Affiliation:
1. Universidade de Santa Cruz do Sul, Brazil
Abstract
ABSTRACT This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively.
Subject
Agronomy and Crop Science,Environmental Engineering
Reference16 articles.
1. MToS: A tree of shapes for multivariate images;Carlinet E.;IEEE Transactions on Image Processing,2015
2. An analytical method for determination of quality parameters in cotton plumes by digital image and chemometrics;Gonçalves M. I. S.;Computers and Electronics in Agriculture,2016
3. Digital image processing;Gonzalez R. C.,2008
4. Análise multivariada de dados;Hair Junior J. F.,2009
5. The WEKA data mining software: An update;Hall M.;SIGKDD Explorations,2009
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献