A Porn Video Detecting Method Based on Motion Features Using HMM

This paper proposes a method of identified reciprocating motion in pornographic video from other human action using Hidden Markov Model (HMM). The motion vectors are obtained by decoding the compressed MPEG video. Then the feature vectors are extracted by calculating the direction and the magnitude...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyi Qu, Yanmin Liu, Ying Liu, Kang Jiu, Yong Chen
Format: Conference Proceeding
Language:English
Subjects:
Feature extraction
Filters
Government
Hidden Markov models
HMM
Humans
Internet
Motion detection
Motion features
Motion vectors
Porn video
Reciprocating motion detection
Skin
Transform coding
Video compression
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a method of identified reciprocating motion in pornographic video from other human action using Hidden Markov Model (HMM). The motion vectors are obtained by decoding the compressed MPEG video. Then the feature vectors are extracted by calculating the direction and the magnitude of the motion vectors. The feature vectors are fed to Hidden Markov Model for training and classification of actions. Six actions were trained with distinct HMM for classification. The correct recognition result is up to 90%.
DOI:10.1109/ISCID.2009.261