Intelligent classifier applied to visual quality inspection of bean grains

• Grant number: 14/09194-5
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2014
• End date: July 31, 2016
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Sidnei Alves de Araújo
• Grantee: Sidnei Alves de Araújo
• Host Institution: Universidade Nove de Julho (UNINOVE). Campus Memorial. São Paulo , SP, Brazil
• Associated researchers: Jorge Henrique Pessota ; José Carlos Curvelo Santana ; Wonder Alexandre Luz Alves

Abstract

Bean is an important source of energy and protein and is present in the daily diet of the Brazilian people. Like most food products, their visual properties are important to determine its market price and help its choice by the consumer. Basically, the quality inspection of Brazilian beans is done manually by following the operating procedures established by the Ministry of Agriculture, Livestock and Supply. However, in manual processes of quality inspection usually occur some problems such as high cost and lack of standardization of results. In this context, it is important the use of computational systems for supporting such processes in order to reduce operational costs and standardize the results, generating competitive advantage for the companies. In this project, we propose to develop an intelligent classifier, based on techniques of visual pattern recognition and computational intelligence, able to classify the most consumed beans in Brazil, based on the color and size of the grains. This classifier can be applied to the quality inspection of Brazilian beans, since one of the steps of this process is the measurement of the mixture contained in a sample, taking into account the skin colors of the grains, to determine the predominant class of the product, which directly affects its market price. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DE ARAUJO, SIDNEI ALVES; PESSOTA, JORGE HENRIQUE; KIM, HAE YONG. Beans quality inspection using correlation-based granulometry. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, v. 40, p. 84-94, APR 2015. (14/09194-5)