Development of AI Based Computer Vision Scrap Sorting System for Aluminium Alloy Scrap

The development of improved sorting systems for aluminium alloy scrap is required due to the growing need for effective recycling procedures. Using state-of-the-art feature extraction techniques and machine learning algorithms, this study offers an AI-based computer vision scrap sorting system that accurately classifies aluminium alloy scrap. To be more specific, we use convolutional neural networks (CNN) to take use of deep learning capabilities in addition to scale-invariant feature transforms (SIFT) and the Histogram of Oriented Gradients (HOG) for robust feature extraction. Artificial Neural Network (ANN) and Support Vector Machine (SVM) are two different models that are used to tackle the classification job. A large dataset of photos of aluminium alloy scrap is used to train and refine these models, guaranteeing strong classification accuracy and robustness. Our research results demonstrate that the integrated system can detect various scrap types with more than 90 percent accuracy, indicating its potential to improve recycling efficiency in industrial applications. By encouraging the efficient recovery of precious materials, the suggested approach not only expedites the sorting procedure but also supports sustainable resource management.