Contrast enhancement in endoscopic images using fusion exposure histogram equalization

Citation

Sim, Kok Swee and Lim, Choon Chen and Tan, Sin Ching (2020) Contrast enhancement in endoscopic images using fusion exposure histogram equalization. Engineering Letters, 28 (3). pp. 73-81. ISSN 2193-567X

[img] Text
101.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

Single illumination source of endoscopy screening can cause recorded images to have low contrast and imbalanced brightness. Low quality of endoscopic images will have difficulties in analyzing endoscopy images. Among contrast enhancement techniques, histogram equalization technique is the most popular image processing technique in improving the contrast of endoscopic images. However, conventional histogram equalization techniques may cause some regions to be over enhanced and some information to be lost due to dominating gray levels. Some existing modified histogram equalization have solved the contrast problem of image but the performance of information preserved still has room for improvement. Therefore, fusion exposure histogram equalization technique (FEHE) is developed to overcome the drawbacks of histogram equalization techniques. There are two stages in FEHE which are low light enhancement technique and the exposure-based histogram equalization with adaptive sigmoid function. In low light enhancement technique, image is converted to principal component analysis and converted into luminance and chrominance component. Each component is enhanced by tone mapping function, adaptive filter and histogram modification respectively. Exposure histogram equalization technique with sigmoid function divides histogram into two sub histograms based on average exposure level. The cumulative distribution function of each sub histogram is manipulated to become two smooth sigmoid functions and equalized the image by referring to the modified cumulative distribution function. The method (FEHE) is tested on endoscopic images. Experimental results have shown that the performance of FEHE is satisfactory in terms of enhancement level and information preserving level.

Item Type: Article
Uncontrolled Keywords: Image Processing
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 23 Dec 2020 12:07
Last Modified: 23 Dec 2020 12:07
URII: http://shdl.mmu.edu.my/id/eprint/7924

Downloads

Downloads per month over past year

View ItemEdit (login required)