This project has the aim to reduce food spoilage by developing autonomous and flexible quality-assessment systems. Using state-of-the-art technologies in machine learning, we will develop methods that learn to translate raw sensor information into quality aspects of fresh produce. The system can be trained from a number of examples, which can be presented to the system by the food expert. We will focus on three types of sensor data; NIR spectra, RGB images and hyperspectral images. The first holds spectral information, the second spatial information and the third spectral and spatial information combined. The developed methods will be tested on a number of case studies; vine tomatoes, pears, apples and strawberries.
|Effective start/end date||1/01/16 → 31/12/18|