• Prashant Kumar

Authors build up a view-normalization way to deal with multi-view face and gait recognition. An image based visual hull (IBVH) is registered from a lot of monocular views and used to render virtual viewpoints for tracking and recognition. Authors determine canonical viewpoints by looking at the 3-D structure, appearance (texture), and movement of the moving individual. For ideal face recognition, authors place virtual cameras to catch frontal face appearance; for gait recognition authors place virtual cameras to catch a side-perspective on the individual. Numerous cameras can be rendered at the same time, and camera position is powerfully refreshed as the individual travels through the workspace. Image arrangements from each accepted view are passed to an unmodified face or gait recognition algorithm. Authors show that our methodology gives more noteworthy recognition precision than is acquired utilizing the unnormalized input successions, and that integrated face and gait recognition gives improved performance over either methodology alone. Canonical view estimation, rendering, and recognition have been efficiently actualized and can run at close to real-time paces.

: Biometrics, Face recognition, Fusion, Gait recognition, Multiple views.

"Multiple Angled Integration of Face and Gait Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.353-358, January-2019, Available :http://www.jetir.org/papers/JETIREY06075.pdf

"Multiple Angled Integration of Face and Gait Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp353-358, January-2019, Available at : http://www.jetir.org/papers/JETIREY06075.pdf