The QUALISPECTRA project (2024-2026) aims to improve food safety through innovative technology: hyperspectral imaging combined with advanced Machine Learning algorithms. The objective is clear, i.e. to offer rapid, reliable, non-destructive testing capable of detecting disease or contaminants in agri-food products at an early stage.
Advanced technology
Unlike conventional imaging, hyperspectral imaging simultaneously captures spatial information (shapes, textures) and spectral information (chemical composition). Each pixel, therefore, contains a unique "signature" that enables a detailed analysis of agricultural and food products. When combined with artificial intelligence, this technique paves the way for accurate, near-instant diagnostics adapted to industrial constraints.
Two case studies illustrate this potential:
- fusarium detection in common wheat ears (also studied under the Phenet and Phenweat projects), enabling rapid identification of this fungal disease;
- flour mixture homogeneity quantification (using samples from the ValCerWal project), ensuring product quality and uniformity.
By reducing the need for destructive or time-consuming laboratory methods, QUALISPECTRA offers practical decision-making tools for manufacturers.
A strategic Walloon cooperation partnership
The project is being carried out in collaboration with CETIC, a research centre specialising in data science. This cooperation partnership illustrates the desire to combine technological skills and scientific expertise to create a safer, more efficient Walloon agri-food chain.
Financing : Project subsidised by SPW's Win4Collective research programme, convention no. 2410108
