Automatic labeling of fish species using deep learning across different classification strategies
Convolutional neural networks (CNNs) have revolutionized image recognition. Their ability to identify complex patterns, combined with learning transfer techniques, has proven effective in multiple fields, such as image classification. In this article we propose to apply a two-step methodology for im...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Computer Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2024.1326452/full |
| _version_ | 1797291685352308736 |
|---|---|
| author | Javier Jareño Guillermo Bárcena-González Jairo Castro-Gutiérrez Remedios Cabrera-Castro Pedro L. Galindo |
| author_facet | Javier Jareño Guillermo Bárcena-González Jairo Castro-Gutiérrez Remedios Cabrera-Castro Pedro L. Galindo |
| author_sort | Javier Jareño |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) have revolutionized image recognition. Their ability to identify complex patterns, combined with learning transfer techniques, has proven effective in multiple fields, such as image classification. In this article we propose to apply a two-step methodology for image classification tasks. First, apply transfer learning with the desired dataset, and subsequently, in a second stage, replace the classification layers by other alternative classification models. The whole methodology has been tested on a dataset collected at Conil de la Frontera fish market, in Southwest Spain, including 19 different fish species to be classified for fish auction market. The study was conducted in five steps: (i) collecting and preprocessing images included in the dataset, (ii) using transfer learning from 4 well-known CNNs (ResNet152V2, VGG16, EfficientNetV2L and Xception) for image classification to get initial models, (iii) apply fine-tuning to obtain final CNN models, (iv) substitute classification layer with 21 different classifiers obtaining multiple F1-scores for different training-test splits of the dataset for each model, and (v) apply post-hoc statistical analysis to compare their performances in terms of accuracy. Results indicate that combining the feature extraction capabilities of CNNs with other supervised classification algorithms, such as Support Vector Machines or Linear Discriminant Analysis is a simple and effective way to increase model performance. |
| first_indexed | 2024-03-07T19:40:22Z |
| format | Article |
| id | doaj.art-225ec01f326e4a0e823789f1ee0dcf97 |
| institution | Directory Open Access Journal |
| issn | 2624-9898 |
| language | English |
| last_indexed | 2024-03-07T19:40:22Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computer Science |
| spelling | doaj.art-225ec01f326e4a0e823789f1ee0dcf972024-02-29T05:34:41ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982024-02-01610.3389/fcomp.2024.13264521326452Automatic labeling of fish species using deep learning across different classification strategiesJavier Jareño0Guillermo Bárcena-González1Jairo Castro-Gutiérrez2Remedios Cabrera-Castro3Pedro L. Galindo4Computer Science Department, University of Cádiz, Cádiz, SpainComputer Science Department, University of Cádiz, Cádiz, SpainBiology Department, University of Cádiz, Cádiz, SpainBiology Department, University of Cádiz, Cádiz, SpainComputer Science Department, University of Cádiz, Cádiz, SpainConvolutional neural networks (CNNs) have revolutionized image recognition. Their ability to identify complex patterns, combined with learning transfer techniques, has proven effective in multiple fields, such as image classification. In this article we propose to apply a two-step methodology for image classification tasks. First, apply transfer learning with the desired dataset, and subsequently, in a second stage, replace the classification layers by other alternative classification models. The whole methodology has been tested on a dataset collected at Conil de la Frontera fish market, in Southwest Spain, including 19 different fish species to be classified for fish auction market. The study was conducted in five steps: (i) collecting and preprocessing images included in the dataset, (ii) using transfer learning from 4 well-known CNNs (ResNet152V2, VGG16, EfficientNetV2L and Xception) for image classification to get initial models, (iii) apply fine-tuning to obtain final CNN models, (iv) substitute classification layer with 21 different classifiers obtaining multiple F1-scores for different training-test splits of the dataset for each model, and (v) apply post-hoc statistical analysis to compare their performances in terms of accuracy. Results indicate that combining the feature extraction capabilities of CNNs with other supervised classification algorithms, such as Support Vector Machines or Linear Discriminant Analysis is a simple and effective way to increase model performance.https://www.frontiersin.org/articles/10.3389/fcomp.2024.1326452/fullsupervised learningclassificationfish speciesSVMLDAdeep learning |
| spellingShingle | Javier Jareño Guillermo Bárcena-González Jairo Castro-Gutiérrez Remedios Cabrera-Castro Pedro L. Galindo Automatic labeling of fish species using deep learning across different classification strategies Frontiers in Computer Science supervised learning classification fish species SVM LDA deep learning |
| title | Automatic labeling of fish species using deep learning across different classification strategies |
| title_full | Automatic labeling of fish species using deep learning across different classification strategies |
| title_fullStr | Automatic labeling of fish species using deep learning across different classification strategies |
| title_full_unstemmed | Automatic labeling of fish species using deep learning across different classification strategies |
| title_short | Automatic labeling of fish species using deep learning across different classification strategies |
| title_sort | automatic labeling of fish species using deep learning across different classification strategies |
| topic | supervised learning classification fish species SVM LDA deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fcomp.2024.1326452/full |
| work_keys_str_mv | AT javierjareno automaticlabelingoffishspeciesusingdeeplearningacrossdifferentclassificationstrategies AT guillermobarcenagonzalez automaticlabelingoffishspeciesusingdeeplearningacrossdifferentclassificationstrategies AT jairocastrogutierrez automaticlabelingoffishspeciesusingdeeplearningacrossdifferentclassificationstrategies AT remedioscabreracastro automaticlabelingoffishspeciesusingdeeplearningacrossdifferentclassificationstrategies AT pedrolgalindo automaticlabelingoffishspeciesusingdeeplearningacrossdifferentclassificationstrategies |