Abstract
Using a sensor in variable lighting conditions, especially very low-light conditions, requires the application of image enhancement followed by denoising to retrieve correct information. The limits of such a process are explored in the present paper, with the objective of preserving the quality of enhanced images. The LIP (Logarithmic Image Processing) framework was initially created to process images acquired in transmission. The compatibility of this framework with the human visual system makes possible its application to images acquired in reflection. Previous works have established the ability of the LIP laws to perform a precise simulation of exposure time variation. Such a simulation permits the enhancement of low-light images, but a denoising step is required, realized by using a CNN (Convolutional Neural Network). A main contribution of the paper consists of using rigorous tools (metrics) to estimate the enhancement reliability in terms of noise reduction, visual image quality, and color preservation. Thanks to these tools, it has been established that the standard exposure time can be significantly reduced, which considerably enlarges the use of a given sensor. Moreover, the contribution of the LIP enhancement and denoising step are evaluated separately.
Highlights
Our main goal is to study the case of extremely low-light images acquired with a very short exposure time, up to fifty times smaller than a standard one
We already knew that the Logarithmic Image Processing (LIP) tools permit precisely simulating a target exposure time, performing an accurate brightness correction of low-light images
PSNR, SSIM, and Delta E values according to images exposures and processing step
Summary
Our main goal is to study the case of extremely low-light images acquired with a very short exposure time, up to fifty times smaller than a standard one. Many other enhancement solutions are proposed in the literature, and most of them take into account a specific knowledge of the studied domain, for example, kind of noise, sought information, etc. Some recent papers propose general solutions, most of the time based on Neural Networks [4,5]. This amount of papers is due to the various domains concerned, night photography, night vision, astronomy, and the reduction of X-rays doses in medical imaging, among others
Sign-in/Register to view highlights & summary 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.
