Raw sugarcane classification in the presence of small solid impurity amounts using a simple and effective digital imaging system

Author(s)

Guedes, Wesley Nascimento ^[1] ; Verbi Pereira, Fabiola Manhas ^{[2, 1]}

Affiliation

^[1] Sao Paulo State Univ UNESP, Bioenergy Res Inst IPBEN, Inst Chem, BR-14800060 Sao Paulo - Brazil

^[2] Idaho State Univ, Dept Chem, Pocatello, ID 83209 - USA

• Document type: Journal article
• Source: COMPUTERS AND ELECTRONICS IN AGRICULTURE; v. 156, p. 307-311, JAN 2019.
• Web of Science Citations: 0

Abstract

Specific amounts of solid impurities in raw sugarcane need to be detected before raw materials are carried into mills. Solid impurities come from the plant, e.g., green and dry leaves and soil. This study proposed to classify sugarcane via a new strategy using a well-established method that combines digital images converted into ten color-scale color histograms of red (R), green (G) and blue (B), RGB; hue (H), saturation (S) and value (v), HSV; relative colors of RGB, rgb; and luminosity (L) with multivariate classification methods. Sampling was performed using a mixture design that comprised 122 different combinations of sugarcane stalks, vegetal plant parts and soil to achieve 100 wt% for evaluating the desirable and undesirable situations for the solid impurity amounts. Classical algorithms, such as soft independent modeling of class analogy (SIMCA), partial least squares discriminant analysis (PLS-DA) and k nearest neighbors (kNN), were used to perform the calculations. Receive operating characteristic (ROC) revealed the high sensitivity and specificity of the three algorithms using the color histogram data. The outstanding result was the ability to classify sugarcane content higher than 85 wt%, which is considered high-quality raw material by cane mills. (AU)

• FAPESP's process: 16/00779-6 - Direct obtaining of chemical information with commercial purposes from several solid analytical matrices using laser induced breakdown spectroscopy (LIBS) and Chemometrics
• Grantee: Hideko Yamanaka
• Support Opportunities: Regular Research Grants
• FAPESP's process: 17/05550-0 - New chemometric strategies using Tikhonov regularization for improvement of multivariate calibration models
• Grantee: Fabiola Manhas Verbi Pereira
• Support Opportunities: Scholarships abroad - Research