Robust Classification of Beef and Pork Images Using EfficientNet B0 Feature Extraction and Ensemble Learning with Visual Interpretation
https://doi.org/10.26594/register.v11i1.4045
Keywords:
EfficientNet B0, Ensemble Learning, Image Classification, Deep Feature Extraction, Explainable AIAbstract
Distinguishing between beef and pork based on image appearance is a critical task in food authentication, but it remains challenging due to visual similarities in color and texture, especially under varying lighting and capture conditions. To address these challenges, we propose a robust classification framework that utilizes EfficientNet B0 as a deep feature extractor, combined with an ensemble of Regularized Linear Discriminant Analysis (RLDA), Support Vector Machine (SVM), and Random Forest (RF) classifiers using soft voting to enhance generalization performance. To improve interpretability, we incorporate Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize classification decisions and validate that the model focuses on relevant regions of the meat, such as red-channel intensity and muscle structure. The proposed method was evaluated on a public dataset containing 400 images evenly split between beef and pork. It achieved a hold-out accuracy of 99.0% and a ROC-AUC of 0.995, outperforming individual learners and demonstrating strong resilience to limited data and variation in imaging conditions. By integrating efficient transfer learning, ensemble decision-making, and visual interpretability, this framework provides a powerful and transparent solution for binary meat classification. Future work will focus on fine-tuning the CNN backbone, applying GAN-based augmentation, and extending the approach to multiclass meat authentication tasks.
Downloads
References
[1] R. M. Ellahi, L. C. Wood, M. Khan, and A. E.-D. A. Bekhit, "Integrity Challenges in Halal Meat Supply Chain: Potential Industry 4.0 Technologies as Catalysts for Resolution," Foods, vol. 14, no. 7, p. 1135, Mar. 2025, doi: 10.3390/foods14071135.
[2] A. Haider et al., "Food authentication, current issues, analytical techniques, and future challenges: A comprehensive review," Compr. Rev. Food Sci. Food Saf., vol. 23, no. 3, May 2024, doi: 10.1111/1541-4337.13360.
[3] F. A. Mazlan, M. A. J. Wasmuth, M. E. M. Nesbeth-Bain, and D. N. Nesbeth, "Halal considerations that signpost a cellular agriculture compatible with world religions," Trends Food Sci. Technol., vol. 161, p. 105015, Jul. 2025, doi: 10.1016/j.tifs.2025.105015.
[4] M. A. M. Hossain et al., "Authentication of Halal and Kosher meat and meat products: Analytical approaches, current progresses and future prospects," Crit. Rev. Food Sci. Nutr., vol. 62, no. 2, pp. 285–310, Jan. 2022, doi: 10.1080/10408398.2020.1814691.
[5] M. R. Vishnuraj, N. Aravind Kumar, S. Vaithiyanathan, and S. B. Barbuddhe, "Authentication issues in foods of animal origin and advanced molecular techniques for identification and vulnerability assessment," Trends Food Sci. Technol., vol. 138, pp. 164–177, Aug. 2023, doi: 10.1016/j.tifs.2023.05.019.
[6] K. Agrawal, C. Abid, N. Kumar, and P. Goktas, "Machine Vision and Deep Learning in Meat Processing," in Innovative Technologies for Meat Processing, Boca Raton: CRC Press, 2025, pp. 170–210.
[7] C. Shen, R. Wang, H. Nawazish, B. Wang, K. Cai, and B. Xu, "Machine vision combined with deep learning–based approaches for food authentication: An integrative review and new insights," Compr. Rev. Food Sci. Food Saf., vol. 23, no. 6, Nov. 2024, doi: 10.1111/1541-4337.70054.
[8] M. Modzelewska-Kapitula and S. Jun, "The application of computer vision systems in meat science and industry – A review," Meat Sci., vol. 192, p. 108904, Oct. 2022, doi: 10.1016/j.meatsci.2022.108904.
[9] P. D. C. Sanchez, H. B. T. Arogancia, K. M. Boyles, A. J. B. Pontillo, and M. M. Ali, "Emerging nondestructive techniques for the quality and safety evaluation of pork and beef: Recent advances, challenges, and future perspectives," Appl. Food Res., vol. 2, no. 2, p. 100147, Dec. 2022, doi: 10.1016/j.afres.2022.100147.
[10] X. Wu, X. Liang, Y. Wang, B. Wu, and J. Sun, "Non-Destructive Techniques for the Analysis and Evaluation of Meat Quality and Safety: A Review," Foods, vol. 11, no. 22, p. 3713, Nov. 2022, doi: 10.3390/foods11223713.
[11] C. Magdalena, H. C. Rustamaji, and B. Yuwono, "Identification of beef and pork using gray level co-occurrence matrix and probabilistic neural network," Comput. Inf. Process. Lett., vol. 1, no. 1, p. 17, 2021, doi: 10.31315/cip.v1i1.6126.
[12] A. K. Hussein, "Histogram of Gradient and Local Binary Pattern with Extreme Learning Machine Based Ear Recognition," J. Southwest Jiaotong Univ., vol. 54, no. 6, pp. 1–6, 2019, doi: 10.35741/issn.0258-2724.54.6.31.
[13] F. D. Adhinata, N. G. Ramadhan, M. D. Fauzi, and N. A. Ferani Tanjung, "A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets," Int. J. Informatics Vis., vol. 7, no. 2, pp. 535–541, 2023, doi: 10.30630/joiv.7.2.1164.
[14] A. T. Akbar, S. Saifullah, H. Prapcoyo, R. Husaini, and B. M. Akbar, "EfficientNet B0-Based RLDA for Beef and Pork Image Classification BT," in Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023), 2024, pp. 136–145, doi: 10.2991/978-94-6463-366-5_13.
