Microwave sensor for tangerine classification based on coupled-patch antennas

This paper deals with a microwave sensor for classifying tangerines by flavour using coupled-patch antennas. The operating frequency of the antennas is 2.45 GHz. The sensor determines the flavour of each tangerine by measuring the magnitudes of coupled signals of the antennas with the tangerine fruit at the centre. The sorting is carried out using an artificial neural network implemented on a field programmable gate array. The classification performance of the sensor is 95% accurate, so it has potential for use in sorting tangerines by flavour. In addition, the system uncertainty is analysed to determine optimal operating conditions.