Invariant recognition of rectangular biscuits through an algorithm operating exclusively in hough space. Flawed pieces detection

• Autor: Montenegro J., Javier
• Formato: artículo
• Fecha de Publicación: 2002
• Institución: Universidad Nacional Mayor de San Marcos
• Repositorio: Revistas - Universidad Nacional Mayor de San Marcos
• Lenguaje: español
• OAI Identifier: oai:ojs.csi.unmsm:article/8791
• Enlace del recurso: https://revistasinvestigacion.unmsm.edu.pe/index.php/fisica/article/view/8791
• Nivel de acceso: acceso abierto
• Materia: Cybernetic Vision; Artificial Intelligence; Computational Vision; Invariant pattern recognition; Invariant shape classification; Polar Hough transform; Biscuit Recognition; Flawed Biscuits Detection.; Visión Cibernética; Inteligencia Artificial; Visión Computacional; Reconocimiento de Patrones; Clasificación Invariante de formas; Transformada Polar de Hough; Reconocimiento de Galletas; Detección de Galletas Falladas.

An Algorithm based on the polar Hough Transform has been developed so as to carry out rotation, translation and size-scaling invariant pattern recognition. The algorithm exploits the fundamental properties of the HT and all the required operations take place strictly in Hough space. The developed system has been successfully applied to the recognition of biscuits in the form of rectangular crackers, including f!awed pieces, which were easily discriminated against by the algorithm. The results suggest the possibility of an industrial application of this algorithm particularly in industrial quality control. © 2002 CSI. All rights reserved