A strategy to abstract WCE video clips based on LDA

Wireless Capsule Endoscopy (WCE) is a novel technique that allows visualization of the whole gastrointestinal (GI) tract especially the small intestine in a comfortable, non-invasive and efficacious way. The main disadvantage of WCE is that physicians need to examine a video of over 55,000 frames which is a time-consuming and labor intensive task. To address the problem, a strategy of WCE video clip abstraction based on linear discriminant analysis (LDA) is proposed in this paper. We extract multiple features based on which the frame differences are measured. Then the video clips are segmented using a non-parametric key-point detection algorithm and finally the most representative frames (MRFs) are extracted based on LDA algorithm. Experimental results demonstrate the proposed strategy achieves promising performances.