PROJECT TITLE :
Robust Face Recognition From Multi View Videos - 2014
Multiview face recognition has become a full of life analysis space in the previous few years. During this paper, we have a tendency to present an approach for video-based mostly face recognition in camera networks. Our goal is to handle cause variations by exploiting the redundancy within the multiview video information. But, in contrast to ancient approaches that explicitly estimate the create of the face, we tend to propose a novel feature for robust face recognition in the presence of diffuse lighting and cause variations. The proposed feature is developed using the spherical harmonic illustration of the face texture-mapped onto a sphere; the texture map itself is generated by back-projecting the multiview video data. Video plays an necessary role in this situation. First, it provides an automatic and efficient approach for feature extraction. Second, the data redundancy renders the recognition algorithm a lot of sturdy. We measure the similarity between feature sets from totally different videos using the reproducing kernel Hilbert house. We tend to demonstrate that the proposed approach outperforms traditional algorithms on a multiview video database.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here