A brightness-preserving two-dimensional histogram equalization method based on two-level segmentation
- PDF / 2,340,623 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 156 Views
A brightness-preserving two-dimensional histogram equalization method based on two-level segmentation Qingjie Cao 1,2 & Zaifeng Shi 1,3
1
1
& Rong Wang & Pumeng Wang & Suying Yao
1
Received: 28 August 2019 / Revised: 15 June 2020 / Accepted: 24 June 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Histogram equalization (HE) is a classical enhancement method for image processing. However, conventional HE techniques have poor performance in terms of preserving the brightness and natural appearance of images, meaning they typically fail to produce satisfactory results. A novel two-dimensional HE method with two-level segmentation for refining image brightness is proposed in this paper. Additionally, a modified twodimensional histogram is generated to determine the locations of main segmentation points based on neighborhood matrices. The weights of the absolute brightness differences between low and high local contrast regions in this two-dimensional histogram are adjustable. After separating images into two main areas based on main segmentation points, multiple sub-segmentation points are selected based on a novel criterion derived from the maximum value distribution of the double histograms. Experimental results for various test images demonstrate that the proposed method achieves excellent performance in terms of brightness preservation and image contrast enhancement. Keywords Image enhancement . Two-dimensional histogram . Histogram equalization . Brightness-preserving . Two-level segmentation
* Zaifeng Shi [email protected] Qingjie Cao [email protected] Rong Wang [email protected] Pumeng Wang [email protected] Suying Yao [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Introduction Enhancing image contrast using histogram equalization (HE) is a fundamental technique in computer vision. Methods based on HE have been widely used in consumer electronics, image enhancement, and medical image processing [10, 25, 21]. A transformation function called the cumulative distribution function (CDF) is used to enhance images by stretching their gray density distributions [11]. However, conventional HE methods typically fail to achieve satisfactory results based on various inherent problems, such as brightness drift and overenhancement effects [6]. To overcome these issues, many researchers have attempted to improve HE and have achieved some promising results. Sub-HE methods focus on improving image brightness drift in HE. These methods divide an original histogram into several parts and then perform HE on each part separately. The brightness-maintenance bi-HE (BBHE) method generates sub-images according to average values of image brightness and performs independent equalization [15]. To some extent, BBHE preserves the average brightness of images. Similar to BBHE, dualistic sub-image HE (DSIHE) [29] uses a CDF value of 0.5 or area attributes to bisect histograms, and then equalizes sub-histograms i
Data Loading...
