Multimodel Human Authentication by Matching 3D Skull and Gait

This research paper focuses multimodal human identifications that are captured in a web cam as images of face and walking style. The image can then be considered for further analyses of gait and skull characteristics as per Human Identification Systems. We propose to identify a skull by using a correlation measure between the 3D skull and 3D face in terms of morphology, and measure the correlation using Enhance Canonical Correlation Coefficient Analysis (ECCCA). We use the 3D skull data as the probe and 3D face geometric data as the gallery and match the skull with enrolled 3D faces by the correlation measure between the Probe and the Gallery. This paper proposes Uncorrelated Multilinear Discriminant Analysis (UMLDA) algorithm for the challenging problem of Gait Recognition. Finally, Neural Network for mat-lab tool is used for training and testing purpose. We have created different model of neural network based on hidden layer, selection of training algorithm and setting the different parameter for training. And then, we will test for the combination of NN+SVM, Knearest Neighbour Classification. Here all these experiments are done on CASIA gait database and input video.