A Novel Method for Sensing Obscene Videos using Scene Change Detection

Abstract

Video scene change detection has great importance of managing and analyzing large amount ofvideos. Traditionally this technique used for indexing, segmenting and categorizing different typesof videos. Very few works addressed to classify obscene using scene change detection method. Inthis research we proposed a simple approach for sensing objectionable videos by observing scenechanges into different video genres. Video scenes are grouped into set of key frames. Afteranalyzing duration of each scene and counting the number of key frames of designated scene, ithas been shown that obscene videos have infrequent scene changing nature. While in sports,dramas, music and action films have large number of scene changes. We used six types of videogenres and the decision has been made by setting a threshold based on extracted key.

DOI:  http://dx.doi.org/10.11591/telkomnika.v13i2.6873