Classification of Fusarium-infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: a comparative analysis

• DOI: 10.1007/s00217-018-3059-7
• Publication Date: 2018-03-16T07:25:59Z
• Authors: Ewa Ropelewska; Piotr Zapotoczny
• Keywords: 2. Zero hunger; 0404 agricultural biotechnology; 04 agricultural and veterinary sciences

Wheat infections caused by fungi of the genus Fusarium decrease yields and have serious economic consequences. The produced mycotoxins harmful effects on human animal health. aim this study was to develop classification models based selected textural parameters distinguish between infected healthy wheat kernels. accuracy kernels positioned ventral side determined at 78–100% in model from hyperspectral images, 95–100% images generated a flatbed scanner. Kernels dorsal were correctly classified 78–98% 92–100% colour images. In combining sides kernels, reached 76–98% 94–100% imaging technique—flatbed scanner provided higher results. results will contribute further research aiming for determination fungal chemotypes and/or species features