Gait Recognition is an Biometric Feature which has attracted many researchers in recent years. Gait recognition is a task to identify or verify individuals by the way they walk. In Video Surveillance based application identifying the Human gait is important because it captures the human from a distance[1]. Gait Recognition have advantages like Unobtrusiveness, other is that without knowledge of a person his gait can be captured and also high quality of videos are not required. Gait Recognition approaches are divided into two types : Model Free and Model based Approaches[2]. Model based approaches have a series of static or Dynamic body parameters by tracking body components such as limbs, legs, arms and thighs, Gait signatures derived from …show more content…
Recognition: Extracted samples are compared to the samples stored in a database. The identity of an individual having the most (and enough) similar gait sample is picked and stated as the recognition verdict. Gait recognition system can be used in a number of scenarios. If an individual walks by the camera who’s gait has been previously recorded and he is stated as a threat, then the system will identify him and the concerned authorities can be automatically alerted. Such systems have a large amount of strong application in airports, banks or other high security areas. METHODS FOR GAIT RECOGNITION [4] Principal component analysis (PCA) is applied to reduce the dimensionality . Dynamic time warping is used to differentiate the different gaits of human. This reduction obtained by PCA is important to make classification with DTW more efficient and save computing time to meet the requirements of real-time applications. PCA (Principal Component Analysis) : PCA is the simplest method of the True Eigenvector-based multivariate …show more content…
In order to enhance the class separability further and avoid the potential overfitting, a discriminative locality preserving projection with sparse regularization is used to transform the refined tensor data to the final vector feature representation for recognition. An efficient tensor to vector projection algorithm is introduced to find a low-dimensional tensor subspace of the original input gait sequence