Saliency-Driven Scene Learning and Recognition Based on Competitively Growing Neural Network Using Temporal Coding
Department of Information Systems Science, Faculty of Engineering, Soka University, 1-236 Tangi-cho, Hachioji-shi, Tokyo 192-8577, Japan
This paper proposes a model of saliency-driven scene learning and recognition in which objects in saliency-driven attended spots are quickly learned and recognized based on the competitively growing neural network using temporal coding. In this model, objects in attended spots are sequentially encoded to be invariant with respect to position and size by this neural network and their positions and sizes are encoded simultaneously. This neural network represents objects using latency-based temporal coding and grows size and recognizability through self-organized learning with growth. Through simulation experiments of a robot equipped with a camera, it is shown that quick self-organized learning and glance recognition of objects in scenes are well performed by our model.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.