System measurement optimized for damages detection in fruit

To avoid economic losses due to fruit diseases, farmers need to control quality before harvesting and thus before the fruit reaches the consumer. In this paper, we present a proof of concept for damages detection in fruit with a minimum number of measurement points. By using the Grey Wolf optimizer, the number of measurement points drops from 12701 to 106 and we obtained 93% and 100% of accuracy. We also investigated the influence of sensitivity of the measurement system on the classifier.