Image Characterization via Multilayer Neural Networks

• Published in: 2008 20th IEEE International Conference on Tools with Artificial Intelligence Vol. 1; pp. 325 - 332
• Main Authors: Barcelos, C.A.Z., Ribeiro, E.F., Batista, M.A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-11-2008
• Subjects: Artificial intelligence; Artificial neural networks; Computer networks; Feature extraction; Humans; Image retrieval; Information retrieval; Input variables; Multi-layer neural network; Neural networks
• ISBN: 0769534406; 9780769534404
• ISSN: 1082-3409; 2375-0197
• DOI: 10.1109/ICTAI.2008.71

The achievement of image retrieval systems severally depends on the way the data is represented. This paper proposes a new image representation through an intelligent mechanism via neural networks for semantic-gap and dimensionality reduction. The goal of the multilayer neural network is to represent high-level semantic concepts and 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 human perception and automatic feature extraction. The experimental results show the effective performance of the proposed technique.