Description

The recognition of human from the Gait and Footprint were helpful in security purposes. Recognition of persons is not a matter for human visual system. The identification of the persons by the system needs some special mechanisms. The identification of the persons by the systems will be helpful in computer vision process. Recognizing the persons using the feature values extracted from Foot print and Gait is more reliable since the foot print of the same persons have same patterns. These process were easy to implement and they are reliable all the time. The gait of the persons were also more reliable in the identification of the individual persons. Gait analysis is the systematic study of locomotion, more specifically the study of human motion, using the eye and the brain of observers, augmented by instrumentation for measuring body movements, body mechanics, and the activity of the muscles. Gait analysis is used to assess, plan, and treat individuals with conditions affecting their ability to walk. It is also commonly used in sports biomechanics to help athletes run more efficiently and to identify posture-related or movement-related problems in people with injuries. The study encompasses quantification, (i.e. introduction and analysis of measurable parameters of gaits), as well as interpretation, i.e. drawing various conclusions about the animal (health, age, size, weight, speed etc.) from its gait pattern. The Gait sequences were now used for the authentication of a person. The gait energy images and the foot print of the individuals were collected. The collected Gait Energy Image and Foot prints were trained by extracted the feature values and by labeling the individuals. Preprocessing is done by applying median filter. Features were extracted from the preprocessed images. LDA and PCA were employed to extract the feature values from the images. The features were then classified using Euclidean distance metrics. The classifier gives the label corresponding to the input feature. The person is recognized based on the label returned by the classifier. The performance of the processed is measured by employing only Gait for recognition then Foot print alone for recognition and then by combing the Gait and foot print for recognition. The combination of the gait and foot print were proved to produce better recognition rates in all the cases. In most of the cases combination of the biometrics can possibly improve the performance of the recognition process since the disadvantages of one biometric can be overcome by another biometric. The correct classification is measured inorder to measure the performance of the process. The process is tested with different training samples and the results shows that the correct classification rate is high for the combination of Gait and footprint compared to identification using gait and footprint alone.