A Vision-based Cutting System for Fennel Postharvest Processing

In the last few years automated and intelligent systems have been increasingly adopted in agriculture in order to improve productivity and efficiency. Computer Vision plays a critical role in this field. This paper describes recent and current work at the Politecnico of Bari in collaboration with the University of Lecce in the field of automation of postharvest processes of vegetables with high market value and production rate. Specifically, a vision-based system is described for the automated cutting of harvested fennel. The functional design of the cutting mechanism is described, based on two asynchronous fourbar linkages, which allow to perform a double cut of the fennel in order to remove parts of the plant unfit for the market, i.e. root and leafy parts. The locations of the cutting lines along the plant are provided by a real-time vision-based module, which exploits intelligent color filtering. We call the visual algorithm the Fennel Visual Identification (FVI). Detailed experiments are described in order to asses the performances of the visual algorithms in terms of accuracy, repeatability and robustness to lighting conditions and noises. It is shown that the proposed system could be potentially applied to automate the cutting process of fennel in order to improve quality and efficiency.