A new perspective — Face recognition with light-field camera

Face recognition has received a substantial attention from industry and also academics. The improvement in the image sensors has further boosted the performance of the face recognition algorithm in real-world scenarios. In this paper, we evaluate the strength of the light-field camera for for face recognition applications. The main advantage of a light-field camera is that, it can provide different focus (or depth) images in a single capture which is not possible with a conventional 2D camera. We first collected a new face dataset using both the light-field and a conventional camera by simulating real-world scenarios. We then propose a new scheme to select the best focused face image from a set of focus images rendered by the light-field camera. Extensive experiments are carried out on our new face dataset to bring out the merits and demerits of employing the light-field camera for face recognition applications.