RESUMEN

Imaging sensors are largely employed in the food processing industry for quality control. Flour from malting barley varieties is a valuable ingredient in the food industry, but its use is restricted due to quality aspects such as color variations and the presence of husk fragments. On the other hand, naked varieties present superior quality with better visual appearance and nutritional composition for human consumption. Computer Vision Systems (CVS) can provide an automatic and precise classification of samples, but identification of grain and flour characteristics require more specialized methods. In this paper, we propose CVS combined with the Spatial Pyramid Partition ensemble (SPPe) technique to distinguish between naked and malting types of twenty-two flour varieties using image features and machine learning. SPPe leverages the analysis of patterns from different spatial regions, providing more reliable classification. Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), J48 decision tree, and Random Forest (RF) were compared for samples' classification. Machine learning algorithms embedded in the CVS were induced based on 55 image features. The results ranged from 75.00% (k-NN) to 100.00% (J48) accuracy, showing that sample assessment by CVS with SPPe was highly accurate, representing a potential technique for automatic barley flour classification.

Asunto(s)

RESUMEN

OBJECTIVE: The objective of this study was to evaluate three different degrees of white striping (WS) addressing their automatic assessment and customer acceptance. The WS classification was performed based on a computer vision system (CVS), exploring different machine learning (ML) algorithms and the most important image features. Moreover, it was verified by consumer acceptance and purchase intent. METHODS: The samples for image analysis were classified by trained specialists, according to severity degrees regarding visual and firmness aspects. Samples were obtained with a digital camera, and 25 features were extracted from these images. ML algorithms were applied aiming to induce a model capable of classifying the samples into three severity degrees. In addition, two sensory analyses were performed: 75 samples properly grilled were used for the first sensory test, and 9 photos for the second. All tests were performed using a 10-cm hybrid hedonic scale (acceptance test) and a 5-point scale (purchase intention). RESULTS: The information gain metric ranked 13 attributes. However, just one type of image feature was not enough to describe the phenomenon. The classification models support vector machine, fuzzy-W, and random forest showed the best results with similar general accuracy (86.4%). The worst performance was obtained by multilayer perceptron (70.9%) with the high error rate in normal (NORM) sample predictions. The sensory analysis of acceptance verified that WS myopathy negatively affects the texture of the broiler breast fillets when grilled and the appearance attribute of the raw samples, which influenced the purchase intention scores of raw samples. CONCLUSION: The proposed system has proved to be adequate (fast and accurate) for the classification of WS samples. The sensory analysis of acceptance showed that WS myopathy negatively affects the tenderness of the broiler breast fillets when grilled, while the appearance attribute of the raw samples eventually influenced purchase intentions.

RESUMEN

Identification of different chicken parts using portable equipment could provide useful information for the processing industry and also for authentication purposes. Traditionally, physical-chemical analysis could deal with this task, but some disadvantages arise such as time constraints and requirements of chemicals. Recently, near-infrared (NIR) spectroscopy and machine learning (ML) techniques have been widely used to obtain a rapid, noninvasive, and precise characterization of biological samples. This study aims at classifying chicken parts (breasts, thighs, and drumstick) using portable NIR equipment combined with ML algorithms. Physical and chemical attributes (pH and L*a*b* color features) and chemical composition (protein, fat, moisture, and ash) were determined for each sample. Spectral information was acquired using a portable NIR spectrophotometer within the range 900-1700 nm and principal component analysis was used as screening approach. Support vector machine and random forest algorithms were compared for chicken meat classification. Results confirmed the possibility of differentiating breast samples from thighs and drumstick with 98.8% accuracy. The results showed the potential of using a NIR portable spectrophotometer combined with a ML approach for differentiation of chicken parts in the processing industry.

Asunto(s)