Two low illuminance image enhancement algorithms based on grey level mapping
- PDF / 6,430,139 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 64 Downloads / 138 Views
Two low illuminance image enhancement algorithms based on grey level mapping Hong Cheng 1
1
1
& Wei Long & Yanyan Li & Huaguo Liu
1
Received: 18 February 2020 / Revised: 15 August 2020 / Accepted: 16 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Two image enhancement contrast methods are proposed in this paper for low-intensity images. The first method (LEAM) is a new greyscale mapping function, and it can be significantly enhanced in the low grey range and compressed slowly in the high grey range, which is beneficial for retaining more image details; the second method (LEAAM) is based on the data characteristics of a histogram combined with the first mapping function, which adaptively sets the gamma value to correct the image. The experimental results show that compared with a traditional mapping function, LEAM is more effective at enriching image details and enhancing visual effects, and LEAAM, compared with a recent low-illumination image enhancement algorithm, achieves good performance for average gradient, information entropy and contrast index; additionally, the overall visual effect is the best compared with other methods. Keywords Contrast-enhanced . Dark image . Gamma correction . Mapping function . Selfadaption
1 Introduction Car cameras, surveillance cameras and other devices equipped with cameras all seek to achieve good image quality. However, ideal images cannot be obtained on all occasions. The external causes of low-quality images include low-quality sensors, insufficient exposure, insufficient light and bad weather, while the internal causes include image compression and hidden data image recovery [20, 21]. Therefore, it is particularly important to improve image contrast. Image contrast enhancement is widely used in computer vision [16], pattern recognition, the classification and detection of agricultural products [17, 30, 42], medical images [22, 23, 27, 29, 43] and remote sensing images. Image contrast enhancement in a low-illumination
* Hong Cheng [email protected]
1
College of Mechanical Engineering, Sichuan University, Chengdu, China
Multimedia Tools and Applications
environment has always been a research topic of interest. Histogram equalization (HE) is a simple and effective image contrast enhancement technique. HE can enhance the global contrast of an input image by remapping the original grey level. However, this method ignores the local features, resulting in artefacts or excessive enhancement in some images. To overcome the above shortcomings, brightness-preserving bi-histogram equalization (BBHE,1997) [37] decomposes the original image into two sub-images based on the average histogram and then performs histogram equalization. Dualistic sub-image histogram equalization (DSIHE,1999) [41] decomposes the original image into two sub-images based on the median of the histogram and then performs histogram equalization. To compensate for the deficiency of BBHE and DSIHE in some cases, a novel extension of BBHE—minimum mean bright
Data Loading...
