A Wavelet Enhanced Deep Learning Model for Mineral Image Classification: WFeedNet

Abstract

The classification of minerals is of critical importance in many fields such as geology, mining, environmental engineering, and materials engineering. Accurate mineral identification directly impacts the efficiency of mineral exploration, ore enrichment, and industrial production processes. However, traditional identification methods performed in a laboratory setting (e.g., XRD, XRF, SEM-EDS, etc.) are costly, time-consuming, and dependent on expert knowledge. With the rapid advancements in artificial intelligence, deep learning-based image classification techniques, thanks to their ability to learn complex visual patterns automatically, have become powerful alternatives to traditional methods. In this study, a novel deep learning model called WFeedNet is proposed for the automatic classification of mineral images. The proposed model integrates both spatial and frequency domain information simultaneously by feeding the low-frequency components (LL) obtained from the multi-level wavelet transform (DWT) into the network via feed-forward blocks. Furthermore, the spatial and channel attention mechanisms integrated into the model ensure that feature maps are made more meaningful. Experimental results obtained from a unique dataset containing 1,474 mineral images demonstrate that the model achieved an accuracy of 94.8% without using any pretrained weights. The findings indicate that WFeedNet achieves higher classification success compared to traditional pretrained CNN and ViT-based models.