Managing fisheries requires regular monitoring and assessment of fish populations. Traditional methods of evaluating fish stocks, particularly their size, can be time-consuming, labor-intensive, and inaccurate. Recently, digital image processing (DIP) and machine learning (ML) have emerged as promising technologies to automate fish measurement and classification. In this study, we aim to develop deep learning models to predict, and classify shape and size of the fish using convolutional neural networks (CNNs) and DIP techniques. The study utilizes publicly available fish datasets and evaluates the efficiency of the proposed models using metrics such as precision, recall, and F1 score. The developed models utilize Python programming language with TensorFlow and Keras libraries. The regression component investigates the intricate relationship between various physical attributes of fish, uncovering the connections between body length, height, and weight. This analysis provides valuable insights into the correlations among these attributes, enhancing our understanding of fish characteristics. Simultaneously, the classification segment introduces an innovative approach to fish classification, incorporating shape and size attributes. Through a combination of classifiers and ensemble learning with stacking, exceptional accuracy is achieved in identifying distinct fish classes. This integration of techniques facilitates a more nuanced classification process, allowing for comprehensive categorization based on visual attributes. Our study establishes a robust framework for fish analysis and classification, Utilizing the combined strengths of digital image processing (DIP) and machine learning (ML). The developed models not only enhance the accuracy and efficiency of size classification but also contribute to the broader goal of sustainable fisheries management. This research sets a foundation for future endeavors in automating fish stock assessments, contributing to the advancement of fisheries science and management practices.
Published in | Computational Biology and Bioinformatics (Volume 11, Issue 2) |
DOI | 10.11648/j.cbb.20231102.12 |
Page(s) | 33-48 |
Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
Copyright |
Copyright © The Author(s), 2023. Published by Science Publishing Group |
Machine Learning, Convolutional Neural Networks (CNNs), Fish Measurement and Classification
[1] | Akhtar Jamil, M. A. S. (2023). "Stock Price Prediction in Response to US Dollar Exchange Rate Using Machine Learning Techniques." ResearchGate. |
[2] | al, A. e. (2021). "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions." journal of Big Data. |
[3] | Barbedo, J. G. A. (2022). "A Review on the Use of Computer Vision and Artificial Intelligence for Fish Recognition, Monitoring, and Management." Fishes. |
[4] | Boopathi, S., et al (2023). Advances in Artificial Intelligence for Image Processing: Techniques, Applications, and Optimization. Handbook of Research on Thrust Technologies’ Effect on Image Processing. e. a. Binay Kumar Pandey: 73-95. |
[5] | Dertat, A. "Applied Deep Learning - Part 4: Convolutional Neural Networks." From https://towardsdatascience.com/applied-deep-learning-part-4-convolutional-neural-networks-584bc134c1e2. |
[6] | Dey, R., Mathur, R (2023). "Ensemble Learning Method Using Stacking with Base Learner, A Comparison." Springer vol 727. |
[7] | Guduru Dhanush, N. K., Sandeep Kumar, Praveen Kumar Shukla (2023). "A comprehensive review of machine vision systems and artificial intelligence algorithms for the detection and harvesting of agricultural produce." Scientific African. |
[8] | Javad Ansarifar, L. W. S. V. A. (2021). An interaction regression model for crop yield prediction. |
[9] | Li, D., Wang, Q., Li, X., Niu, M., Wang, H., and Liu, C (2022). "Recent advances of machine vision technology in fish classification." ICES Journal of Marine Science: 263–284. |
[10] | Minggang Zhou, P. S., Hao Zhu and Yang Shen (2023). "In-Water Fish Body-Length Measurement System Based on Stereo Vision." sensors. |
[11] | Mouhafid M, C. Y. (2022). Diagnosing COVID-19 from CT Images Based on Ensemble Learning and Transfer Learning, HEBEI UNIVERSITY OF TECHNOLOGY. Master Degree. |
[12] | Muntean, M., Militaru, FD (2023). "Metrics for Evaluating Classification Algorithms." Springer vol 321. |
[13] | Mutasem K. Alsmadi, I. A. (2020). "A survey on fish classification techniques." Journal of King Saud University – Computer and Information Sciences. |
[14] | Onyutha, C. (2020). "From R-squared to coefficient of model accuracy for assessing "goodness-of-fits"." |
[15] | scikit-learn. "Neural network models (supervised)." from https://scikit-learn.org/stable/modules/neural_networks_supervised.html. |
[16] | Sumei Li, Y. L., Yongtian Han (2021). "Stereoscopic image quality assessment considering visual mechanism and multi-loss constraints." Journal of Visual Communication and Image Representation. |
[17] | Taylor, S. (2022). "Regression Analysis." from https://corporatefinanceinstitute.com/resources/data-science/regression-analysis/. |
APA Style
Hiak, S. E., He, X. (2023). Automated Fish Measurement and Classification Using Convolutional Neural Networks (CNNs). Computational Biology and Bioinformatics, 11(2), 33-48. https://doi.org/10.11648/j.cbb.20231102.12
ACS Style
