Author(s): LIMA, C. M. de; FERNANDES, D. D. S.; PEREIRA, G. E.; GOMES, A. de A.; ARAÚJO, M. C. U. de; DINIZ, P. H. G. D.

Summary: This work proposes the development of a simple, fast, and inexpensive methodology based on color histograms (obtained from digital images), and supervised pattern recognition techniques to classify redwines produced in the São Francisco Valley (SFV) region to trace geographic origin, winemaker, and grape variety. PCA-LDA coupled with HSI histograms correctly differentiated all of the SFV samples from the other geographic regions in the testset; SPA-LDA selecting just 10 variables in the Gray scale+HSI histogram achieved 100% accuracy in the test set when classifying three different SFV winemakers. Regarding the three grape varieties, SPA-LDA selected 15 variables in the RGB histogram to obtain the best result, misclassifying only 2 samples in the tests et. Pairwise grape variety classification was also performed with only 1 misclassification. Besides following the principles of Green Chemistry, the proposed methodology is a suitable analytical tool; for tracing origins, grapetype, and even (SFV) winemakers

Publication year: 2020

Types of publication: Journal article

Unit: Embrapa Grape & Wine

Keywords: Cabernet Sauvignon, Color histogram, Digital images, Geographical origin indication, Histograma de cores, Imagens digitais Algoritmo, Indicação de origem geográfica, Red wines, Successive projections algorithm, Syrah, Touriga Nacional, Vinho tinto