Open AccessGait-based Biometric Identification System using Triangulated Skeletal Models (TSM)
Author(s) -
Azhin Tahir Sabir
Publication year - 2021
Publication title -
academic journal of nawroz university
Language(s) - English
Resource type - Journals
ISSN - 2520-789X
DOI - 10.25007/ajnu.v10n3a1223
Subject(s) - biometrics , gait , computer science , artificial intelligence , identification (biology) , computer vision , pattern recognition (psychology) , feature (linguistics) , set (abstract data type) , gait analysis , physical medicine and rehabilitation , medicine , linguistics , philosophy , botany , biology , programming language
Human gait identification is a behavioral biometric technology which can be used to monitor human beings without user interaction. Recent researches are more focused on investigating gait as one of the biometric traits. Further, gait recognition aims to analyze and identify human behavioral activities and may be implemented in different scenarios including access control and criminal analysis. However, using various techniques in relation to image processing and obtaining better accuracy are remaining challenges. In last decade, Microsoft has introduced the Kinect sensor as an innovative sensor to provide image characteristics, precisely. Therefore, this article uses a Kinect sensor to extract gait characteristics to be used in individual recognition. A set of Triangulated shape are generated as new feature vector and called Triangulated Skeletal Model (TSM). Nearest Neighbor technique is utilized to do the recognition issue based on leave-one-out strategy. The experimental outcomes indicated that the recommended technique provides significant results and outperforms other comparative similar techniques with accuracy of 93.46%.