Multidimensional non supervised analysis (textural and spatial) in MRI tomography for watercore detection - INRAE - Institut national de recherche pour l’agriculture, l’alimentation et l’environnement Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Multidimensional non supervised analysis (textural and spatial) in MRI tomography for watercore detection

Analyse multidimensionnelle non superpervisée d'image tomographique pour la détection de défauts (watercore)

Résumé

This work has been carried out in the frame of the European project InsideFood (Integrated sensing and imaging devices for designing, monitoring and controlling microstructure of foods). The aim of this project is to provide technological solutions for exploring the microstructure of foods, by the combination and application of different non-destructive techniques such as X-ray CT, OCT, MRI, NMR, TRS and SRS, aimed at online sensing of food microstructure, water status, texture and optical properties. Magnetic Resonance Imaging (MRI) has been used in order to detect watercore disorder in three different varieties of apples, which are non commercialized due to their watercore development problems. These three varieties are: Ascara2, Rebellón and Tempera, which were grown under favourable conditions for the development of such disorder. At first step, MRI has been used for screening the apples population in order to detect those ones which had watercore problems. Then, an image analysis has been done in all these apples, in order to check the evidences of such disorder. Several methods have been used: Texture analysis, Principal Components Analysis (PCA) and Cluster Analysis
Fichier non déposé

Dates et versions

hal-02594020 , version 1 (15-05-2020)

Identifiants

Citer

A. Melado, P. Barreiro, J. Ruiz-Cabello, M.E. Fernandez-Valle, A. Blanco, et al.. Multidimensional non supervised analysis (textural and spatial) in MRI tomography for watercore detection. VII Colloquium chemiometricum mediterraneum, 2010, Grenade, Spain. pp.4. ⟨hal-02594020⟩
10 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More