Open Access Open Access  Restricted Access Subscription or Fee Access

A Novel Approach of Gait Recognition Using LDA, PAL and Neural Network Technique

Ekta Chauhan, Akansha Shrivastava


Gait recognition is one type of biometric technology that can be used to the monitor person without their any cooperation. Controlled atmospheres for example; military installations, banks and even airports required to be able to rapidly detect threats and give differing stages of access to various customer groups. Gait presents a specific way or moving manner on the foot and gait recognition is the recognizing procedure an individual through the manner in which they walk. Gait analysis is mainly referred to human locomotion study. From the surveillance view point behavioral recognition and biometrics at a distance are becoming more famous in researchers rather than physiological and interactive biometrics. In this paper, a time effective Human gait identification scheme is proposed. Human gait recognition is a distance based behavioral biometric feature. It is relatively a novel area being studied currently mostly because it is Unobtrusive. This paper presents a survey of various techniques used for recognition of a person based on different activities such as walking style. And also this paper considering a new human gait recognition system based on the Radon transform which provide a high precision recognition rate. For human identification with applying Gait Recognition algorithm which is based on PAL, LDA (Linear Discriminant Analysis) and PAL entropy and NN (Neural Network Technique). Our enhanced human identification applying Gait Recognition algorithm is low cost and more accurate. Our enhanced human identification using Gait Recognition algorithm is fast and thus saves time.

Keywords: Biometrics, Gait, Gait Recognition Approaches

Cite this Artilce
Ekta Chauhan, Akansha Shrivastava. A Novel Approach of Gait Recognition Using LDA, PAL and Neural Network Technique. Recent Trends in Parallel Computing. 2015; 2(3): 27–35p.

Full Text:



David C Post, Gait Analysis Review, 2006. Available at:

Jeffrey E. Boyd, James J. Little, Biometric Gait Recognition, Springer- Verlag Berlin Heidelberg, 2005, 19–42p.

Kota Iwamoto, Kazuyuki Sonobe, Naohisa Komatsu, A Gait Recognition Method using HMM, SICE, Fukui, Japan, 2003; 2: 1936–1941p.

Yanmei Chai, Qing Wang, Jingping Jia, et al. A Novel Human Gait Recognition Method by Segmenting and Extracting the Region Variance Feature, IEEE Computer Society Washington, DC, USA, Patt Recog. 2006; 4: 425 – 428p.

Mark Ruane Dawson, [M. Sc. Thesis], Gait Recognition, Department of Computing Imperial College of Science, Technology & Medicine, 2002.

Jasvinder Pal Singh, Sanjeev Jain, Person Identification Based on Gait using Dynamic Body Parameters, IEEE, Chennai, Trendz in Information Sciences & Computing. 2010, 248–252p.

Jeffrey E. Boyd, James J. Little, Biometric Gait Recognition, Springer- Verlag Berlin Heidelberg, 2005.

Rong Zhang, Christian Vogler, Dimitris Metaxas, Human Gait Recognition, Computer Vision and Pattern Recognition Workshop, 2004.

Sarkar S, Phillips PJ, Liu Z, et al. The Human ID Gait Challenge Problem: Data Sets, Performance, and Analysis, IEEE T Patt Anal Mach Intell. Feb. 2005; 27(2): 162–177p.

Rui Y, Huang TS, Chang SF, Image Retrieval: Current Techniques, Promising Directions and Open Issues, J Vis Commun Image Represent. 1999; 10(4): 39–62p.

Chang SF, The Holy Grail of Content-based Media Analysis, IEEE Multimedia Mag. Apr. 2002; 9(2): 6–10p.

Kale A, Rajagopalan AN, Cuntoor N, et al. Gait-based Recognition of Humans using Continuous HMMs, in Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, Washington, DC, USA, 2002, 336–341p.

Zhong H, Shi J, Visontai M, Detecting Unusual Activity in Video, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2004, 2: 819–826p.

Stauffer C, Grimson WEL, Learning Patterns of Activity using Real-time Tracking, IEEE T Patt Anal Mach Intell. Aug. 2000; 22(8): 747–757p.

Hu W, Xie D, Tan T, et al. Learning Activity Patterns using Fuzzy Self-organizing Neural Network, IEEE T Syst Man Cybern B, Cybern. Jun. 2004; 34(3): 1618–1626p.

Pentland A, Smart Rooms, Smart Clothes, in Proc. Int. Conf. Pattern Recog. 1998; 2: 949–953p.

Forsyth DA, Arikan O, Ikemoto L, et al. Computational Studies of Human Motion: Part 1, Tracking and Motion Synthesis, Found. T Comput Graph Vis. 2005; 1(2-3): 77–254p.

Sadaf Asif, Ali Javed, Muhammad Irfan, Human Identification on the basis of Gaits Using Time Efficient Feature Extraction and Temporal Median Background Subtraction, J Image, Graph Signal Process. 2014; 3: 35–42p. Published Online February 2014 in MECS (

Babak Mohammadi, Mehrdad Fojlaley, Sharzad Busaleiky, et al. Design and Evaluation of New Strategy in Human Gait Recognition, Int J Tech Res Appl. July-Aug 2014; 2(1): 73–76p, e-ISSN: 2320-8163,

Navneet Kaur, Samandeep Singh, Review On: Gait Recognition for Human Identification using NN, Navneet Kaur et al. (IJCSIT) Int J Comp Sci Info Technol. 2014; 5(3): 3991–3993p.

Zankhana P Purohit, Mukesh Sakle, Survey on Biometric Human Gait Recognition, Int J Adv Res Comp Sci Softw Eng. November 2014; 4(11): 771–774p. 22. Murat Ekinci, Murat Aykut, Improved Gait Recognition by Multiple Projections Normalization, Springer- Verlag, 2008.

Bineng Zhong, Hongxun Yao, Shaohui Liu, et al. Local Histogram of Figure/Ground Segmentations for Dynamic Background Subtraction, EURASIP J Adv Signal Process. 2010; 55: doi>10.1155/2010/782101.


  • There are currently no refbacks.

This site has been shifted to