Bleeding detection in wireless capsule endoscopy based on color features from histogram probability
Authors:
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 08407789,p. 1-4
Abstract
This paper presents a novel technique for detecting bleeding regions in capsule endoscopy images. The proposed algorithm extracts color features from image-regions by calculating mean, standard deviation, skew and energy from the first order histogram of the RGB planes separately. Through the use of RGB color space, three times more number of features can be obtained than while using a grayscale image. Such color features have been used in content based retrieval system in pathology images. However, in spite of simplicity and ease of calculation, these features have not yet been studied in the classification of bleeding and non-bleeding regions in capsule endoscopic images. This paper studies the feasibility of using these features by assessing all possible feature subsets through the use of classification accuracy. The proposed algorithm could obtain classification accuracy up to 89%.Keywords
This publication has 7 references indexed in Scilit:
- Bleeding region detection in WCE images based on color features and neural network2011
- Bleeding Detection in Wireless Capsule Endoscopy Based on Probabilistic Neural NetworkJournal of Medical Systems, 2010
- Performance Characteristics of the Suspected Blood Indicator Feature in Capsule Endoscopy According to Indication for StudyClinical Gastroenterology and Hepatology, 2008
- Blood detection in wireless capsule endoscopy using expectation maximization clustering2006
- A Meta-Analysis of the Yield of Capsule Endoscopy Compared to Other Diagnostic Modalities in Patients with Obscure Gastrointestinal BleedingAmerican Journal of Gastroenterology, 2005
- Capsule endoscopy in the evaluation of patients with suspected small intestinal bleeding: Results of a pilot studyGastrointestinal Endoscopy, 2002
- An Algorithm for Fast Segmentation of Color Images1999