Robust coal granularity estimation via deep neural network with an image enhancement layer

Accurate granularity estimation of ore images is vital in automatic geometric parameter detecting and composition analysis of ore dressing progress. Machine learning based methods have been widely used in multi-scenario ore granularity estimation. However, the adhesion of coal particles in the image...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi Chen, Hua-Yi Feng, Jia-Le Wang
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2021.2015290
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763925709553664
author Xi Chen
Hua-Yi Feng
Jia-Le Wang
author_facet Xi Chen
Hua-Yi Feng
Jia-Le Wang
author_sort Xi Chen
collection DOAJ
description Accurate granularity estimation of ore images is vital in automatic geometric parameter detecting and composition analysis of ore dressing progress. Machine learning based methods have been widely used in multi-scenario ore granularity estimation. However, the adhesion of coal particles in the images usually results in lower segmentation accuracy. Because much powdery coal fills between blocky ones, making edge contrast between them is not distinct. Currently, the coal granularity estimation is still carried out empirical in nature. We propose a novel method for coal granularity estimation based on a deep neural network called Res-SSD to deal with the problem. Then, to further improve the detection performance, we propose an image enhancement layer for Res-SSD. Since the dust generated during production and transportation will seriously damage the image quality, we first propose an image denoising method based on dust modelling. By investigating imaging characteristics of coal, we second propose the optical balance transformation(OBT), by which the distinguishability of coal in dark zones can be increased. Meanwhile, OBT can also suppress overexposed spots in images. Experimental results show that the proposed method is better than classic and state-of-the-art methods in terms of accuracy while achieving a comparable speed performance.
format Article
id doaj-art-bfac1dfe8d2b4655a365b86aedbc192c
institution DOAJ
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-bfac1dfe8d2b4655a365b86aedbc192c2025-08-20T03:05:17ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134147249110.1080/09540091.2021.20152902015290Robust coal granularity estimation via deep neural network with an image enhancement layerXi Chen0Hua-Yi Feng1Jia-Le Wang2Key Lab of Civil Aircraft Airworthiness TechnologyTianjin Meiteng Technology CO., LTDTianjin Meiteng Technology CO., LTDAccurate granularity estimation of ore images is vital in automatic geometric parameter detecting and composition analysis of ore dressing progress. Machine learning based methods have been widely used in multi-scenario ore granularity estimation. However, the adhesion of coal particles in the images usually results in lower segmentation accuracy. Because much powdery coal fills between blocky ones, making edge contrast between them is not distinct. Currently, the coal granularity estimation is still carried out empirical in nature. We propose a novel method for coal granularity estimation based on a deep neural network called Res-SSD to deal with the problem. Then, to further improve the detection performance, we propose an image enhancement layer for Res-SSD. Since the dust generated during production and transportation will seriously damage the image quality, we first propose an image denoising method based on dust modelling. By investigating imaging characteristics of coal, we second propose the optical balance transformation(OBT), by which the distinguishability of coal in dark zones can be increased. Meanwhile, OBT can also suppress overexposed spots in images. Experimental results show that the proposed method is better than classic and state-of-the-art methods in terms of accuracy while achieving a comparable speed performance.http://dx.doi.org/10.1080/09540091.2021.2015290coal granularity estimationdeep neural networkdust removalimage enhancementindustrial and mining intelligence
spellingShingle Xi Chen
Hua-Yi Feng
Jia-Le Wang
Robust coal granularity estimation via deep neural network with an image enhancement layer
Connection Science
coal granularity estimation
deep neural network
dust removal
image enhancement
industrial and mining intelligence
title Robust coal granularity estimation via deep neural network with an image enhancement layer
title_full Robust coal granularity estimation via deep neural network with an image enhancement layer
title_fullStr Robust coal granularity estimation via deep neural network with an image enhancement layer
title_full_unstemmed Robust coal granularity estimation via deep neural network with an image enhancement layer
title_short Robust coal granularity estimation via deep neural network with an image enhancement layer
title_sort robust coal granularity estimation via deep neural network with an image enhancement layer
topic coal granularity estimation
deep neural network
dust removal
image enhancement
industrial and mining intelligence
url http://dx.doi.org/10.1080/09540091.2021.2015290
work_keys_str_mv AT xichen robustcoalgranularityestimationviadeepneuralnetworkwithanimageenhancementlayer
AT huayifeng robustcoalgranularityestimationviadeepneuralnetworkwithanimageenhancementlayer
AT jialewang robustcoalgranularityestimationviadeepneuralnetworkwithanimageenhancementlayer