Adaptive specular reflection detection and inpainting in colonoscopy video frames

TL;DR

This paper introduces a two-phase method for detecting and removing specular reflections in colonoscopy videos, improving image quality for better diagnosis.

Contribution

It presents a novel adaptive detection and inpainting approach combining color space analysis and a two-step inpainting process.

Findings

Achieved 99.68% detection accuracy.

Attained 71.79% Dice score in reflection segmentation.

Enhanced colonoscopy image quality for diagnostic purposes.

Abstract

Colonoscopy video frames might be contaminated by bright spots with unsaturated values known as specular reflection. Detection and removal of such reflections could enhance the quality of colonoscopy images and facilitate diagnosis procedure. In this paper we propose a novel two-phase method for this purpose, consisting of detection and removal phases. In the detection phase, we employ both HSV and RGB color space information for segmentation of specular reflections. We first train a non-linear SVM for selecting a color space based on image statistical features extracted from each channel of the color spaces. Then, a cost function for detection of specular reflections is introduced. In the removal phase, we propose a two-step inpainting method which consists of appropriate replacement patch selection and removal of the blockiness effects. The proposed method is evaluated by testing on an available colonoscopy image database where accuracy and Dice score of 99.68% and 71.79% are achieved respectively.