Hiak, S. E.; He, X. Automated Fish Measurement and Classification Using Convolutional Neural Networks (CNNs). Comput. Biol. Bioinform. 2023, 11(2), 33-48. doi: 10.11648/j.cbb.20231102.12
AMA Style
Hiak SE, He X. Automated Fish Measurement and Classification Using Convolutional Neural Networks (CNNs). Comput Biol Bioinform. 2023;11(2):33-48. doi: 10.11648/j.cbb.20231102.12
@article{10.11648/j.cbb.20231102.12, author = {Soad El Hiak and Xu He}, title = {Automated Fish Measurement and Classification Using Convolutional Neural Networks (CNNs)}, journal = {Computational Biology and Bioinformatics}, volume = {11}, number = {2}, pages = {33-48}, doi = {10.11648/j.cbb.20231102.12}, url = {https://doi.org/10.11648/j.cbb.20231102.12}, eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.cbb.20231102.12}, abstract = {Managing fisheries requires regular monitoring and assessment of fish populations. Traditional methods of evaluating fish stocks, particularly their size, can be time-consuming, labor-intensive, and inaccurate. Recently, digital image processing (DIP) and machine learning (ML) have emerged as promising technologies to automate fish measurement and classification. In this study, we aim to develop deep learning models to predict, and classify shape and size of the fish using convolutional neural networks (CNNs) and DIP techniques. The study utilizes publicly available fish datasets and evaluates the efficiency of the proposed models using metrics such as precision, recall, and F1 score. The developed models utilize Python programming language with TensorFlow and Keras libraries. The regression component investigates the intricate relationship between various physical attributes of fish, uncovering the connections between body length, height, and weight. This analysis provides valuable insights into the correlations among these attributes, enhancing our understanding of fish characteristics. Simultaneously, the classification segment introduces an innovative approach to fish classification, incorporating shape and size attributes. Through a combination of classifiers and ensemble learning with stacking, exceptional accuracy is achieved in identifying distinct fish classes. This integration of techniques facilitates a more nuanced classification process, allowing for comprehensive categorization based on visual attributes. Our study establishes a robust framework for fish analysis and classification, Utilizing the combined strengths of digital image processing (DIP) and machine learning (ML). The developed models not only enhance the accuracy and efficiency of size classification but also contribute to the broader goal of sustainable fisheries management. This research sets a foundation for future endeavors in automating fish stock assessments, contributing to the advancement of fisheries science and management practices. }, year = {2023} }
TY - JOUR T1 - Automated Fish Measurement and Classification Using Convolutional Neural Networks (CNNs) AU - Soad El Hiak AU - Xu He Y1 - 2023/12/05 PY - 2023 N1 - https://doi.org/10.11648/j.cbb.20231102.12 DO - 10.11648/j.cbb.20231102.12 T2 - Computational Biology and Bioinformatics JF - Computational Biology and Bioinformatics JO - Computational Biology and Bioinformatics SP - 33 EP - 48 PB - Science Publishing Group SN - 2330-8281 UR - https://doi.org/10.11648/j.cbb.20231102.12 AB - Managing fisheries requires regular monitoring and assessment of fish populations. Traditional methods of evaluating fish stocks, particularly their size, can be time-consuming, labor-intensive, and inaccurate. Recently, digital image processing (DIP) and machine learning (ML) have emerged as promising technologies to automate fish measurement and classification. In this study, we aim to develop deep learning models to predict, and classify shape and size of the fish using convolutional neural networks (CNNs) and DIP techniques. The study utilizes publicly available fish datasets and evaluates the efficiency of the proposed models using metrics such as precision, recall, and F1 score. The developed models utilize Python programming language with TensorFlow and Keras libraries. The regression component investigates the intricate relationship between various physical attributes of fish, uncovering the connections between body length, height, and weight. This analysis provides valuable insights into the correlations among these attributes, enhancing our understanding of fish characteristics. Simultaneously, the classification segment introduces an innovative approach to fish classification, incorporating shape and size attributes. Through a combination of classifiers and ensemble learning with stacking, exceptional accuracy is achieved in identifying distinct fish classes. This integration of techniques facilitates a more nuanced classification process, allowing for comprehensive categorization based on visual attributes. Our study establishes a robust framework for fish analysis and classification, Utilizing the combined strengths of digital image processing (DIP) and machine learning (ML). The developed models not only enhance the accuracy and efficiency of size classification but also contribute to the broader goal of sustainable fisheries management. This research sets a foundation for future endeavors in automating fish stock assessments, contributing to the advancement of fisheries science and management practices. VL - 11 IS - 2 ER -