A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction
2024
Mishra, Puneet | Albano-Gaglio, Michela | Font-i-Furnols, Maria | Indústries Alimentàries | Qualitat i Tecnologia Alimentària
This study demonstrates a new approach to process hyperspectral images where both the contextual spatial information as well as the spectral information are used to predict sample properties. The deep contextual spatial information is extracted using the deep feature extraction from pretrained resnet-18 deep learning architecture, while the spectral information was readily available as the average pixel values. To fuse the information in a complementary way, a multiblock modeling approach called sequential orthogonalized partial least squares was used. The sequential model guarantees that the information learned is complementary from spatial and spectral domains. The potential of the approach is demonstrated to predict several physical and chemical properties in pork bellies.
Afficher plus [+] Moins [-]he authors would like to thank the researchers Begonya Marcos (IRTA) and Juan Florencio Tejeda (UEX) and the IRTA technicians Albert Brun, Agustí Quintana, Albert Rossell, Adrià Pacreu, Cristina Canals, and Joel González, for their help in the execution of the project. Thanks also given to José M. Martínez for their contribution in the analysis of fatty acids. The authors thank the Spanish National Institute of Agricultural Research (INIA) for the scholarship to Michela Albano-Gaglio (PRE2019-089669). This work was partly funded by the Spanish Ministry of Science and Innovation, project number RTI2018-096993-B-I00. The CERCA programme from the Generalitat de Catalunya is also acknowledged.
Afficher plus [+] Moins [-]info:eu-repo/semantics/publishedVersion
Afficher plus [+] Moins [-]Informations bibliographiques
Cette notice bibliographique a été fournie par Institut de Recerca i Tecnologia Agroalimentàries
Découvrez la collection de ce fournisseur de données dans AGRIS