A video-frame based registration using segmentation and graph connectivity for Wireless Capsule Endoscopy

Gastroenterologists using Wireless Capsule Endoscopy (WCE) extract valuable information regarding the health condition of the intestine. WCE produces, however, near 50,000 frames that have to be examined. In this paper a registration methodology is presented to reduce the amount of frames, which are the same or similar. It utilizes a segmentation scheme and a graph method to register similar regions in two consecutive frames. In addition our methodology offers a degree of similarity between two frames using a confidence function of similarity, in order to discard extremely dissimilar frames and thus set a mark of a new series of frames. Finally, a useful feature called Center of Image Similarity is also presented. Illustrative results from the methodology are also given in this paper.

[1]  Dimitrios K. Iakovidis,et al.  Automatic frame reduction of Wireless Capsule Endoscopy video , 2008, 2008 8th IEEE International Conference on BioInformatics and BioEngineering.

[2]  G. Iddan,et al.  Wireless capsule endoscopy , 2003, Gut.

[3]  Sudhanshu K. Mishra.  Median as a Weighted Arithmetic Mean of All Sample Observations , 2004 .

[4]  Nikolaos G. Bourbakis,et al.  A fuzzy region growing approach for segmentation of color images , 1997, Pattern Recognit..

[5]  Nikolaos G. Bourbakis,et al.  Detecting abnormal patterns in WCE images , 2005, Fifth IEEE Symposium on Bioinformatics and Bioengineering (BIBE'05).

[6]  Douglas G. Adler,et al.  Wireless Capsule Endoscopy , 2003 .

[7]  Nikolaos G. Bourbakis,et al.  A stochastic optimization scheme for automatic registration of aerial images , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.

[8]  Mubarak Shah,et al.  Adaptive Region-Based Video Registration , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[9]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[10]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.