Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network
In the aspect of food quality measurement, the application of image analysis has emerged as a powerful and versatile tool, enabling a highly accurate and efficient automated recognition and the quality classification of visual data. This study examines the feasibility of employing an AI algorithm on...
Published in: | Processes |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/pr11102864 https://doaj.org/article/1066dd21b34445618eef697e1ec33a49 |
id |
ftdoajarticles:oai:doaj.org/article:1066dd21b34445618eef697e1ec33a49 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:1066dd21b34445618eef697e1ec33a49 2023-11-12T04:00:00+01:00 Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network Won Byong Yoon Timilehin Martins Oyinloye Jinho Kim 2023-09-01T00:00:00Z https://doi.org/10.3390/pr11102864 https://doaj.org/article/1066dd21b34445618eef697e1ec33a49 EN eng MDPI AG https://www.mdpi.com/2227-9717/11/10/2864 https://doaj.org/toc/2227-9717 doi:10.3390/pr11102864 2227-9717 https://doaj.org/article/1066dd21b34445618eef697e1ec33a49 Processes, Vol 11, Iss 2864, p 2864 (2023) surimi gel color auto machine learning Convolutional Neural Network image classification Chemical technology TP1-1185 Chemistry QD1-999 article 2023 ftdoajarticles https://doi.org/10.3390/pr11102864 2023-10-29T00:35:49Z In the aspect of food quality measurement, the application of image analysis has emerged as a powerful and versatile tool, enabling a highly accurate and efficient automated recognition and the quality classification of visual data. This study examines the feasibility of employing an AI algorithm on labeled images as a non-destructive method to classify surimi gels. Gels were made with different moisture (76–82%) and corn starch (5–16%) levels from Alaska pollock and Threadfin breams. In surimi gelation, interactions among surimi, starch, and moisture caused color and quality shifts. Color changes are indicative of structural and quality variations in surimi. Traditional color measuring techniques using colorimeter showed insignificant differences ( p < 0.05) in color values and whiteness among treatments. This complexity hindered effective grading, especially in intricate formulations. Despite insignificant color differences, they signify structural changes. The Convolutional Neural Network (CNN) predicts the visual impact of moisture and starch on gel attributes prepared with different surimi species. Automated machine learning assesses AI algorithms; and CNN’s 70:30 training/validation ratio involves 400–700 images per category. CNN’s architecture, including input, convolutional, normalization, Rectified Linear Unit (ReLU) activation, and max-pooling layers, detects subtle structural changes in treated images. Model test accuracies exceed 95%, validating CNN’s precision in species and moisture classification. It excels in starch concentrations, yielding > 90% accuracy. Average precision (>0.9395), recall (>0.8738), and F1-score (>0.8731) highlight CNN’s high performance. This study demonstrates CNN’s value in non-destructively classifying surimi gels with varying moisture and starch contents across species, and it provides a solid foundation for advancing our understanding of surimi production processes and their optimization in the pursuit of high-quality surimi products. Article in Journal/Newspaper alaska pollock Alaska Directory of Open Access Journals: DOAJ Articles Processes 11 10 2864 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
surimi gel color auto machine learning Convolutional Neural Network image classification Chemical technology TP1-1185 Chemistry QD1-999 |
spellingShingle |
surimi gel color auto machine learning Convolutional Neural Network image classification Chemical technology TP1-1185 Chemistry QD1-999 Won Byong Yoon Timilehin Martins Oyinloye Jinho Kim Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
topic_facet |
surimi gel color auto machine learning Convolutional Neural Network image classification Chemical technology TP1-1185 Chemistry QD1-999 |
description |
In the aspect of food quality measurement, the application of image analysis has emerged as a powerful and versatile tool, enabling a highly accurate and efficient automated recognition and the quality classification of visual data. This study examines the feasibility of employing an AI algorithm on labeled images as a non-destructive method to classify surimi gels. Gels were made with different moisture (76–82%) and corn starch (5–16%) levels from Alaska pollock and Threadfin breams. In surimi gelation, interactions among surimi, starch, and moisture caused color and quality shifts. Color changes are indicative of structural and quality variations in surimi. Traditional color measuring techniques using colorimeter showed insignificant differences ( p < 0.05) in color values and whiteness among treatments. This complexity hindered effective grading, especially in intricate formulations. Despite insignificant color differences, they signify structural changes. The Convolutional Neural Network (CNN) predicts the visual impact of moisture and starch on gel attributes prepared with different surimi species. Automated machine learning assesses AI algorithms; and CNN’s 70:30 training/validation ratio involves 400–700 images per category. CNN’s architecture, including input, convolutional, normalization, Rectified Linear Unit (ReLU) activation, and max-pooling layers, detects subtle structural changes in treated images. Model test accuracies exceed 95%, validating CNN’s precision in species and moisture classification. It excels in starch concentrations, yielding > 90% accuracy. Average precision (>0.9395), recall (>0.8738), and F1-score (>0.8731) highlight CNN’s high performance. This study demonstrates CNN’s value in non-destructively classifying surimi gels with varying moisture and starch contents across species, and it provides a solid foundation for advancing our understanding of surimi production processes and their optimization in the pursuit of high-quality surimi products. |
format |
Article in Journal/Newspaper |
author |
Won Byong Yoon Timilehin Martins Oyinloye Jinho Kim |
author_facet |
Won Byong Yoon Timilehin Martins Oyinloye Jinho Kim |
author_sort |
Won Byong Yoon |
title |
Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
title_short |
Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
title_full |
Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
title_fullStr |
Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
title_full_unstemmed |
Classification of Quality Characteristics of Surimi Gels from Different Species Using Images and Convolutional Neural Network |
title_sort |
classification of quality characteristics of surimi gels from different species using images and convolutional neural network |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/pr11102864 https://doaj.org/article/1066dd21b34445618eef697e1ec33a49 |
genre |
alaska pollock Alaska |
genre_facet |
alaska pollock Alaska |
op_source |
Processes, Vol 11, Iss 2864, p 2864 (2023) |
op_relation |
https://www.mdpi.com/2227-9717/11/10/2864 https://doaj.org/toc/2227-9717 doi:10.3390/pr11102864 2227-9717 https://doaj.org/article/1066dd21b34445618eef697e1ec33a49 |
op_doi |
https://doi.org/10.3390/pr11102864 |
container_title |
Processes |
container_volume |
11 |
container_issue |
10 |
container_start_page |
2864 |
_version_ |
1782341400473370624 |