Local reinforcement learning for object recognition

Jing Peng and Bir Bhanu College of Engineering University of California, Riverside, CA 92521 fjp,[email protected] Abstract Current computer vision systems whose basic methodology is open-loop or lter type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most realworld applications. In contrast, the system presented here achieves robust performance by using local reinforcement learning to induce a highly adaptive mapping from input images to segmentation strategies. This is accomplished by using the con dence level of model matching as reinforcement to drive learning. The system is veri ed through experiments on a large set of real images.