Intelligent image characterization
Eduardo Ferreira Ribeiro, Célia A. Zorzo Barcelos, M.A. Batista · 2008
This work presents a new image characterization through an intelligent mechanism via neural networks. The goal of a neural network is to represent the high-level semantic concepts and the knowledge through a pre-defined set of images. As a consequence of this low-level into high-level feature transformation there is a semantic gap reduction between the human perception and the automatic feature extraction. The experimental results show the effective performance of the proposed technique.