XGBoost Implementation for Marine Fish Image Classification Using VGG19-Based Transfer Learning
DOI:
https://doi.org/10.15294/rji.v4i2.37834Keywords:
XGBoost, VGG-19, Transfer Learning, Image Classification, Marine Fish, Deep LearningAbstract
Abstract. Accurate identification of fish species is important for trade supervision, marine biology, and fisheries management. This study develops a classification system for nine marine fish species by combining VGG19-based feature extraction with XGBoost. Using 9,000 balanced RGB images from the Kaggle Large-Scale Fish Dataset, the workflow includes EDA, preprocessing, an 80:20 data split, feature extraction, and model training. EDA showed that Red Mullet and Striped Red Mullet share similar visual characteristics, while the Shrimp class appears more distinct. The model achieved 97% accuracy and was deployed through a Flask web application that processes, extracts features, and classifies images. These findings demonstrate that integrating VGG19 with XGBoost offers an effective and efficient approach for marine fish image classification.
Purpose: The primary objective here is to build a hybrid classification model for marine fish that is both efficient and robust, merging deep feature extraction from the VGG19 architecture with the XGBoost classifier. Specifically, this research seeks to improve classification accuracy while reducing computational overhead, thereby providing a reliable automated identification system that can support fisheries management, ecological monitoring, and marine biological research.
Methods: This research employed a dataset of 9,000 images representing nine marine fish species. The preprocessing stage included resizing each image to 224×224 pixels and applying normalization. Deep feature representations were obtained using a pre-trained VGG19 model, utilizing only its convolutional layers to extract semantic features. These features were then classified with the XGBoost algorithm, chosen for its efficiency, resilience, and strong performance on structured data. The model was trained using an 80:20 split for training and testing, and its performance was assessed through accuracy, precision, recall, F1-score, and a confusion matrix.
Result/Findings: The combination of VGG19 feature extraction with XGBoost produced strong results, achieving an accuracy of about 97%. This performance was further supported by consistently high precision, recall, and F1-scores across all nine species.
Novelty/Value: A hybrid architecture integrating VGG19-based transfer learning with the XGBoost classifier is presented with an approach rarely explored in this domain. This combination capitalizes on deep semantic feature extraction from VGG19 alongside efficient structured classification via XGBoost, producing a model that delivers high accuracy with significantly reduced computational costs. Additionally, the hybrid approach proposed in this study remains competitive with fully end-to-end deep learning models yet operates with fewer parameters and reduced training demands. These results illustrate that well-designed hybrid pipelines can match the performance of conventional deep learning architecture while providing clear benefits in terms of training efficiency, interpretability, and scalability.
References
[1] I. Abdurahim, U. Tangke, S. S. Titaheluw, and U. Muhammadiyah, “Potensi dan Tingkat Pemanfaatan Sumberdaya Ikan Pelagis Unggulan di Kota Ternate,” 2021, doi: 10.52046/jssh.v1i1.1-6.
[2] E. A. Supeni, P. Mudhlika Lestarina, and W. Lesmanawati, “Potensi lestari dan musim penangkapan ikan gulamah yang didaratkan pada pelabuhan perikanan Muara Kintap: Sustainable yield and fishing season of gulamah fish at landing in Muara Kintap fishing port,” 2020.
[3] M. K. Alsmadi, M. Tayfour, R. A. Alkhasawneh, U. Badawi, I. Almarashdeh, and F. Haddad, “Robust feature extraction methods for general fish classification,” International Journal of Electrical and Computer Engineering, vol. 9, no. 6, pp. 5192–5204, 2019, doi: 10.11591/ijece.v9i6.pp5192-5204.
[4] F. B. Pour, L. Parra, J. Lloret, and S. Abdanan Mehdizadeh, “Measuring and Evaluating the Speed and the Physical Characteristics of Fishes Based on Video Processing,” Water (Switzerland), vol. 15, no. 11, Jun. 2023, doi: 10.3390/w15112138.
[5] P. Paul, T. K. Kar, and K. Pujaru, “Impacts of zoning management of coastal ecosystem for three different activities: Reserve-fishing-ecotourism,” Ecol Inform, vol. 60, Nov. 2020, doi: 10.1016/j.ecoinf.2020.101171.
[6] A. N. Anugrah and A. Alfarizi, “Literature review potensi dan pengelolaan sumber daya perikanan laut di Indonesia,” Jurnal Sains Edukatika Indonesia (JSEI), vol. 3, no. 2, pp. 31–36, 2021.
