Learning Integrated Image Segmentation and Object Recognition

This paper presents a general approach to image segmentation and object recognition that learns a mapping from images with varying properties to segmentation algorithm parameters. The mapping is built using a reinforcement learning algorithm that is based on a team of generalized stochas-tic learning automata and operates separately in a global or local manner on an image. The edge-border coincidence is rst used as an immediate reinforcement to reduce computational expenses associated with model matching during the early stage of the learning process. Since this measure however can not reliably predict the outcome of object recognition , it is used in conjunction with model matching that provides optimal segmentation evaluation in a closed-loop object recognition system. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.