The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.02 - February (1998 vol.20)
pp: 139-154
ABSTRACT
<p><b>Abstract</b>—Current computer vision systems whose basic methodology is open-loop or <it>filter</it> type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applications. In contrast, the system presented here achieves robust performance by using reinforcement learning to induce a mapping from input images to corresponding segmentation parameters. This is accomplished by using the confidence level of model matching as a reinforcement signal for a <it>team of learning automata</it> to search for segmentation parameters during training. The use of the recognition algorithm as part of the evaluation function for image segmentation gives rise to significant improvement of the system performance by automatic generation of recognition strategies. The system is verified through experiments on sequences of indoor and outdoor color images with varying external conditions.</p>
INDEX TERMS
Adaptive color image segmentation, function optimization, generalized learning automata, learning in computer vision, model-based object recognition, multiscenario recognition, parameter learning, recognition feedback, segmentation evaluation.
CITATION
Jing Peng, Bir Bhanu, "Closed-Loop Object Recognition Using Reinforcement Learning", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.20, no. 2, pp. 139-154, February 1998, doi:10.1109/34.659932
16 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool