Authentication of carioca common bean cultivars (Phaseolus vulgaris L.) using digital image processing and chemometric tools

Cláudia Domiciano Tormena; Rafaela Cassia Souza Campos; Gustavo Galo Marcheafave; Roy Edward Bruns; Ieda Spacino Scarminio; Elis Daiane Pauli

doi:10.1016/j.foodchem.2021.130349

Authentication of carioca common bean cultivars (Phaseolus vulgaris L.) using digital image processing and chemometric tools

Food Chem. 2021 Dec 1:364:130349. doi: 10.1016/j.foodchem.2021.130349. Epub 2021 Jun 17.

Authors

Cláudia Domiciano Tormena¹, Rafaela Cassia Souza Campos², Gustavo Galo Marcheafave³, Roy Edward Bruns⁴, Ieda Spacino Scarminio⁵, Elis Daiane Pauli⁴

Affiliations

¹ Laboratory of Chemometrics in Natural Sciences (LQCN), Department of Chemistry, State University of Londrina, CP 6001, 86051-990 Londrina, PR, Brazil. Electronic address: claudia.tormena@uel.br.
² Laboratory of Chemometrics in Natural Sciences (LQCN), Department of Chemistry, State University of Londrina, CP 6001, 86051-990 Londrina, PR, Brazil.
³ Laboratory of Chemometrics in Natural Sciences (LQCN), Department of Chemistry, State University of Londrina, CP 6001, 86051-990 Londrina, PR, Brazil. Electronic address: ggalo@uel.br.
⁴ Institute of Chemistry, State University of Campinas, CP 6154, 13083-970 Campinas, SP, Brazil.
⁵ Laboratory of Chemometrics in Natural Sciences (LQCN), Department of Chemistry, State University of Londrina, CP 6001, 86051-990 Londrina, PR, Brazil. Electronic address: ieda@uel.br.

PMID: 34175626
DOI: 10.1016/j.foodchem.2021.130349

Abstract

Bean authentication can result in higher quality products for commerce. Partial least squares discriminant analysis (PLS-DA) was applied to digital images in order to develop a methodology that allows the non-destructive discrimination of three Phaseolus vulgaris L. cultivars (Agro ANfc9, IPR-Andorinha, and IPR-Sabiá) having different technological characteristics. Principal component analysis resulted in a separation of these cultivars, but with a certain amount of overlap. Supervised analysis showed that three PLS1-DA models, each for two cultivars, was moderately better than the simultaneous treatment of all three cultivars (PLS2-DA). Permutation test evaluated statistical significance of PLS-DA models. The classification models were more accurate for Agro ANfc9 and IPR-Sabiá cultivars than for IPR-Andorinha. The Agro ANfc9-IPR-Sabiá model correctly classified 100% of the two bean classes in both training and test sets. This analytical strategy is fast, inexpensive, environmentally friendly, and can be applied for bean quality control helping cultivar authenticity for commerce.

Keywords: Chemometrics; Common bean cultivars; Food authentication; Image analysis; PLS-DA.

MeSH terms

Discriminant Analysis
Image Processing, Computer-Assisted
Least-Squares Analysis
Phaseolus* / genetics
Principal Component Analysis