to perceived translucency, and they attract the visual attention of the human observers when assessing translucency of an object. To test this hypothesis, we replicated the experiment reported in the previous study, but in addition to collecting the observer responses, we also conducted eye tracking during the experiment. This study has revealed that although gaze fixation patterns differ between white and black floor images, the objects' body still attract most of the fixations, while caustics might be a cue of only secondary importance.
Image enhancement is important in different application areas such as medical imaging, computer graphics, and military applications. In this paper, we introduce a dataset with enhanced images. The images have been enhanced by five end users, and these have been evaluated by observers in an online image quality experiment. The enhancement steps by the end users and subjective results are analysed in detail. Furthermore, 38 image quality metrics have been evaluated on the introduced dataset to reveal their suitability to measure image enhancement. The results show that the image quality metrics have low to average performance on the new dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.