The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness

Tarık Talan; Habibe Aslan

doi:10.35377/saucis...1839329

The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness

Abstract

Regular monitoring of fish freshness is critical to product reliability, consumer health, and compliance with food industry quality standards and quality control processes. In this study, fish were classified as fresh or non-fresh using image-based methods. To determine the model that best predicted fish freshness, eight models were compared: four deep learning (DL) architectures, three hybrid models, and one ensemble model. The dataset consisted of images of each fish taken from approximately 20 different angles. Data leakage, which emerged during initial tests, enabled the models to distinguish freshness classes more easily than expected. To address this issue, a group-based splitting method was applied. All models in the study were evaluated with a single, common training protocol under the same regularization, epoch, and optimization settings. Dropout, early stopping, and image enhancement (rotation, color jittering, and horizontal flipping) were used during training. According to the results, the ensemble model performed best with 98.44% accuracy. This was followed by ResNet50 (97.10%) and MobileNetV2 (94.31%) models. Grad-CAM and Layer-CAM analyses revealed that the models focused on regions that indicate freshness, such as the fish’s eyes, gills, and surface texture.

Keywords

Supporting Institution

This study was not supported by any institution or organization.

References

İsmail Yüksel Genç, R. Gürfidan, and T. Yiğit, “Quality prediction of seabream sparus aurata by deep learning algorithms and explainable artificial intelligence,” Food Chemistry, vol. 474, p. 143150, 5 2025.
A. Taheri-Garavand, S. Fatahi, A. Banan, and Y. Makino, “Real-time nondestructive monitoring of common carp fish freshness using robust vision-based intelligent modeling approaches,” Computers and Electronics in Agriculture, vol. 159, pp. 16–27, 4 2019.
M. B. Yildiz, E. T. Yasin, and M. Koklu, “Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application,” European Food Research and Technology, vol. 250, pp. 1919–1932, 7 2024.
F. Kapute, “Sensory, microbiological, biochemical and physico-chemical assessment of freshness and quality of fresh lake malawi tilapia (chambo) stored in ice,” International Journal of Aquaculture, 2016.
S. Kılıçarslan, M. M. H. Çiçekliyurt, and S. Kılıçarslan, “Fish freshness detection through artificial intelligence approaches: A comprehensive study,” Turkish Journal of Agriculture - Food Science and Technology, vol. 12, pp. 290–295, 2 2024.
E. T. Yasin, I. A. Ozkan, and M. Koklu, “Detection of fish freshness using artificial intelligence methods,” European Food Research and Technology, vol. 249, pp. 1979–1990, 8 2023.
R. Liu, Y. Sun, S. Wang, N. Liu, L. Zhao, Q. Liu, and R. Cao, “A deep learning-enhanced electrophoresis method for rapid freshness monitoring in cold-stored turbot (scophthalmus maximus),” Microchemical Journal, vol. 218, p. 115775, 11 2025.
C. Balım, N. Olgun, and M. Çalışan, “Leveraging feature fusion of image features and laser reflectance for automated fish freshness classification,” Sensors 2025, Vol. 25, Page 4374, vol. 25, p. 4374, 7 2025.

