@article {868, title = {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}, journal = {Biosystems Engineering}, volume = {195}, year = {2020}, pages = {136{\textendash}151}, abstract = {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{\textendash}560 nm, 835{\textendash}855 nm, and 950{\textendash}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{\textendash}560 nm, 835{\textendash}855 nm, and 950{\textendash}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{\textendash}560 nm wavelength range.}, doi = {https://doi.org/10.1016/j.biosystemseng.2020.04.015}, url = {https://www.sciencedirect.com/science/article/pii/S1537511020301148}, author = {Pourdarbani, Razieh and Sabzi, Sajad and Kalantari, Davood and Karimzadeh, Rouhollah and Ilbeygi, Elham and J I Arribas} } @article {864, title = {A Computer Vision System Based on Majority-Voting Ensemble Neural Network for the Automatic Classification of Three Chickpea Varieties}, journal = {Foods}, volume = {9}, year = {2020}, pages = {113}, abstract = {Since different varieties of crops have specific applications, it is therefore important to properly identify each cultivar, in order to avoid fake varieties being sold as genuine, i.e., fraud. Despite that properly trained human experts might accurately identify and classify crop varieties, computer vision systems are needed since conditions such as fatigue, reproducibility, and so on, can influence the expert{\textquoteright}s judgment and assessment. Chickpea (Cicer arietinum L.) is an important legume at the world-level and has several varieties. Three chickpea varieties with a rather similar visual appearance were studied here: Adel, Arman, and Azad chickpeas. The purpose of this paper is to present a computer vision system for the automatic classification of those chickpea varieties. First, segmentation was performed using an Hue Saturation Intensity (HSI) color space threshold. Next, color and textural (from the gray level co-occurrence matrix, GLCM) properties (features) were extracted from the chickpea sample images. Then, using the hybrid artificial neural network-cultural algorithm (ANN-CA), the sub-optimal combination of the five most effective properties (mean of the RGB color space components, mean of the HSI color space components, entropy of GLCM matrix at 90{\textdegree}, standard deviation of GLCM matrix at 0{\textdegree}, and mean third component in YCbCr color space) were selected as discriminant features. Finally, an ANN-PSO/ACO/HS majority voting (MV) ensemble methodology merging three different classifier outputs, namely the hybrid artificial neural network-particle swarm optimization (ANN-PSO), hybrid artificial neural network-ant colony optimization (ANN-ACO), and hybrid artificial neural network-harmonic search (ANN-HS), was used. Results showed that the ensemble ANN-PSO/ACO/HS-MV classifier approach reached an average classification accuracy of 99.10 {\textpm} 0.75\% over the test set, after averaging 1000 random iterations.}, doi = {https://doi.org/10.3390/foods9020113}, url = {https://www.mdpi.com/2304-8158/9/2/113}, author = {Pourdarbani, Razieh and Sabzi, Sajad and Kalantari, Davood and Hern{\'a}ndez-Hern{\'a}ndez, Jos{\'e} Luis and J I Arribas} } @article {865, title = {A Computer Vision System for the Automatic Classification of Five Varieties of Tree Leaf Images}, journal = {Computers}, volume = {9}, year = {2020}, pages = {6}, abstract = {A computer vision system for automatic recognition and classification of five varieties of plant leaves under controlled laboratory imaging conditions, comprising: 1{\textendash}Cydonia oblonga (quince), 2{\textendash}Eucalyptus camaldulensis dehn (river red gum), 3{\textendash}Malus pumila (apple), 4{\textendash}Pistacia atlantica (mt. Atlas mastic tree) and 5{\textendash}Prunus armeniaca (apricot), is proposed. 