Image Classification Algorithm for Graphite Ore Carbon Grade Based on Multi-scale Feature Fusion

Based on the tedious process of using a carbon-sulfur analyzer to detect the carbon grade of graphite in graphite mining production, this paper proposes a graphite carbon grade image recognition and classification method based on multi-scale feature fusion. The experiment preprocesses the images and constructs a residual network model that combines pyramid convolution (PyConv) and spatial attention mechanism (SAM). This model enhances the extraction of both global and local feature information from graphite images. Transfer learning is introduced by using pre-trained weights to accelerate the convergence of the model, achieving efficient and accurate recognition and classification of graphite carbon grade with an accuracy of 92.5%, surpassing traditional machine learning methods using single features. The experimental results demonstrate that the neural network model constructed in this paper effectively extracts texture and color features from graphite images, improving the accuracy of graphite image classification and recognition. The model exhibits good robustness and provides valuable insights for practical graphite mining production.