Image Enhancement Method Based on Adaptive Fraction Gamma Transformation and Color Restoration for Wireless Capsule Endoscopy

Abstract

Wireless capsule endoscopy (WCE) plays an important role in gastrointestinal (GI) tract observation and disease diagnosis. However, due to the limited illumination and complex environment in GI tract, endoscopic images are usually not clear enough to be interpreted by doctors or used for further processing. Although many algorithms have been proposed to improve image quality from different aspects, the balance of algorithm complexity and image quality is still a challenge worth exploring. In this paper, we propose a novel function named adaptive fraction gamma transformation (AFGT) to enhance the quality of images captured by the WCE. Characteristics of AFGT are adaptive to different luminance in an image and self-tunable to the statistical characteristics of different images. Besides, HSI color space is adopted for color restoration, namely, the saturation component is linearly scaled according to the enhanced intensity component. Experimental results show that performances of the proposed method in both visual quality and objective assessments are better than that of the state-of-art methods.