Multi Task Learning System for Face and Gait Recognition and Comparison of Different Algorithms on These Recognitions

— In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. As in our project we are dealing with the Face recognition and the Gait recognition combine. Face recognition: Face recognition is a task so common to humans, that the individual does not even notice the extensive number of times it is performed every day. y. Many face analysis and face modeling techniques have progressed significantly in the last decade. However, the reliability of face recognition schemes still poses a great challenge to the scientific community. Gait recognition: Gait recognition is the process where the features of human motion are automatically obtained/extracted and later these features enable us to authenticate the identity of the person in motion. gait recognition technique also involves 2 stages: Information is derived from human locomotion in the first stage i.e. feature extraction stage and in the next stage, i.e. the recognition stage, a standard similarity computation technique is used to obtain results for being a match or a mismatch. A unique advantage of gait as a biometric is that it offers potential for recognition at a distance or at low-resolution or when other biometrics might not be perceivable. Combining these two recognitions is known as multi task learning.