516 tree leaves images were taken and 285 features computed from each object including shape features, color features, texture features based on the gray level co-occurrence matrix, texture descriptors based on histogram and moment invariants. Seven discriminant features were selected and input for classification purposes using three classifiers: hybrid artificial neural network{\textendash}ant bee colony (ANN{\textendash}ABC), hybrid artificial neural network{\textendash}biogeography based optimization (ANN{\textendash}BBO) and Fisher linear discriminant analysis (LDA). Mean correct classification rates (CCR), resulted in 94.04\%, 89.23\%, and 93.99\%, for hybrid ANN{\textendash}ABC; hybrid ANN{\textendash}BBO; and LDA classifiers, respectively. Best classifier mean area under curve (AUC), mean sensitivity, and mean specificity, were computed for the five tree varieties under study, resulting in: 1{\textendash}Cydonia oblonga (quince) 0.991 (ANN{\textendash}ABC), 95.89\% (ANN{\textendash}ABC), 95.91\% (ANN{\textendash}ABC); 2{\textendash}Eucalyptus camaldulensis dehn (river red gum) 1.00 (LDA), 100\% (LDA), 100\% (LDA); 3{\textendash}Malus pumila (apple) 0.996 (LDA), 96.63\% (LDA), 94.99\% (LDA); 4{\textendash}Pistacia atlantica (mt. Atlas mastic tree) 0.979 (LDA), 91.71\% (LDA), 82.57\% (LDA); and 5{\textendash}Prunus armeniaca (apricot) 0.994 (LDA), 88.67\% (LDA), 94.65\% (LDA), respectively.}, doi = {https://doi.org/10.3390/computers9010006}, url = {https://www.mdpi.com/2073-431X/9/1/6}, author = {Sabzi, Sajad and Pourdarbani, Razieh and J I Arribas} } @article {870, title = {Non-destructive visible and short-wave near-infrared spectroscopic data estimation of various physicochemical properties of Fuji apple (Malus pumila) fruits at different maturation stages}, journal = {Chemometrics and Intelligent Laboratory Systems}, year = {2020}, pages = {104147}, abstract = {measurement of physicochemical properties of fruits during maturation stages can help having proper fruit management. Spectroscopy data analyzing and processing is among the commonly used methods that enable non-destructive accurate property estimation. Non-destructive linear (partial least squares regression, PSLR) and non-linear (artificial neural network, ANN) regression estimation of different physicochemical properties including firmness, acidity (pH) and starch content of 160 Fuji (Malus pumila) apple fruit samples at various maturity stages using visible and short wave near infrared (VSWIR) spectroscopic data in wavelength range 400{\textendash}1000 nm is investigated with the following steps: (1) harvesting 160 Fuji apple samples at four different maturation levels; (2) extracting spectral data in wavelength range of 400{\textendash}1000 nm; extracting physicochemical properties of tissue firmness, acidity (pH) and starch content; (3) pre-processing the reflectance spectra from each sample; (4) selecting effective wavelength values for each chemical property; and (5) non-destructive estimation of tissue firmness, acidity (pH) and starch content using spectral data range 400{\textendash}1000 nm and spectral data based on effective wavelengths, by means of an ensemble average artificial neural network method. Results show that the neural ensemble reached similar results when using VSWIR spectral data content (wavelength range) and fixed effective selected NIR wavelengths. Correlation coefficients estimating tissue firmness, acidity (pH), and starch content were 0.800, 0.919, and 0.940 for VSWIR spectral data (linear PLS regression), 0.826, 0.947, and 0.969 for VSWIR spectral data (non-linear ANN), 0.827, 0.946, and 0.969 for fixed NIR effective wavelengths (non-linear ANN). Mean {\textpm} std. Regression coefficients for tissue firmness, acidity (pH), and starch content were 0.717 {\textpm} 0.113, 0.786 {\textpm} 0.131, and 0.941 {\textpm} 0.013 for Vis/NIR spectral data (linear PLS regression), 0.849 {\textpm} 0.017, 0.930 {\textpm} 0.017, and 0.967 {\textpm} 0.007 for Vis/NIR spectral data (non-linear ANN), 0.852 {\textpm} 0.016, 0.929 {\textpm} 0.015, and 0.966 {\textpm} 0.006 for fixed effective NIR wavelengths (non-linear ANN).}, doi = {https://doi.org/10.1016/j.chemolab.2020.104147}, url = {https://www.sciencedirect.com/science/article/pii/S016974392030304X}, author = {Pourdarbani, Razieh and Sabzi, Sajad and Kalantari, Davood and J I Arribas} }