Automatic non-destructive video estimation of maturation levels in Fuji apple (Malus Malus pumila) fruit in orchard based on colour (Vis) and spectral (NIR) data

Non-destructive estimates information on the desired properties of fruit without damaging them. The objective of this work is to present an algorithm for the automatic and non-destructive estimation of four maturity stages (unripe, half-ripe, ripe, or overripe) of Fuji apples (Malus Malus pumila) using both colour and spectral data from fruit. In order to extract spectral and colour data to train a proposed system, 170 samples of Fuji apples were collected. Colour and spectral features were extracted using a CR-400 Chroma Meter colorimeter and a custom set up. The second component of colour space and near infrared (NIR) spectrum data in wavelength ranges of 535–560 nm, 835–855 nm, and 950–975 nm, were used to train the proposed algorithm. A hybrid artificial neural network-simulated annealing algorithm (ANN-SA) was used for classification purposes. A total of 1000 iterations were conducted to evaluate the reliability of the classification process. Results demonstrated that after training the correction classification rate (CCR, accuracy) was, at the best state, 100% (test set) using both colour and spectral data. The CCR of the four different classifiers were 93.27%, 99.62%, 98.55%, and 99.59%, for colour features, spectral data wavelength ranges of 535–560 nm, 835–855 nm, and 950–975 nm, respectively, over the test set. These results suggest that the proposed method is capable of the non-destructive estimation of different maturity stages of Fuji apple with a remarkable accuracy, in particular within the 535–560 nm wavelength range.