Multimodal Biometric Database for Person Identification and Gait Analysis

In this paper, we report the development and evaluation of a benchmark database, the University of Canberra Multimodal Biometric Database (UCMB-Database) for human identity verification. The UCMB database developed in mid-2013 was developed for Doctoral thesis work in School of Information Technology and Engineering, Faculty of ESTeM. This is the 1st database of its kind in Australia, and is accessible to the researchers in the biometric area around the world. For each person, the database consists of (7) different types of walking or gait pattern information, including (i) normal walking, (ii) fast walking, (iii) walking with heavy bag, (iv) walking with overcoat (long jacket), (v) walking with hat, (vi) walking with hoody and (vii) walking with mask. All these sequences have captured with four (4) different cameras in four (4) different dimensions including; 130 degree, 270 degree, 315 degree view point, and 315 degree from top (roof) with surveillance Camera. More than hundred (100) individual and around three thousand (3000) different video-sequences are included in the UCMB-Database. The evaluation study of this benchmark biometric database shows that this database can be used for development of novel algorithmic approaches for person identification based on side-face, frontal face, ear, gait etc. Further, the approaches developed in this study can also be extended for it for medical analysis (such as investigating gait abnormalities in children due to cerebral palsy),and in sports studies (impact of gait abnormalities due to sports injuries on performance in a sport such as football or soccer). We are expecting the database is one of largest and one of unique database (in terms of different traits) in the world.