Pyramidal Structure Algorithm for Fingerprint Classification Based on Artificial Neural Networks
Eugène Cokou Ezin, Unité de Recherche en Informatique et Sciences Appliquées Institut de Mathématiques et de Sciences Physiques Université d’Abomey-Calavi, Benin · Journal of Advanced Computational Intelligence and Intelligent Informatics · 2010
Feature extraction plays a primary role in pattern recognition classification. Many context-based and problem-based algorithms have been proposed providing good performance in high-quality fingerprint imaging but fail when declining with poor-quality fingerprints. The pyramidal algorithm we present in this paper operates on an image matrix layer for extracting features from ink-and-paper fingerprints. The effectiveness of the pyramidal algorithm compared to the consolidation algorithm is demonstrated using a backpropagation neural network experiment to test preprocessed data.