Probability density function based modeling of spatial feature variation in capsule endoscopy data for automatic bleeding detection

Amit Kumar Kundu, Shaikh Anowarul Fattah

Abstract: Highlights•Local spatial feature variation patterns are obtained for various statistical measures.•The new idea introduced in this paper is to exploit the characteristics of the feature variation pattern for utilizing in classification by introducing PDF model fitting approach.•A new scheme is developed to further examine few more critical pixels for precise bleeding region identification.•The last part of the manuscript deals with analysis in continuous videos.