Identificación automática de cilindros de almacenamiento de gas utilizando redes neuronales tipo hopfield
No Thumbnail Available
Date
Advisors
Evaluators
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Industrial de Santander
Abstract
Description
Las compañías que se dedican a la fabricación, comercialización y mantenimiento de cilindros para el gas licuado de petróleo en Colombia, estampan en placas de acero y soldadas al producto un código serial único para ser identificado dentro del parque de cilindros del país. Actualmente el proceso de identificación es manual y se revisan aproximadamente 7000 cilindros al día en una sola fábrica. El objetivo principal de este documento es presentar un sistema de visión artificial que utiliza redes neuronales artificiales para reconocer dicho código. Este sistema se compone físicamente de un dispositivo portátil de ambiente controlado en iluminación y escena para la adquisición de las imágenes. Otro componente del sistema es el ajuste de la imagen. El ajuste se realiza a partir de filtros de mediana, binarización, etiqueta, y segmentación; este procesamiento permite obtener mayor información significativa y discriminación de la imagen. Por último el componente inteligente para la identificación se realiza con redes neuronales artificiales tipo Hopfield y un algoritmo que verifica la evolución del reconocimiento de la imagen. La efectividad del sistema se reporta con los resultados experimentales obtenidos con base al error con una cantidad significativa de muestras.
Companies engaged in the manufacture, marketing and maintenance of cylinders for liquefied petroleum gas in Colombia, stamped steel plates and welded to the product a unique serial code to be identified within the cylinder of the country park. Currently, the identification process is manual and checked approximately 7000 cylinders per day in a single factory. The main objective of this paper is to present a vision system that uses artificial neural networks to recognize the code. This system consists physically of a portable device that controls light environment and scene for the acquisition of images. Another component of the system is to adjust the image. The adjustment is based on median filtering, binarization, label, and segmentation, this processing allows more meaningful information and image discrimination. Finally, the intelligent component identification is performed with Hopfield neural networks and an algorithm that checks the development of image recognition. The effectiveness of the system was reported with experimental results obtained on the basis of error with a significant number of samples.
Companies engaged in the manufacture, marketing and maintenance of cylinders for liquefied petroleum gas in Colombia, stamped steel plates and welded to the product a unique serial code to be identified within the cylinder of the country park. Currently, the identification process is manual and checked approximately 7000 cylinders per day in a single factory. The main objective of this paper is to present a vision system that uses artificial neural networks to recognize the code. This system consists physically of a portable device that controls light environment and scene for the acquisition of images. Another component of the system is to adjust the image. The adjustment is based on median filtering, binarization, label, and segmentation, this processing allows more meaningful information and image discrimination. Finally, the intelligent component identification is performed with Hopfield neural networks and an algorithm that checks the development of image recognition. The effectiveness of the system was reported with experimental results obtained on the basis of error with a significant number of samples.
Keywords
Artificial Vision, gas cylinders, codes, serials, artificial neural networks, hopfield, Visión artificial, cilindros de gas, códigos, seriales, redes neuronales artificiales, Hopfield