Software 2.0 na classificação de sucata metálica
Date
2019-11-15
Embargo
Coadvisor
Journal Title
Journal ISSN
Volume Title
Publisher
Language
Portuguese
Alternative Title
Abstract
O software 2.0 e sua abordagem para o processamento de imagens multi-espectrais,
ajudando a realizar uma classificação automática de sucata metálica, é o tema desta
pesquisa. O uso de ferramentas de Machine Learning e Deep Learning contribuem para
o desenvolvimento de sistemas inteligentes, permitindo obter resultados relevantes na
classificação de imagens, principalmente de sucatas metálicas. Neste mestrado, os testes
serão realizados com uma câmara multi-espectral para obter imagens de alumínio, ferro,
cobre, latão, aço inoxidável, simulando um ambiente de sucata metálica. O objetivo é
obter a classificação destes metais através do desenvolvimento de software e realizar
uma análise multi-espectral das imagens obtidas. Testes preliminares foram feitos em
um ambiente controlado, com uma pequena amostra desses materiais. Estudos para
implementar um protótipo em uma indústria siderúrgica brasileira se seguirão.
Software 2.0 and its approach to the processing of multi-spectral images helping to perform an automatic classification of metal scrap is the subject of this research. The use of Machine Learning and Deep Learning tools contribute to the development of intelligent systems, allowing to achieve relevant results in the classification of images, particularly of metal scrap. In this Master research, tests will be performed with a multi-spectral chamber to obtain images of aluminum, iron, copper, brass, stainless steel, simulating an environment of metal scrap. The aim is to obtain the classification of these metals through the development of software and to perform a multi-spectral analysis of the obtained images. Preliminary tests were made in a controlled environment, with a small sample of these materials. Studies to implement a prototype in a Brazilian steel industry will follow.
Software 2.0 and its approach to the processing of multi-spectral images helping to perform an automatic classification of metal scrap is the subject of this research. The use of Machine Learning and Deep Learning tools contribute to the development of intelligent systems, allowing to achieve relevant results in the classification of images, particularly of metal scrap. In this Master research, tests will be performed with a multi-spectral chamber to obtain images of aluminum, iron, copper, brass, stainless steel, simulating an environment of metal scrap. The aim is to obtain the classification of these metals through the development of software and to perform a multi-spectral analysis of the obtained images. Preliminary tests were made in a controlled environment, with a small sample of these materials. Studies to implement a prototype in a Brazilian steel industry will follow.
Keywords
Software 2.0, Scrap metal classification, Spectral images, Software 2.0, Scrap metal classification, Spectral images
Document Type
Master thesis
Publisher Version
Dataset
Citation
Robalinho, M. J. S. (2019). Software 2.0 na classificação de sucata metálica. (Dissertação de Mestrado), Univerisdade Portucalense, Portugal. Disponível no Repositório UPT, http://hdl.handle.net/11328/2960
Identifiers
TID
202322572
Designation
Mestrado em Informática
Access Type
Open Access