A feasibility cachaca type recognition using computer vision and pattern recognition

Abstract

a b s t r a c tBrazilian rum (also known as cachaça) is the third most commonly consumed distilled alcoholic drink in the world, with approximately 2.5 billion liters produced each year. It is a traditional drink with refined features and a delicate aroma that is produced mainly in Brazil but consumed in many countries. It can be aged in various types of wood for 1-3 years, which adds aroma and a distinctive flavor with different characteristics that affect the price. A research challenge is to develop a cheap automatic recognition system that inspects the finished product for the wood type and the aging time of its production. Some classical methods use chemical analysis, but this approach requires relatively expensive laboratory equipment. By contrast, the system proposed in this paper captures image signals from samples and uses an intelligent classification technique to recognize the wood type and the aging time. The classification system uses an ensemble of classifiers obtained from different wavelet decompositions. Each classifier is obtained with different wavelet transform settings. We compared the proposed approach with classical methods based on chemical features. We analyzed 105 samples that had been aged for 3 years and we showed that the proposed solution could automatically recognize wood types and the aging time with an accuracy up to 100.00% and 85.71% respectively, and our method is also cheaper.

A fast and low‐cost approach for the discrimination of commercial aged cachaças using synchronous fluorescence spectroscopy and multivariate classification

“…14,16,17,19 Although the models developed by Rodrigues co-workers exhibited better qualitative performance parameters, commercial samples were not used for their construction and validation, significantly reducing the data variance, and consequently the applicability and robustness of these models. 17,19 Moreover, one more disadvantage presented by the models developed by Rodrigues et al was the need for several steps of complex image-processing methods. 17 The model developed in this work showed performance parameters similar to the models by Fernandes et al, 14 and better performance parameters than those by Bernardes and Barbeira.…”

“…[9][10][11][12][13] A brief description of works that present the separation of aged cachaças by the wood used in the maturation process using different analytical and chemometric methods is shown in Table 1. [14][15][16][17][18][19][20][21][22][23] The following unsupervised exploratory methods: principal component analysis (PCA) and hierarchical cluster analysis have been used in combination with high-performance liquid chromatography coupled with diode array detection, 15,18,20 sensorial analysis, 21 electrospray ionization mass spectrometry, 22 and electronic spectroscopy. 23 Supervised classification methods have also been used: Rodrigues and co-workers presented models using artificial neural networks, k-nearest neighbor, linear discriminant analysis, quadratic discriminant analysis, multilayer perceptron, and support vector machine coupled to a computer vision system and chemical information, obtaining accuracy up to 100%.…”

“…23 Supervised classification methods have also been used: Rodrigues and co-workers presented models using artificial neural networks, k-nearest neighbor, linear discriminant analysis, quadratic discriminant analysis, multilayer perceptron, and support vector machine coupled to a computer vision system and chemical information, obtaining accuracy up to 100%. 17,19 Fernandes et al used digital images decomposed into color histograms associated with k-nearest neighbor, linear discriminant analysis, quadratic discriminant analysis, and partial least squares discriminant analysis (PLS-DA), reaching accuracy, sensitivity, and specificity rates higher than 90%. 14 Bernardes and Barbeira presented data fusion PLS2-DA models using electronic spectroscopy and spectrofluorimetry with reliability rates ranging from 56 to 100%.…”

Comparison of Chemometric Problems in Food Analysis using Non-Linear Methods

“…Pérez-Caballero et al [157], reported classification accuracies of above 94% in differentiating between white, rested, aged, and extra-aged tequilas using RF and SVM. Making use of the ensemble of MLP, SVM and NB, Rodrigues et al [158] were able to classify Brazilian rum by aging time and wood type used during the aging process. By co-averaging the individual classifiers, accuracies of 100% was achieved for the wood type and 85.7% for aging time.…”

Emerging Technologies Based on Artificial Intelligence to Assess the Quality and Consumer Preference of Beverages

“…The authors compared different algorithms from discriminant analysis, SVM, and counter-propagation ANN, getting the best results from quadratic discriminant analysis combined with principal components analysis (PCA) with an accuracy of 89%. On the other hand, Rodrigues et al [101] assessed the chemical components and color in RGB and CIELab scales of Cachaça samples and used those values as inputs to develop ANN models to classify the beverages according to (i) age and (ii) type of wood used for aging.…”