Fish Check: Sistem Berbasis Convolutional Neural Network untuk Menilai Kelayakan Konsumsi Ikan Laut di Desa Weru, Kecamatan Paciran, Kabupaten Lamongan: Fish Check: A Convolutional Neural Network-Based System for Assessing the Edibility of Marine Fish in Weru Village, Paciran District, Lamongan Regency

Santi Febrianti; Aisyah Nur Nabila; Ratih Berliana; Nuke Amalia; Rudy Suryadi; Riyan Bagus Prihandanu

doi:10.59061/jentik.v4i2.1564

Authors

Santi Febrianti Politeknik Perkapalan Negeri Surabaya https://orcid.org/0009-0002-3812-065X
Aisyah Nur Nabila Politeknik Perkapalan Negeri Surabaya https://orcid.org/0009-0001-6171-3800
Ratih Berliana Politeknik Perkapalan Negeri Surabaya https://orcid.org/0009-0000-6653-226X
Nuke Amalia Politeknik Perkapalan Negeri Surabaya https://orcid.org/0000-0003-4668-9280
Rudy Suryadi Politeknik Perkapalan Negeri Surabaya https://orcid.org/0009-0009-5781-2919
Riyan Bagus Prihandanu Politeknik Perkapalan Negeri Surabaya https://orcid.org/0009-0005-5036-4077

DOI:

https://doi.org/10.59061/jentik.v4i2.1564

Keywords:

Computer Vision, Convolutional Neural Network, Fish Freshness, MobileNetV2, TensorFlow Lite

Abstract

Conventional assessment of fish freshness remains subjective, resulting in inconsistent evaluations. Advances in computer vision and Convolutional Neural Networks (CNNs) offer an opportunity to develop automated and objective approaches for assessing fish freshness through mobile devices. This study developed Fish Check, a smartphone-based application that utilizes the MobileNetV2 architecture to classify the freshness status of marine fish from digital images captured using a smartphone camera. A dataset comprising 2,400 marine fish images was collected. Image acquisition was conducted under varying lighting conditions, camera angles, and object positions to represent practical field conditions. The proposed approach involved image preprocessing, data augmentation, transfer learning-based model training, and performance evaluation using Accuracy, Precision, Recall, F1-score, and a Confusion Matrix. The optimized MobileNetV2 model was subsequently integrated into a React Native mobile application using TensorFlow Lite to enable efficient real-time inference directly on smartphones. The experimental results showed that the proposed model achieved an Accuracy of 96.39%, Precision of 96.11%, Recall of 96.74%, and F1-score of 96.42% demonstrate that the model can effectively distinguish between fresh and non-fresh marine fish. Overall, Fish Check provides a practical approach for real-time fish freshness assessment by combining a locally collected marine fish image dataset with an efficient deep learning architecture optimized for mobile deployment.

Author Biographies

Aisyah Nur Nabila, Politeknik Perkapalan Negeri Surabaya

Ship building Engineering, Shipbuilding Institute of Polytechnic Surabaya, Surabaya

Ratih Berliana, Politeknik Perkapalan Negeri Surabaya

Ship Machinery Engineering, Shipbuilding Institute of Polytechnic Surabaya, Surabaya

Nuke Amalia, Politeknik Perkapalan Negeri Surabaya

Ship Machinery Engineering, Shipbuilding Institute of Polytechnic Surabaya, Surabaya

Rudy Suryadi, Politeknik Perkapalan Negeri Surabaya

Ship Machinery Engineering, Shipbuilding Institute of Polytechnic Surabaya, Surabaya

Riyan Bagus Prihandanu, Politeknik Perkapalan Negeri Surabaya

Ship Machinery Engineering, Shipbuilding Institute of Polytechnic Surabaya, Surabaya

References

Al-Ghiffary, M. M. I., Sari, C. A., Rachmawanto, E. H., Yacoob, N. M., Cahyo, N. R. D., & Ali, R. R. (2023). Milkfish Freshness Classification Using Convolutional Neural Networks Based on Resnet50 Architecture. Advance Sustainable Science Engineering and Technology, 5(3), 0230304. https://doi.org/10.26877/asset.v5i3.17017

Al-Quraishi, M. S., El-Alfy, E. S. M., & Al-Turjman, F. (2022). Survey on lightweight deep learning models for edge computing. IEEE Access, 10, 89363–89387. https://doi.org/https://doi.org/10.1109/ACCESS.2022.3199857

Anas, D. F., Jaya, I., & Nurjanah. (2021). Design and implementation of fish freshness detection algorithm using deep learning. IOP Conference Series: Earth and Environmental Science, 944(1), 012007. https://doi.org/10.1088/1755-1315/944/1/012007

Chollet, F. (2021). Deep Learning With Python, Second. Manning Publications Co.

David, R., Duke, J., Jain, A., Janapa Reddi, V., Jeffries, N., Li, J., & Warden, P. (2021). TensorFlow Lite Micro: Embedded machine learning on TinyML systems. Proceedings of Machine Learning and Systems, 800–811. https://doi.org/https://doi.org/10.48550/arXiv.2010.08678

Elfwing, S., Uchidate, E., & Tokoro, K. (2021). Optimization of depthwise separable convolutions for mobile vision architectures. Journal of Real-Time Image Processing, 18(4), 1145–1158. https://doi.org/https://doi.org/10.1007/s11554-021-01102-7

Forsyth, D. A., & Ponce, J. (2012). Computer vision: A modern approach (2nd ed.). Pearson.

