Feature extraction in X-ray images for hazelnuts classification

Abstract

In the food industry, the importance of automatic detection and selection of raw food ingredients is increasing. In this paper, a method for real time automatic detection, segmentation and classification of hazelnuts using x-ray images is presented. Automatic extraction of independent nut images is made using image processing techniques. To extract meaningful features, moment invariants and texture properties are calculated on global level as well as from co-occurrence matrices. Principal component analysis is applied on features to achieve orthogonality in addition to dimensionality reduction. An anomaly detection algorithm is used for classification. Multivariate Gaussian distributions are calculated for model estimation using training data. Results are calculated on test data by using the threshold value obtained from best validation outcome. The classifier showed 98.6% correct classification rate for negative examples with 0% false negative rate.

Genome-Wide Association Study Reveals Candidate Genes Involved in Fruit Trait Variation in Persian Walnut (Juglans regia L.)

“…Careful consideration of the phenotyping method is of great importance since the heritability of a given trait may depend on the accuracy of the data ( Furbank and Tester, 2011 ; Burghardt et al, 2017 ). Phenotyping techniques are evolving along with genotyping technologies, and X-ray computed tomography (CT) is one of the imaging techniques applied in food sciences to evaluate internal quality ( Kotwaliwale et al, 2014 ), used notably for studying nut species such as almond, hazelnut, pecan ( Harrison et al, 1993 ; Kim and Schatzki, 2001 ; Khosa and Pasero, 2014 ), and recently walnut ( Bernard et al, 2020a ).…”

3D characterization of walnut morphological traits using X-ray computed tomography

“…In apples, X-ray CT was used to evaluate the density and the water content under varying moisture conditions [44], while in pears this technology was used to study the core breakdown development [45]. This method was also used in nuts and few works are reported, such as the detection of pinhole insect damage in almonds [46], the segmentation and classification in hazelnuts [47] and the behaviour study of fourth-instar weevil in pecan nuts [48]. In grapevine, a recent study aimed to characterize inflorescence architecture using X-rays [49].…”

Breeding Innovations in Underutilized Temperate Fruit Trees

“…Careful consideration of the phenotyping method is of great importance since the heritability of a given trait may depend on the accuracy of the data (Furbank and Tester, 2011;Burghardt et al, 2017). Phenotyping techniques are evolving along with genotyping technologies, and X-ray computed tomography (CT) is one of the imaging techniques applied in food sciences to evaluate internal quality (Kotwaliwale et al, 2014), used notably for studying nut species such as almond, hazelnut, pecan (Harrison et al, 1993;Kim and Schatzki, 2001;Khosa and Pasero, 2014), and recently walnut (Bernard et al, 2020a).…”