A diet high in fruit (and vegetables) can reduce the risk of developing heart disease, cancer, inflammation and diabetes. But the fruit needs to be fresh for a sustainable, healthy diet. Several techniques are being used to detect ripening fruit.
One company, smartGAS in Germany, has two different sensors to detect the ethylene (C2H4) that is released into ambient air by almost all fruits. When present in the right concentration, ethylene contributes substantially to fruit ripening that can occur during transportation or in storage.
Image source: smartGAS.
Based on the principle of non-dispersive infrared (NDIR) measuring technology, the FLOWEVO series combines measuring precision with compact design and simple handling. The F3-032205-05000 can detect 2000 ppm of C2H4. For detecting even lower concentration rates, the company’s PAS sensor can detect 1000 ppm and as low as 200 ppm in two different product offerings. The photoacoustic spectroscopy (PAS) technique used in these sensors provides one of the most sensitive measuring methods for detecting gases.
Vision has been a widely researched technology for analyzing fruit. However, many challenges remain. To implement robotic harvesting of tomatoes, automatic recognition of ripening tomatoes must occur. One group of researchers combined a Live Metal Oxide Semiconductor (Live MOS; 17.3 × 13.0 mm size) camera, the E-P3, from Olympus to take images of tomato fruit with a newly developed algorithm. The automatic algorithm for recognizing the ripening tomatoes used an improved method that combined multiple features, feature analysis and selection, a weighted relevance vector machine (RVM) classifier and a bi-layer classification strategy. Their test results provided a success rate of 94.90% with the identification process taking 2.94 s on the average. While this may be suitable for implementing robotic tomato harvesting, the authors plan further research to focus on fault identification during the second classification step and increase the efficiency of the proposed algorithm.
Another group of researchers studied the capacitive property of bananas to develop a rapid and non-invasive ripening assessment method to control their ripening treatment. The parallel plate capacitor sensor system operating at 1 MHz showed that permittivity at this frequency changed from 1.7433 for green-ripe bananas to 1.6431 for fully ripe ones after a five-day period providing an encouraging measurement of quality. However, further research is required to move towards a production technique.