Content-Based Image Retrieval: A Comprehensive User Interactive Simulation Tool for Endoscopic Image Databases

Abstract

Until few years ago, radiological methods were widely used for the examination and investigation of the digestive tract. Today, wireless capsule endoscopy represents an innovative, noninvasive, effective solution that does not imply a risk of irradiation. Due to the impressive number of images captured on the entire “trip” covered by the video capsule, diagnostic accuracy is greatly improved, also allowing the visualization of certain areas of the digestive tract that were previously inaccessible. Captured images can be analyzed by a specialist who can identify lesions or possible active bleeding within the digestive tract. This paper presents the implementation of a recovery system for endoscopic images based on Content-Based Image Retrieval (CBIR) technique.

Keywords

• Wireless capsule endoscopy
• Content-Based Image Retrieval (CBIR) system
• Local Binary Pattern
• Intensity histogram
• Color Coherence Vector