A Novel Fusion Method for Low Brightness Enhancement Derivatives
- PDF / 2,604,178 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 79 Downloads / 171 Views
A Novel Fusion Method for Low Brightness Enhancement Derivatives Chao Wei1,2 · Hongxin Lin1 · Lijuan Tang1,2 · Weiping Liu1,2 · Mengzhen Jiang1,2 · Junfeng Wang1,2 · Guannan Chen1,2 Received: 13 May 2019 / Revised: 28 May 2020 / Accepted: 29 May 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, a straightforward and effective fusion method is designed for low brightness enhancement derivatives, which are generated through using brightness enhancement technique for a single low-brightness image. First, illumination estimation techniques and the principle of retinal imaging and cerebral cortex adjustment are combined to acquire the exposure ratio map. Then, a novel Chi-squared conversion function model and an accurate exposure ratio map are employed to obtain two derivatives with different characteristics: one is natural but not very detailed; the other is excessively bright but with prominent details. Finally, the improved weight matrix design and a novel derivatives fusion method are utilized to fuse the improved features of the derivatives. Experiments on a diverse set of images demonstrate that the proposed algorithm can not only reveal the efficiency of the brightness and detail enhancement, but also can show its superiority over several state-of-theart processes in terms of overall visual information enhancement. Keywords Brightness enhancement · Illumination estimation techniques · Chisquared conversion · Derivatives fusion
1 Introduction In underlit environments, images and videos captured by visual imaging devices are often low light and offer little in the way of crisp detail. This low-brightness imaging environment is also very influential in life applications, such as traffic night surveillance systems and mobile phone night shooting. For example, in a low-bright night traffic road setting, surveillance cameras cannot clearly obtain license plate numbers of vehicles or facial information of pedestrians. Since the exposure level of mobile phones is limited, in some shooting situations, the appearance of the backlight is also * Guannan Chen [email protected] Extended author information available on the last page of the article Vol.:(0123456789)
Circuits, Systems, and Signal Processing
accompanied by low-brightness vision. For the image that has bright background regions and dark foreground regions, it is difficult to acquire both object and other details simultaneously. In retinex relevant theory [17, 18, 38], the image can be considered as the composition of two parts: reflectance and illumination. Early experiments were based on retinex theory, such as single-scale retinex (SSR) [3] and multiscale retinex (MSR) [15], which incorporates reflectance in the enhanced result. In recent developments, multiscale retinex with color restoration (MSRCR) [2] has been shown to effectively reduce excessive brightness enhancement and restore color fidelity. Dong et al. [6] proposed a fast-efficient algorithm to dehaze and enhance inverted low-light images. The
Data Loading...