[7] S. Wasik and R. Pattinson, “Artificial Intelligence Applications in Fish Classification and Taxonomy: Advancing Our Understanding of Aquatic Biodiversity,” 2024.
[8] P. Pandiyan, T. Rajasekaran, K. Vishnu Kumar, R. Sivaramakrishnan, and T. Thigarajan, “Fish Species Classification using SVM Kernels,” Innovations in Information and Communication Technology Series, pp. 466–470, Dec. 2020, doi: 10.46532/978-81-950008-1-4_102.
[9] R. Nuraini, A. Wibowo, B. Warsito, W. A. Syafei, and I. Jaya, “Combination of K-NN and PCA Algorithms on Image Classification of Fish Species,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 5, pp. 1026–1032, Aug. 2023, doi: 10.29207/resti.v7i5.5178.
[10] S. Saputra, A. Yudhana, and R. Umar, “Implementation of Naïve Bayes for Fish Freshness Identification Based on Image Processing,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 3, pp. 412–420, Jun. 2022, doi: 10.29207/resti.v6i3.4062.
[11] V. R. Raja, F. A. Hollioake, K. N. Kumar, K. P. L, and G. Dhanalakshmi, “Identification of Underwater Species Using Condition-Based Ensemble Supervised Learning Classification,” 2023. [Online]. Available: www.ijisae.org
[12] N. Rachmat, Y. Yohannes, and A. Mahendra, “Klasifikasi Jenis Ikan Laut Menggunakan Metode SVM dengan Fitur HOG dan HSV,” JATISI (Jurnal Teknik Informatika dan Sistem Informasi), vol. 8, no. 4, pp. 2235–2247, Dec. 2021, doi: 10.35957/jatisi.v8i4.1686.
[13] Y. Gao, X. Li, J. Xiang, Y. Xie, C. Yang, and W. Xiang, “FFM ‐ ViT : an efficient fish species classification method based on deep features and transformers,” J Fish Biol, Sep. 2025, doi: 10.1111/jfb.70213.
[14] E. A. Awalludin and N. M. A. Anang, “Deep Learning Models Performance on Marine Fish Species Classification,” Jurnal Ilmiah Perikanan dan Kelautan, Jul. 2025, doi: 10.20473/jipk.v17i3.71815.
[15] H. M. Essa and A. M. Murshid, “Optimizing Image Processing with CNNs through Transfer Learning: Survey,” Al-Kitab Journal for Pure Sciences, vol. 7, no. 1, pp. 57–68, Aug. 2023, doi: 10.32441/kjps.07.01.p6.
[16] E. Olsvik et al., “Biometric Fish Classification of Temperate Species Using Convolutional Neural Network with Squeeze-and-Excitation,” Apr. 2019, [Online]. Available: http://arxiv.org/abs/1904.02768
[17] O. Ulucan, D. Karakaya, and M. Turkan, “A Large-Scale Dataset for Fish Segmentation and Classification,” in 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), IEEE, Oct. 2020, pp. 1–5. doi: 10.1109/ASYU50717.2020.9259867.
[18] M. Bansal, M. Kumar, M. Sachdeva, and A. Mittal, “Transfer learning for image classification using VGG19: Caltech-101 image data set,” J Ambient Intell Humaniz Comput, vol. 14, no. 4, pp. 3609–3620, Apr. 2023, doi: 10.1007/s12652-021-03488-z.
[19] V. Verma, “Exploring Key XGBoost Hyperparameters: A Study on Optimal Search Spaces and Practical Recommendations for Regression and Classification,” International Journal of All Research Education and Scientific Methods, vol. 12, no. 10, pp. 3259–3266, 2024, doi: 10.56025/IJARESM.2024.1210243259.
[20] S. Priya et al., “Radiomics Detection of Pulmonary Hypertension via Texture-Based Assessments of Cardiac MRI: A Machine-Learning Model Comparison—Cardiac MRI Radiomics in Pulmonary Hypertension,” J Clin Med, vol. 10, no. 9, p. 1921, Apr. 2021, doi: 10.3390/jcm10091921.
[21] M. N. K. Nababan, Muhathir, R. A. Rizal, E. Panggabean, and M. Turnip, “Comparative Analysis of Machine Learning Techniques for Formalin Fish Classification using Image-based GLCM Feature Extraction,” Internetworking Indonesia Journal (IIJ), vol. Vol. 15, No. 1, no. 1, pp. 21–26, Jun. 2023.
