A new image centrality descriptor for wrinkle frame detection in WCE videos

Small bowel motility dysfunctions are a widespread functional disorder characterized by abdominal pain and altered bowel habits in the absence of specific and unique organic pathology. Current methods of diagnosis are complex and can only be conducted at some highly specialized referral centers. Wireless Video Capsule Endoscopy (WCE) could be an interesting diagnostic alternative that presents excellent clinical advantages, since it is non-invasive and can be conducted by non specialists. The purpose of this work is to present a new method for the detection of wrinkle frames in WCE, a critical characteristic to detect one of the main motility events: contractions. The method goes beyond the use of one of the classical image feature, the Histogram of Oriented Gradients (HoG), and proposes the use of a mid-level image descriptor, centrality. In the case of wrinkle detection in WCE, this descriptor is computed by applying a graph-based centrality measure on histograms of oriented structure tensor image descriptors. We show how to apply this image descriptor to the detection of contractions in WCE videos and that it outperforms previous methods.