Abstract: Challenges such as low accuracy,limited adaptability,and a lack of portability in the field of mineral recognition were addressed through the proposal of an intelligent mineral recognition model ( CA-MobileNet V3) based on the improved MobileNet. For research purposes,a collection of 19 minerals was compiled from images sourced from mindat. org and self-captured images. The images,following data enhancement procedures,were categorized into training,validation,and test sets in an 8 ∶1 ∶1 ratio. To enhance the feature extraction capabilities,the original SE attention mechanism in the lightweight MobileNet V3 model was replaced by the coordination attention mechanism. The aim of this alteration was to elevate mineral recognition accuracy. Subsequently,pre-training using transfer learning was employed on the CA-MobileNet V3 model to expedite convergence,enhance generalization,and mitigate overfitting. During training,a comparison of the performance of CA-MobileNet V3 was made with other models,including mobilenet v3,MobileNet V3,ShuffleNet V2,and EfficientNet V2. The results revealed notable advantages in terms of convergence speed for all transfer models. Particularly,the CA-MobileNet V3 model achieved TOP1-accuracy,TOP2-accuracy,and f1-score values of 93. 90%,98. 58%,and 93. 89%,respectively,showcasing superior performance compared to other models. Furthermore,this lightweight model boasted a compact size of only 4. 61 MB. To further validate the model′s effectiveness,t-SNE visual analysis was employed,providing a comparative assessment of the recognition effects among different models.

Key words: mineral classification,transfer learning,lightweight model,coordinate attention mechanism,t-SNE