<![CDATA[Automatic identification of apple varieties is one of the challenges in the field of digital image processing, especially due to the similarity of visual characteristics between varieties and the influence of lighting conditions. This study aims to develop an apple variety classification system based on color feature extraction in the HSV (Hue, Saturation, Value) color space combined with Gray Level Co-occurrence Matrix (GLCM) texture features and classified using a Multilayer Perceptron (MLP) Artificial Neural Network. The research process begins with apple image segmentation using the Otsu thresholding method to separate objects from the background, followed by extraction of HSV color features and texture features in the form of contrast and energy. The obtained feature data is then normalized using StandardScaler and divided into training data of 80% and test data of 20%. The MLP model is trained with two hidden layers of 64 and 32 neurons, using the ReLU activation function and the Adam optimization algorithm with a maximum of 500 epochs. The test results show that the developed system is able to achieve a classification accuracy of 87.5% on the test data. These results indicate that the combination of HSV color features and GLCM texture classified using Backpropagation Neural Network is quite effective in identifying apple types, although there are still challenges in classes that have similar color characteristics.]]>
Copyrights © 2026
