Object recognition on humanoids with foveated vision

Object recognition requires a robot to perform a number of nontrivial tasks such as finding objects of interest, directing its eyes towards the objects, pursuing them, and identifying the objects once they appear in the robot's central vision. In this paper we describe a system that makes use of foveated vision to solve the problem of object recognition on a humanoid robot. The system employs a biologically motivated object representation scheme based on Gabor kernel functions to represent multiple views of objects. We demonstrate how to utilize support vector machines to identify known objects in foveal images using this representation. A mechanism for visual search is integrated into the system to find a salient region and to place an object of interest in the field of view of foveal cameras. The framework also includes a control scheme for eye movements, which are directed using the results of attentive processing in peripheral images.