A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
With the rapid advancement of technology, intelligent identification of graphite ore grade in graphite mines has emerged as an essential requirement. To address the variability and low timeliness of traditional manual methods and the limited accuracy of deep learning due to image complexity and feat...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10921646/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With the rapid advancement of technology, intelligent identification of graphite ore grade in graphite mines has emerged as an essential requirement. To address the variability and low timeliness of traditional manual methods and the limited accuracy of deep learning due to image complexity and feature similarity, we propose an improved Inception-ResNet-v2 model for graphite ore grade recognition. Key improvements include: 1) To enhance the extraction of global feature information from graphite mine data, a global average pooling branch is incorporated into the Inception-resnet architecture. 2) Incorporating a <inline-formula> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> convolutional layer at the tail of the model to control channel dimensions and employing the LeakyReLU activation function to address the limitations of the ReLU activation function. 3) Designing an LDP-Conv structure to replace certain <inline-formula> <tex-math notation="LaTeX">$3\times 3$ </tex-math></inline-formula> convolutions and incorporating a channel attention mechanism to improve feature capture. 4) Optimizing the Stem module to expand the early-stage receptive field and reconstructing the network architecture. Experiments on the self-made graphite ore dataset showed improvements of 2.77% in Accuracy, 2.96% in Precision, 2.85% in Recall, and 2.89% in F1 Score. The model also demonstrated enhanced attention to graphite ore features. Compared with some mainstream CNN algorithms, our method offers significant advantages in accuracy and robustness, making it highly suitable for graphite ore grade recognition. |
|---|---|
| ISSN: | 2169-3536 |