Design and manufacturing of artificial intelligence basedhazelnut types classification machine

Hazelnuts are of considerable importance, particularly in the food and agriculture industries, where the utilization of different varieties in various applications directly influences processing efficiency and product quality. Currently, however, there are no machines designed specifically to differentiate hazelnut varieties based on their shell characteristics; instead, existing machinery predominantly separates hazelnuts into categories such as full, empty, or broken. The ability to distinguish between hazelnut varieties is essential for optimizing processing workflows and improving the quality of the final product. In this context, the proposed study seeks to classify hazelnuts by analyzing their physical attributes, including color and texture, to determine their suitability for specific applications. After capturing images of hazelnut shells on the conveyor belt, preliminary image processing steps such as cropping, background removal, and measurement standardization were performed. Subsequently, feature extraction was carried out on the processed images. To ensure high classification accuracy, the feature extraction methods were designed to capture variations in size, color, and texture. Based on the classification results, a vacuum-based system was developed to separate the three types of hazelnuts on a conveyor belt. Sliding plates aligned with the slots on the belt are positioned by stepper motors, and then the hazelnuts are released into the designated chamber through a vacuuming process. The techniques employed for feature extraction included Dimension, Color, Haralick, Local Binary Patterns and Histogram of Oriented Gradients (HOG). These extracted features were then applied to various classifiers, including K-Nearest Neighbor, Decision Tree, Support Vector Machine, Feedforward Neural Networks, Recurrent Neural Networks, and Cascade Forward Neural Network. The classification results revealed that the Cascade Forward Neural Network classifier outperformed the others, achieving an accuracy rate of %92. In conclusion, the machine learning-based system developed for classifying hazelnuts by their outer shell is poised to significantly enhance quality in industrial processes while introducing a major innovation by elevating efficiency to a new level.