Image Enhancement Using Weighted Bi-Histogram Equalization

Abstract

Image enhancement is one of using in various digital signal processing areas. Advances in microcontrollers, microcomputers and computers have developed traditional algorithms in order to improve the quality of the resulting image and have implied many avenues to the design of new innovations using various techniques. This paper proposes contrast enhancement using weighted bi-histogram equalization based on distributed area ratio. Moreover, this technique must use a weighted factor which is calculated by the ratio of the histogram distribution. Likewise, an original image will be equalized by the modification of the probability density function of the gray levels. As result of the experiment, the contrast of resulting image is improved for implement and human perception – as well as also reduces the absolute mean brightness error (AMBE) than the traditional technique of image enhancement.

Local Contrast-Based Pixel Ordering for Exact Histogram Specification

“…Recently, Pallavi et al [17] reviewed state-of-the-art techniques for image enhancement, in which the techniques of histogram equalization are also included such as contrast limited adaptive histogram equalization (CLAHE) [18] and brightness preserving bi-histogram equalization (BBHE) [19]. Trongtirakul and Agaian [20] proposed a weighted histogram equalization using entropy of probability density function, which outperformed related methods including a low-rank regularized retinex model (LR3M) [21]. More recently, Zhang et al [22] proposed an unsupervised low-light image enhancement method via a histogram equalization prior (HEP) based on the observation that the feature maps of histogram equalization enhanced image and the ground truth are similar.…”

Adaptive logarithmic retinex enhancement for iceberg detection in visible imagery

“…This review is primarily aimed at empirically contrasting Retinex-based methodologies with alternative non-Retinex-based approaches. [8], including local histogram equalization [9], and dynamic histogram equalization [10], [11]. However, these methods require significant computational resources, and their effectiveness relies on meticulous parameter calibration.…”