Score Level and Rank Level Fusion for Kinect-Based Multi-Modal Biometric System

Open access

Abstract

Computational intelligence firmly made its way into the areas of consumer applications, banking, education, social networks, and security. Among all the applications, biometric systems play a significant role in ensuring an uncompromised and secure access to resources and facilities. This article presents a first multimodal biometric system that combines KINECT gait modality with KINECT face modality utilizing the rank level and the score level fusion. For the KINECT gait modality, a new approach is proposed based on the skeletal information processing. The gait cycle is calculated using three consecutive local minima computed for the distance between left and right ankles. The feature distance vectors are calculated for each person’s gait cycle, which allows extracting the biometric features such as the mean and the variance of the feature distance vector. For Kinect face recognition, a novel method based on HOG features has been developed. Then, K-nearest neighbors feature matching algorithm is applied as feature classification for both gait and face biometrics. Two fusion algorithms are implemented. The combination of Borda count and logistic regression approaches are used in the rank level fusion. The weighted sum method is used for score level fusion. The recognition accuracy obtained for multi-modal biometric recognition system tested on KINECT Gait and KINECT Eurocom Face datasets is 93.33% for Borda count rank level fusion, 96.67% for logistic regression rank-level fusion and 96.6% for score level fusion.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] Gavrilova M. Monwar M. Multimodal Biometrics and Intelligent Image Processing for Security Systems Hardcover IGI Global 350 pages 2012

  • [2] Ross A. Nandakumar K. Jain A. Handbook of Multibiometrics New York: Springer-Verlag 2006

  • [3] Kastaniotis D. et.al. A Framework for Gait-based Recognition Using Kinect Pattern Recognition Elsevier Vol. 68(2) pp. 327-335 2015

  • [4] Leszek Rutkowski Computational Intelligence: Methods and Techniques 1st Ed book Springer 2008

  • [5] Y Wang et.al. Cognitive Intelligence: Deep Learning Thinking and Reasoning by Brain-Inspired Systems IJCINI vol. 10 no. 4 pp1-20 2016

  • [6] Paul P.P. Gavrilova M. Alhajj R. Decision Fusion for Multimodal Biometrics Using Social Network Analysis IEEE Trans. On Systems Man and Cybernetics vol. 44 no. 11 pp. 1522-1533 2014

  • [7] Monwar M. Gavrilova M. Multimodal Biometric System using Rank-Level Fusion Approach IEEE Trans. on Systems Man and Cybernetics vol. 39 no. 4 pp. 867-878 2009

  • [8] Rahman M.W. Gavrilova M. Kinect Gait Skeletal Joint Feature Based Person Identification 16th Int. Conference on Cognitive Informatics & Cognitive Computing (ICCICC) IEEE pp. 423-430 2017

  • [9] Shakhnarovich G. Darrel T. On Probabilistic Combination of Face and Gait Cues for Identification 5th International Conference on Automatic Face and Gesture Recognition IEEE pp. 1-6 2002

  • [10] Rahman M.W. Zohra F.T. Gavrilova M. Rank Level Fusion for Kinect Gait and Face Biometric Identification Symposium Series on Computational Intelligence (SSCI) IEEE pp. 2218-2224 2017

  • [11] Kale A. Roychowdhury A. Chellappa R. Fusion of Gait and Face for Human Identification International Conference on Acoustics Speech and Signal Processing IEEE pp. 1-5 2004

  • [12] Ranganath T. Lee T. Sanei S. Fusion of Chaotic Measure into a New Hybrid Face-Gait System for Human Recognition 18th International Conference on Pattern Recognition IEEE vol. 4 pp. 541-544 2006

  • [13] Zhou X. Bahanu B. Feature Fusion of Face and Gait for Human Recognition at a Distance in Video 18th International Conference on Pattern Recognition (ICPR) IEEE vol. 4 pp. 529-532 2006

  • [14] Zhou X. Bahanu B. Integrating Face and Gait for Human Recognition at a Distance in Video IEEE Trans. on Systems Man and Cybernetics vol. 37 no. 5 pp. 119-1137 2007

  • [15] Geng X. et.al. Adaptive Fusion of Gait and Face for Human Identification in Video Workshop on Application of Computer Vision IEEE pp. 1-6 2008

  • [16] Hossain E. Chetty G. Multimodal Face-Gait Fusion for Biometric Person Authentication International Conference on Embedded and Ubiquitous Computing (EUC) IEEE pp. 332-337 2011

  • [17] Hoffman M. et.al Combined face and gait recognition using alpha matte preprocessing 5th International Conference on Biometric (ICB) IEEE pp. 390-395 2012

  • [18] Almohammod M. Salma G. Mahmoud T. Human identification system based on feature level fusion using face and gait biometrics International Conference on Engineering and Technology (ICET) IEEE pp. 1-5 2012

  • [19] Xing X. Wang K. Lv Z. Fusion of Gait and Facial Features using Coupled Projections for People Identification at a Distance IEEE Signal Processing Letters vol. 22 no. 12 pp. 2349-2353 2015

  • [20] Zhang D. et.al. Ethnicity classification based on fusion of face and gait International Conference on Biometric (ICB) IEEE pp. 384-389 2012

  • [21] Zhang D. Wang Y. Gender recognition based on fusion on face and gait information International Conference on Machine Learning and Cybernetics IEEE vol. 1 pp. 62-67 2008

  • [22] Ahmed F. Paul P.P. Gavrilova M. DTW based Kernel and Rank Level Fusion for 3D Gait Recognition using Kinect The Visual Computer vol. 31 no 6 pp. 915-924 2015

  • [23] Vondrick C. et. al. HOGgles: Visualizing Object Detection Features International Journal on Computer Vision pp. 1-9 2013

  • [24] http://www.upcv.upatras.gr/personal/kastaniotis/datasets.html Last accessed: September 20 2017

  • [25] Min R. Kose N. Dugelay J.L. KinectFaceDB: A Kinect database for face recognition IEEE Transactions on Systems Man and Cybernetics: Systems vol. 44 no.11 pp. 1534-1548 2014

  • [26] Paul P.P. Gavrilova M. Alhajj R. Decision Fusion for Multimodal Biometrics Using Social Network Analysis Transactions on Systems Man and Cybernetics Systems IEEE vol. 44 no. 11 pp. 1522-1533 2014

  • [27] Xing X. Wang K. Lv Z. Fusion of Gait and Facial Features using Coupled Projections for People Identification at a Distance Signal Processing Letters IEEE vol. 22 no. 12 pp. 2349-2353 2015

Search
Journal information
Impact Factor


CiteScore 2018: 4.70

SCImago Journal Rank (SJR) 2018: 0.351
Source Normalized Impact per Paper (SNIP) 2018: 4.066

Metrics
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 312 312 36
PDF Downloads 182 182 12