Froth image analysis by use of transfer learning and convolutional neural networks

Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a d...

Full description

Bibliographic Details
Main Authors: Fu, Y., Aldrich, Chris
Format: Journal Article
Published: Elsevier 2018
Online Access:http://hdl.handle.net/20.500.11937/68118
_version_ 1848761747846987776
author Fu, Y.
Aldrich, Chris
author_facet Fu, Y.
Aldrich, Chris
author_sort Fu, Y.
building Curtin Institutional Repository
collection Online Access
description Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a database of images of common objects was used as is to extract features from flotation froth images. These features could subsequently be used to predict the conditions or performance of the flotation systems. Two case studies are considered. In the first, froth regimes in an industrial flotation plant could be identified significantly more reliably with the features generated by AlexNet than with previous state-of-the-art approaches, such as wavelets, grey level co-occurrence matrices or local binary patterns. In the second case study, the arsenic concentration in the batch flotation of realgar-orpiment-quartz mixtures could be predicted more accurately than was possible with features extracted by wavelets, grey level co-occurrence matrices, local binary patterns or by use of colour. These results suggest that feature extraction with convolutional neural networks trained on complex data sets from other domains can serve as more reliable methods than previous state-of-the-art approaches to froth image analysis.
first_indexed 2025-11-14T10:36:36Z
format Journal Article
id curtin-20.500.11937-68118
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:36:36Z
publishDate 2018
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-681182018-10-11T01:00:40Z Froth image analysis by use of transfer learning and convolutional neural networks Fu, Y. Aldrich, Chris Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a database of images of common objects was used as is to extract features from flotation froth images. These features could subsequently be used to predict the conditions or performance of the flotation systems. Two case studies are considered. In the first, froth regimes in an industrial flotation plant could be identified significantly more reliably with the features generated by AlexNet than with previous state-of-the-art approaches, such as wavelets, grey level co-occurrence matrices or local binary patterns. In the second case study, the arsenic concentration in the batch flotation of realgar-orpiment-quartz mixtures could be predicted more accurately than was possible with features extracted by wavelets, grey level co-occurrence matrices, local binary patterns or by use of colour. These results suggest that feature extraction with convolutional neural networks trained on complex data sets from other domains can serve as more reliable methods than previous state-of-the-art approaches to froth image analysis. 2018 Journal Article http://hdl.handle.net/20.500.11937/68118 10.1016/j.mineng.2017.10.005 Elsevier restricted
spellingShingle Fu, Y.
Aldrich, Chris
Froth image analysis by use of transfer learning and convolutional neural networks
title Froth image analysis by use of transfer learning and convolutional neural networks
title_full Froth image analysis by use of transfer learning and convolutional neural networks
title_fullStr Froth image analysis by use of transfer learning and convolutional neural networks
title_full_unstemmed Froth image analysis by use of transfer learning and convolutional neural networks
title_short Froth image analysis by use of transfer learning and convolutional neural networks
title_sort froth image analysis by use of transfer learning and convolutional neural networks
url http://hdl.handle.net/20.500.11937/68118