Information Theory Based WCE Video Summarization

Wireless Capsule Endoscopy (WCE) is a technical break-through that allows to produce a video of the entire intestine without surgery. It is reported that a medical clinician spends one or two hours to assess a WCE video. It is hence useful to help the physician to do analysis diagnosis using computerized methods. In this paper an algorithmic information-theroretic method is presented for the automatic summarization of meaningful changes in video sequences extracted from WCE videos. To segment a WCE video into anatomic parts (esophagus, stomach, small intestine, colon) we use a textons-based method. The local textons histogram sequence is used for image representation and the Normalized Compression Distance (NCD) measure is used to compute the similarity between images.