Non-Invasive Optoelectronic System for Color-Change Detection in Oranges to Predict Ripening by Using Artificial Neural Networks

The use of sensors to detect or measure ripening changes in fruit is a growing area of interest to the scientific community. Colorimeters are commonly employed for color and shade identification; however, their usage to measure the color parameters of fruit rinds based on image analysis can be expensive. This article presents a non-invasive and low-cost optoelectronic system for detecting color changes in oranges to predict the ripening stage. The system utilises a 1 W white LED as a light source, an RGB photodiode array, and two plastic optical fibres bundled in parallel to form the head of an extrinsic sensor. A microcontroller is employed for model integration and data acquisition. The evolution of the skin color of the fruit was monitored until over-ripeness was evident. The sensor was designed to detect the color changes; the CIE L*a*b* color difference between the optoelectronic device results and those obtained by colorimetry was 2.6–4.5. To predict the ideal conditions for fruit handling and determine the maturity level, a multilevel perceptron ANN was trained, achieving an accuracy of 96.4%. In addition, an overall precision of 96.6% was achieved when classifying fruit into three maturity categories (under-ripe, ripe, and over-ripe), and the error was 3.4%. The combination of the optoelectronic device and ANN improves considerably this fruit color classification accuracy, can facilitate the determination of the optimal time for consumption, and optimize the postharvest process efficiency.