X-HuBIS: A Fuzzy Rule based Human Behaviour Identification System based on Body Gestures

Abstract

Objectives: In this paper, an attempt is made to identify the behaviour of human based on his/her body gesture. Body gesture recognition is very important and prime feature to detect the behaviour of the human being so behaviour and frame of mind of any person can be judged from one’s body gesture. Methods/Statistical Analysis: Our proposed system captures an image of a person and recognizes different gestures related to head, hands and legs positions. The different types of rules are defined in fuzzy system that will produce the behaviour and mood after analysing the captured image with knowledge base. Findings: The result is produced in the form of classes which tells the behavior and other characteristics of the person. There are 3 main classes that describe the behavior of the person that is: Positive mood, Negative mood and Neutral mood. These three gestures are matched in the database. Name of gestures are passed to fuzzy system and fuzzy system will produce the result. Application/Improvements: This system can be used to identify the behavior of a person. So it can be used to identify any criminals and terrorists.This proposed system can be used to analyse psychological behaviour of human being which may help in different medical treatments.