Image quality enhancement in wireless capsule endoscopy with adaptive fraction gamma transformation and unsharp masking filter

TL;DR

This paper introduces a novel image enhancement technique for wireless capsule endoscopy images that improves brightness, contrast, and color preservation while maintaining low computational complexity, validated by objective metrics.

Contribution

The paper proposes a new method combining adaptive fraction gamma transformation and unsharp masking to enhance WCE images with improved quality and efficiency.

Findings

PSNR and SSIM confirm near-ground error rates.

IRMLE improved by 22%.

CEF increased by 10%.

Abstract

Wireless Capsule Endoscopy (WCE) presented in 2001 as one of the key approaches to observe the entire gastrointestinal (GI) tract, generally the small bowels. It has been used to detect diseases in the gastrointestinal tract. Endoscopic image analysis is still a required field with many open problems. The quality of many images it produced is rather unacceptable due to the nature of this imaging system, which causes some issues to prognosticate by physicians and computer-aided diagnosis. In this paper, a novel technique is proposed to improve the quality of images captured by the WCE. More specifically, it enhanced the brightness, contrast, and preserve the color information while reducing its computational complexity. Furthermore, the experimental results of PSNR and SSIM confirm that the error rate in this method is near to the ground and negligible. Moreover, the proposed method improves intensity restricted average local entropy (IRMLE) by 22%, color enhancement factor (CEF) by 10%, and can keep the lightness of image effectively. The performances of our method have better visual quality and objective assessments in compare to the state-of-art methods.