Face Localization with Recursive Neural Networks

Recognizing a particular face in a complex image or in a video sequence, which the humans can simply accomplish using contextual information, is a difficult task for an automatic recognizer. Moreover, the face recognition problem is usually solved having assumed that the face was previously localized, often via heuristics based on prototypes of the whole face or significant details. In this paper, we propose a novel approach to the solution of the face localization problem using recursive neural networks. In particular, the proposed approach assumes a graph–based representation of images that combines structural and sub–symbolic visual features. Such graphs are then processed by recursive neural networks, in order to establish the eventual presence and the position of the faces inside the image. Some preliminary experiments on snapshots from video sequences are reported, showing very promising results.