Development of an automated method for the identification of defective hazelnuts based on RGB image analysis and colourgrams. (December 2018)

• Record Type: Journal Article
• Authors: Giraudo, A.; Calvini, R.; Orlandi, G.; Ulrici, A.; Geobaldo, F.; Savorani, F.
• Is Part Of: Food control. Volume 94(2018)
• Page Start: 233
• Page End: 240
• Publication Date: 2018-12
• Subjects: Hazelnut -- Defect detection -- Multivariate image analysis -- Colourgrams -- Classification -- Variable selection; Food -- Quality -- Periodicals; Food -- Analysis -- Periodicals; Food handling -- Periodicals; Food industry and trade -- Quality control -- Periodicals; Aliments -- Industrie et commerce -- Qualité -- Contrôle -- Périodiques; Aliments -- Qualité -- Périodiques; Aliments -- Analyse -- Périodiques; Hygiène alimentaire -- Périodiques; Food -- Analysis; Food handling; Food -- Quality; Periodicals; Electronic journals; 664.07
• DOI: 10.1016/j.foodcont.2018.07.018
• Languages: English
• ISSNs: 0956-7135

Abstract

Abstract: Over the past decades, Red-Green-Blue (RGB) image analysis has gained increasing importance in industrial applications, since it has widely proved to be a suitable tool for food quality and process control. This article describes the development of a fast and objective method for the automated identification of defective hazelnut kernels based on multivariate analysis of RGB images. To this aim, an overall sample set of 2000 half-cut hazelnut kernels, previously assigned by industrial expert assessors as sound or defective (i.e. rotten or pest-affected), was collected and imaged using a digital camera. The colour-related information of the images was converted into one-dimensional signals, named colourgrams, which were firstly explored through the Principal Component Analysis and subsequently used to build classification models, based on both Partial Least Square-Discriminant Analysis (PLS-DA) and interval-PLS-DA (iPLS-DA) algorithms. A tree-structure hierarchical classification approach has been considered, i.e. the discrimination between sound and defective kernels as a first rule, and the discrimination between the two types of defect as a second rule. The best sound vs defective classification model was able to correctly recognize approximately the 97% of the test set defective samples, while the best rotten vs pest-affected model allowed classifying correctly more than 92% of the test set samples. Moreover, the image reconstruction performed using the selected colourgram features led to an exhaustive interpretation of the decision-making criteria adopted by the classification algorithms and further confirmed the reliability of the proposed method. Highlights: RGB image analysis was investigated for automatically detecting defective hazelnuts. Conversion of images into colourgrams allowed to easily manage a large image dataset. Partial Least Square-Discriminant Analysis was applied to build classification models. Variable selection applied to colourgrams led to an improvement of prediction results. Visualization of the selected features allowed to identify the defective nut regions.