M. A. Rayan, A. Rahim, M. A. Rahman, M. A. Marjan, and U. A. E. Ali, “Fish freshness classification using combined deep learning model,” 2021 International Conference on Automation, Control and Mechatronics for Industry 4.0, ACMI 2021, 7 2021.
H. K. Zadeh, M. Hardy, M. Sueker, Y. Li, A. Tzouchas, N. MacKinnon, G. Bearman, S. A. Haughey, A. Akhbardeh, I. Baek, C. Hwang, J. Qin, A. M. Tabb, R. S. Hellberg, S. Ismail, H. Reza, F. Vasefi, M. Kim, K. Tavakolian, and C. T. Elliott, “Rapid assessment of fish freshness for multiple supply-chain nodes using multi-mode spectroscopy and fusion-based artificial intelligence,” Sensors, vol. 23, p. 5149, 6 2023.
R. R. Sunduz and A. P. W. Wibowo, “Identification of fish suitable for consumption with artificial intelligence method using cnn and svm algorithms,” Brilliance: Research of Artificial Intelligence, vol. 5, pp. 44–49, 4 2025.
A. Banwari, R. C. Joshi, N. Sengar, and M. K. Dutta, “Computer vision technique for freshness estimation from segmented eye of fish image,” Ecological Informatics, vol. 69, 7 2022.
M. Hasan, N. Vasker, M. M. Hossain, M. I. Bhuiyan, J. Biswas, and M. R. A. Rashid, “Framework for fish freshness detection and rotten fish removal in bangladesh using mask r–cnn method with robotic arm and fisheye analysis,” Journal of Agriculture and Food Research, vol. 16, p. 101139, 6 2024.
Y. L. Khaleel, M. A. Habeeb, and G. G. Shayea, “Integrating image data fusion and resnet method for accurate fish freshness classification,” Iraqi Journal for Computer Science and Mathematics, vol. 5, p. 21, 12 2024.
P. Kabitha and D. U. Nandini, “Freshsense-se: A real-time e-nose system for packed fish freshness classification using voc sensors,” Journal of Food Measurement and Characterization, 2025.
H. Wang, D. Wang, H. Zhu, and T. Yang, “Reconfigurable multi-channel gas-sensor array for complex gas mixture identification and fish freshness classification,” Sensors, vol. 25, p. 6212, 10 2025.
M. G. Lanjewar and K. G. Panchbhai, “Enhancing fish freshness prediction using nasnet-lstm,” Journal of Food Composition and Analysis, vol. 127, 3 2024.
I. Putu, Y. Artana, I. Made, D. P. Asana, N. Nyoman, A. J. Sastaparamitha, K. J. Atmaja, and L. Radhitya, “Combining u-net segmentation and dimensionality reduction methods for k-nn fish freshness classification,” SINTECH (Science and Information Technology) Journal, vol. 8, pp. 81–94, 4 2025.
“Fish freshness classification.”
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, pp. 770–778, 12 2015.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, 1 2018.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, pp. 2818–2826, 12 2015.
G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 2261–2269, 8 2016.

Details

Primary Language

English

Subjects

Artificial Intelligence (Other)

Journal Section

Research Article

Authors

Tarık Talan
0000-0002-5371-4520
Türkiye

Habibe Aslan ^*
0009-0009-3396-9962
Türkiye

Early Pub Date

June 19, 2026

Publication Date

June 30, 2026

Submission Date

December 9, 2025

Acceptance Date

January 19, 2026

Published in Issue

Year 2026 Volume: 9 Number: 3

DOI

https://doi.org/10.35377/saucis...1839329

IZ

https://izlik.org/JA72ZX29LB

Cite

RIS / Bibtex

APA

Talan, T., & Aslan, H. (2026). The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness. Sakarya University Journal of Computer and Information Sciences, 9(3), 712-723. https://doi.org/10.35377/saucis...1839329

AMA

1.Talan T, Aslan H. The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness. SAUCIS. 2026;9(3):712-723. doi:10.35377/saucis.1839329

Chicago

Talan, Tarık, and Habibe Aslan. 2026. “The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness”. Sakarya University Journal of Computer and Information Sciences 9 (3): 712-23. https://doi.org/10.35377/saucis. 1839329.

EndNote

Talan T, Aslan H (June 1, 2026) The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness. Sakarya University Journal of Computer and Information Sciences 9 3 712–723.

IEEE

[1]T. Talan and H. Aslan, “The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness”, SAUCIS, vol. 9, no. 3, pp. 712–723, June 2026, doi: 10.35377/saucis...1839329.

ISNAD

Talan, Tarık - Aslan, Habibe. “The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness”. Sakarya University Journal of Computer and Information Sciences 9/3 (June 1, 2026): 712-723. https://doi.org/10.35377/saucis. 1839329.

JAMA

1.Talan T, Aslan H. The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness. SAUCIS. 2026;9:712–723.

MLA

Talan, Tarık, and Habibe Aslan. “The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 3, June 2026, pp. 712-23, doi:10.35377/saucis. 1839329.

Vancouver

1.Tarık Talan, Habibe Aslan. The Role of Deep Learning and Hybrid Approaches in Food Quality Control: Automatic Classification of Fish Freshness. SAUCIS. 2026 Jun. 1;9(3):712-23. doi:10.35377/saucis. 1839329