The classification of fresh fruits according to their visual ripeness is typically a subjective and tedious task; consequently, there is growing interest in the use of non-contact techniques to automate this process. Machine learning techniques such as artificial neural networks, support vector machines, decision trees, and K-nearest neighbor algorithms have been successfully applied for classification problems in the literature, particularly for images of fruit. However, the particularities of each classification problem make it difficult, if not impossible, to select a general technique that is applicable to all types of fruit. In this paper, combinations of four machine learning techniques and three color spaces (RGB, HSV, and L*a*b*) were evaluated with regard to their ability to classify Cape gooseberry fruits. To this end, 925 Cape gooseberry fruit samples were collected, and each fruit was manually classified into one of seven different classes according to its level of ripeness. The color values of each fruit image in the three color spaces and their corresponding ripening stages were organized for training and validation following a 5-fold cross-validation strategy in an iterative process repeated 100 times. According to the results, the classification of Cape gooseberry fruits by their ripeness level was sensitive to both the color space and the classification technique used. The models based on the L*a*b* color space and the SVM classifier showed the highest f-measure regardless of the color space, and the principal component analysis combination of color spaces improved the performance of the models at the expense of an increased complexity.

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time.

This paper explores five multivariate techniques for information fusion on sorting the visual ripeness of Cape gooseberry fruits (principal component analysis, linear discriminant analysis, independent component analysis, eigenvector centrality feature selection, and multi-cluster feature selection.) These techniques are applied to the concatenated channels corresponding to red, green, and blue (RGB), hue, saturation, value (HSV), and lightness, red/green value, and blue/yellow value (L*a*b) color spaces (9 features in total). Machine learning techniques have been reported for sorting the Cape gooseberry fruits’ ripeness. Classifiers such as neural networks, support vector machines, and nearest neighbors discriminate on fruit samples using different color spaces. Despite the color spaces being equivalent up to a transformation, a few classifiers enable better performances due to differences in the pixel distribution of samples. Experimental results show that selection and combination of color channels allow classifiers to reach similar levels of accuracy; however, combination methods still require higher computational complexity. The highest level of accuracy was obtained using the seven-dimensional principal component analysis feature space.

In this work, the use of expert systems and hyperspectral imaging in the determination of coffee rust infection was evaluated. Three classifiers were trained using spectral profiles from different stages of infection, and the classifier based on a support vector machine provided the best performance. When this classifier was compared to visual analysis, statistically significant differences were observed, and the highest sensitivity of the selected classifier was found at early stages of infection.