Abstract
A desirable photographic reproduction method should have the ability to compress high-dynamic-range images to low-dynamic-range displays that faithfully preserve all visual information. However, during the compression process, most reproduction methods face challenges in striking a balance between maintaining global contrast and retaining majority of local details in a real-world scene. To address this problem, this study proposes a new photographic reproduction method that can smoothly take global and local features into account. First, a highlight/shadow region detection scheme is used to obtain prior information to generate a weight map. Second, a mutually hybrid histogram analysis is performed to extract global/local features in parallel. Third, we propose a feature fusion scheme to construct the virtual combined histogram, which is achieved by adaptively fusing global/local features through the use of Gaussian mixtures according to the weight map. Finally, the virtual combined histogram is used to formulate the pixel-wise mapping function. As both global and local features are simultaneously considered, the output image has a natural and visually pleasing appearance. The experimental results demonstrated the effectiveness of the proposed method and the superiority over other seven state-of-the-art methods.
Highlights
In the real world, the luminance intensity of environmental scenes has a very wide range
We propose using a hybrid histogram analysis scheme to extract mutually compatible global/local features in parallel, and a feature fusion scheme to construct the virtual combined histogram, which allows us to inherit the superiority of the global-based methods smoothly
Owning to the difference the dark/bright regions and normal-luminanc regions,using we propose using the to weight map tomodify adaptively modify locally the weights regions, we propose the weight map adaptively the weights in locally in the feature fusion
Summary
The luminance intensity of environmental scenes has a very wide range. From glimmer starlight to blazing sunlight, the luminance variation could span over ten orders of magnitude. The human visual system (HVS) has an outstanding ability to adapt and perceive about 5~6 orders of magnitude. Most consumer cameras can only capture nearly 2~3 orders of luminance variation. With advancements in optical sensing, high dynamic range (HDR) sensors that can capture the entire luminance range of a real-world scene have been developed [2]. Some latest high-end digital single-lens reflex cameras, or some devised sensors including multiple sensor elements with different exposure levels, are able to capture entire details of both dark and bright parts of the scene simultaneously.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
