Recognition of flotation froth conditions with k-shot learning and convolutional neural networks

In this study, previous work on k-shot learning in flotation froth image analysis using small sets of froth images, is extended. As before, image synthesis is used to augment these data sets, but in addition, fine-tuning of convolutional neural networks, as well as smaller data sets with as few as 1...

Full description

Bibliographic Details
Main Authors: Liu, Xiu, Aldrich, Chris
Format: Journal Article
Published: ELSEVIER 2023
Online Access:http://hdl.handle.net/20.500.11937/97647
_version_ 1848766297843695616
author Liu, Xiu
Aldrich, Chris
author_facet Liu, Xiu
Aldrich, Chris
author_sort Liu, Xiu
building Curtin Institutional Repository
collection Online Access
description In this study, previous work on k-shot learning in flotation froth image analysis using small sets of froth images, is extended. As before, image synthesis is used to augment these data sets, but in addition, fine-tuning of convolutional neural networks, as well as smaller data sets with as few as 10 samples per class are considered. Two convolutional neural network models, namely AlexNet and GoogLeNet, were compared and the latter demonstrated better performance generally. Both performed better than a traditional approach based on the use of image features derived from local binary patterns. Fine-tuning of the convolutional neural networks markedly improved their performance compared to pure transfer learning without fine-tuning. Moreover, a case study with platinum froth images showed that as few as only 10–30 real images per class are needed to achieve reasonably good classification performance, i.e. the ability to recognize four different classes of froths with an accuracy of 63%–84%, if AlexNet or GoogLeNet with fine-tuning is used. Using 100 real images per class with a fine-tuned GoogLeNet resulted in predictive accuracy approaching 92%. These results are comparable to those achievable with traditional approaches to feature extraction based on training data sets up to two orders of magnitude larger.
first_indexed 2025-11-14T11:48:55Z
format Journal Article
id curtin-20.500.11937-97647
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:48:55Z
publishDate 2023
publisher ELSEVIER
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-976472025-04-30T00:44:09Z Recognition of flotation froth conditions with k-shot learning and convolutional neural networks Liu, Xiu Aldrich, Chris In this study, previous work on k-shot learning in flotation froth image analysis using small sets of froth images, is extended. As before, image synthesis is used to augment these data sets, but in addition, fine-tuning of convolutional neural networks, as well as smaller data sets with as few as 10 samples per class are considered. Two convolutional neural network models, namely AlexNet and GoogLeNet, were compared and the latter demonstrated better performance generally. Both performed better than a traditional approach based on the use of image features derived from local binary patterns. Fine-tuning of the convolutional neural networks markedly improved their performance compared to pure transfer learning without fine-tuning. Moreover, a case study with platinum froth images showed that as few as only 10–30 real images per class are needed to achieve reasonably good classification performance, i.e. the ability to recognize four different classes of froths with an accuracy of 63%–84%, if AlexNet or GoogLeNet with fine-tuning is used. Using 100 real images per class with a fine-tuned GoogLeNet resulted in predictive accuracy approaching 92%. These results are comparable to those achievable with traditional approaches to feature extraction based on training data sets up to two orders of magnitude larger. 2023 Journal Article http://hdl.handle.net/20.500.11937/97647 10.1016/j.jprocont.2023.103004 ELSEVIER fulltext
spellingShingle Liu, Xiu
Aldrich, Chris
Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title_full Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title_fullStr Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title_full_unstemmed Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title_short Recognition of flotation froth conditions with k-shot learning and convolutional neural networks
title_sort recognition of flotation froth conditions with k-shot learning and convolutional neural networks
url http://hdl.handle.net/20.500.11937/97647