Gazpersz, N., El, R., Baharudin, M. D. A., Bastio, Z. I. H., Ipaenin, A. I., & Sohilait, M. R. (2024). Molecular Docking Senyawa Aktif Ekstrak Daun Melinjo (Gnetum gnemon) dalam Penghambatan Enzim Histidin Dekarboksilase. KOVALEN: Jurnal Riset Kimia, 10(1), 11–19. https://doi.org/10.22487/kovalen.2024.v10.i1.16603

Gonzalez, R. C., & Woods, R. E. (2018). Digital image processing (4th ed.). Pearson.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

Gunawan, C. R., Nurdin, N., & Fajriana, F. (2023). Deteksi Ikan Segar Secara Realtime dengan YOLOv4 menggunakan Metode Convolutional Neural Network. Jurnal Komtika (Komputasi Dan Informatika), 7(1), 1–11. https://doi.org/10.31603/komtika.v7i1.8986

Gupta, P. K., Sharma, A., & Verma, S. (2022). Quantization and optimization of deep learning models using TensorFlow Lite for mobile edge computing. IEEE Internet of Things Journal, 9(15), 13450–13461. https://doi.org/https://doi.org/10.1109/JIOT.2022.3142980

Hanifa, M. F., Ramadhan, A. T., Husna, N., Widiyono, N. A., Mubarak, R. S., Putri, A. A., & Priyanta, S. (2023). Fishku Apps: Fishes Freshness Detection Using CNN With MobilenetV2. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 17(1), 67–78. https://doi.org/10.22146/ijccs.80049

Jain, S., Agarwal, R., & Kumar, P. (2023). On-device machine learning with TensorFlow Lite: Latency, memory, and energy evaluation on smartphones. Neurocomputing, 542, 126235.

Jaydish, M. J., & Chelladurai, G. (2026). Development of an AI-Based Non-Destructive Fish Freshness Detection [Fish Snap] and Quality Classification System Using Deep Learning. Fishworld, 3(02), 169–175. https://doi.org/10.5281/FIshWorld.18873010

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539

Mahendra, R., & Faurina, R. (2024). Fish Freshness Prediction with Convolutional Neural Network Method Based on Fish Eye Image Analysis. Jurnal Teknik Informatika (Jutif), 5(3), 883–890. https://doi.org/10.52436/1.jutif.2024.5.3.1351

Mulyaningtyas, D., Arvitrid, N. I., Wirawan, A., & Syafrina, M. (2020). Analisis Sistem Cold Chain dengan Strategi Desentralisasi Cold Storage Terhadap Stabilitas Harga Komoditas Ikan Kembung di Lamongan Jawa Timur dengan Pendekatan Simulasi Sistem Dinamis. JOURNAL OF APPLIED BUSINESS ADMINISTRATION, 4(2), 148–155. https://doi.org/10.30871/jaba.v4i2.2181

Nasional, B. S. (2013). Ikan Segar. BSN. www.bsn.go.id

Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191

Perez, M., Sanchez, L., & Torres, R. (2024). Cross-platform deployment of mobile deep learning models using React Native and TensorFlow Lite. Software: Practice and Experience, 54(2), 312–329.

Prayoga, S. D. (2018). Analisis Faktor yang Mempengaruhi Produksi Perikanan dan Kontribusi Subsektor Perikanan Terhadap PDRB di Kabupaten Lamongan.

Prince, S. J. D. (2012). Computer vision: Models, learning, and inference. Cambridge University Press.

Ray, P. P. (2022). A review on TinyML: State-of-the-art and prospects. Journal of King Saud University - Computer and Information Sciences, 34(6), 3395–3423.

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4510–4520. https://doi.org/10.1109/CVPR.2018.00474

Setiadi, I. C., Hatta, A. M., Koentjoro, S., Stendafity, S., Azizah, N. N., & Wijaya, W. Y. (2022). Adulteration detection in minced beef using low-cost color imaging system coupled with deep neural network. Frontiers in Sustainable Food Systems, 6, 1–14. https://doi.org/10.3389/fsufs.2022.1073969

Shorten, C., & Khoshgoftaar, T. M. (2021). Deep learning applications and hardware optimization strategies for computer vision: A review. Journal of Big Data, 8(1), 1–42. https://doi.org/https://doi.org/10.1186/s40537-021-00431-7

Sinha, A., & Mukherjee, R. (2023). Performance benchmark of lightweight Convolutional Neural Networks on mobile platforms. Computers and Electrical Engineering, 108, 108690. https://doi.org/10.1016/j.compeleceng.2023.108690

Sonka, M., Hlavac, V., & Boyle, R. (2014). Image processing, analysis, and machine vision (4th ed.). Cengage Learning.

Suhendra, R., Ayu, R. S., Qaisa, R. S., Juliwardi, I., Astrianda, N., Arisna, P., Syahril, A., & Hasanah, U. (2025). Penerapan CNN Arsitektur VGG16 untuk Deteksi Kesegaran Ikan Berdasarkan Citra Digital. Jurnal Teknologi Informasi, 4(1), 19–25.

Yildiz, M. B., Yasin, E. T., & Koklu, M. (2024). Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application. European Food Research and Technology, 250(7), 1919–1932. https://doi.org/10.1007/s00217-024-04493-0

Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2021). Dive into deep learning. Cambridge University Press.