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...

Full description

Saved in:
Bibliographic Details
Main Authors: Xueyu Huang, Renjie Pan, Jionghui Wang
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!
_version_ 1849393616961667072
author Xueyu Huang
Renjie Pan
Jionghui Wang
author_facet Xueyu Huang
Renjie Pan
Jionghui Wang
author_sort Xueyu Huang
collection DOAJ
description 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.
format Article
id doaj-art-95289a864f3947089c7dba37e3f5585f
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-95289a864f3947089c7dba37e3f5585f2025-08-20T03:40:22ZengIEEEIEEE Access2169-35362025-01-0113480074801810.1109/ACCESS.2025.355042310921646A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 ModelXueyu Huang0Renjie Pan1https://orcid.org/0009-0004-4643-4717Jionghui Wang2School of Software Engineering, Jiangxi University of Science and Technology, Nanchang, ChinaSchool of Software Engineering, Jiangxi University of Science and Technology, Nanchang, ChinaMinmetals Exploration and Development Company Ltd., Beijing, ChinaWith 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.https://ieeexplore.ieee.org/document/10921646/Inception-ResNet-v2graphite ore grade recognitionLeakyReLUglobal average pooling branchLDP-Convmodel restructure
spellingShingle Xueyu Huang
Renjie Pan
Jionghui Wang
A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
IEEE Access
Inception-ResNet-v2
graphite ore grade recognition
LeakyReLU
global average pooling branch
LDP-Conv
model restructure
title A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
title_full A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
title_fullStr A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
title_full_unstemmed A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
title_short A Graphite Ore Grade Recognition Method Based on Improved Inception-ResNet-v2 Model
title_sort graphite ore grade recognition method based on improved inception resnet v2 model
topic Inception-ResNet-v2
graphite ore grade recognition
LeakyReLU
global average pooling branch
LDP-Conv
model restructure
url https://ieeexplore.ieee.org/document/10921646/
work_keys_str_mv AT xueyuhuang agraphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model
AT renjiepan agraphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model
AT jionghuiwang agraphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model
AT xueyuhuang graphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model
AT renjiepan graphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model
AT jionghuiwang graphiteoregraderecognitionmethodbasedonimprovedinceptionresnetv2model