[15] H. Pu, D.-W. Sun, J. Ma, and J.-H. Cheng, "Classification of fresh and frozen-thawed pork muscles using visible and near infrared hyperspectral imaging and textural analysis," Meat Sci., vol. 99, pp. 81–88, Jan. 2015, doi: 10.1016/j.meatsci.2014.09.001.
[16] S. Sandri and A. Molinari, "Preference Learning in Food Recommendation: the 'Myfood' Case Study," in 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Jul. 2023, pp. 1–6, doi: 10.1109/ICECCME57830.2023.10253409.
[17] W. Castro-Silupu, M. Saavedra-García, H. Avila-George, M. De la Torre-Gomora, and A. Bruno-Tech, "Probabilistic or Convolutional-LSTM neuronal networks: a comparative study of discrimination capacity on frozen - thawed fish fillets," in 2022 11th International Conference On Software Process Improvement (CIMPS), Oct. 2022, pp. 112–118, doi: 10.1109/CIMPS57786.2022.10035684.
[18] H. Mu'jizah and D. C. R. Novitasari, "Comparison of the histogram of oriented gradient, GLCM, and shape feature extraction methods for breast cancer classification using SVM," J. Teknol. dan Sist. Komput., vol. 9, no. 3, pp. 150–156, 2021, doi: 10.14710/jtsiskom.2021.14104.
[19] M. A. Siddiqui et al., "Multivariate Analysis Coupled with M-SVM Classification for Lard Adulteration Detection in Meat Mixtures of Beef, Lamb, and Chicken Using FTIR Spectroscopy," Foods, vol. 10, no. 10, p. 2405, Oct. 2021, doi: 10.3390/foods10102405.
[20] S. Stendafity, A. M. Hatta, I. C. Setiadi, Sekartedjo, and A. Rahmadiansah, "Minced Meat Classification using Digital Imaging System Coupled with Machine Learning," in 2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation (ICAMIMIA), Nov. 2023, pp. 804–808, doi: 10.1109/ICAMIMIA60881.2023.10427687.
[21] H. Lu et al., "Classification and identification of chicken-derived adulteration in pork patties: A multi-dimensional quality profile and machine learning-based approach," Food Control, vol. 176, p. 111381, Oct. 2025, doi: 10.1016/j.foodcont.2025.111381.
[22] M. A. Bhat, M. Y. Rather, P. Singh, S. Hassan, and N. Hussain, "Advances in smart food authentication for enhanced safety and quality," Trends Food Sci. Technol., vol. 155, p. 104800, Jan. 2025, doi: 10.1016/j.tifs.2024.104800.
[23] K. B. Chhetri, "Applications of Artificial Intelligence and Machine Learning in Food Quality Control and Safety Assessment," Food Eng. Rev., vol. 16, no. 1, pp. 1–21, Mar. 2024, doi: 10.1007/s12393-023-09363-1.
[24] R. Farinda, Z. R. Firmansyah, C. Sulton, I. G. P. S. Wijaya, and F. Bimantoro, "Beef Quality Classification based on Texture and Color Features using SVM Classifier," J. Telemat. Informatics, vol. 6, no. 3, pp. 201–213, 2025.
[25] Y. Li, H. Wang, Z. Yang, X. Wang, W. Wang, and T. Hui, "Rapid Non-Destructive Detection Technology in the Field of Meat Tenderness: A Review," Foods, vol. 13, no. 10, p. 1512, May 2024, doi: 10.3390/foods13101512.
[26] D. R. Wijaya, R. Sarno, and A. F. Daiva, "Electronic nose for classifying beef and pork using Naïve Bayes," Proc. - 2017 Int. Semin. Sensor, Instrumentation, Meas. Metrol. Innov. Adv. Compet. Nation, ISSIMM 2017, vol. 2017-Janua, pp. 104–108, 2017, doi: 10.1109/ISSIMM.2017.8124272.
[27] B. Sugiarto, C. A. Sari, and M. Arief Soeleman, "KNN Algorithm Optimization in GLCM-Based Beef and Pork Image Classification," in 2023 International Seminar on Application for Technology of Information and Communication (iSemantic), Sep. 2023, pp. 141–146, doi: 10.1109/iSemantic59612.2023.10295331.
[28] K. Kiswanto, H. Hadiyanto, and E. Sediyono, "Meat Texture Image Classification Using the Haar Wavelet Approach and a Gray-Level Co-Occurrence Matrix," Appl. Syst. Innov., vol. 7, no. 3, p. 49, Jun. 2024, doi: 10.3390/asi7030049.
[29] P. Chanasupaprakit, N. Khusita, C. Chootong, J. Charoensuk, W. K. Tharanga Gunarathne, and S. Ruengittinun, "Fake Beef Detection with Machine Learning Technique," in 2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII ), Jul. 2022, pp. 124–127, doi: 10.1109/ICKII55100.2022.9983559.
[30] S. Ayu Aisah, A. Hanifa Setyaningrum, L. Kesuma Wardhani, and R. Bahaweres, "Identifying Pork Raw-Meat Based on Color and Texture Extraction Using Support Vector Machine," in 2020 8th International Conference on Cyber and IT Service Management (CITSM), Oct. 2020, pp. 1–7, doi: 10.1109/CITSM50537.2020.9268892.
[31] D. L. Pinto et al., "Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms," Livest. Sci., vol. 267, p. 105152, Jan. 2023, doi: 10.1016/j.livsci.2022.105152.
[32] D. Liu, Y. Ma, S. Yu, and C. Zhang, "Image based beef and lamb slice authentication using convolutional neural networks," Meat Sci., vol. 195, p. 108997, Jan. 2023, doi: 10.1016/j.meatsci.2022.108997.
[33] S. Saifullah et al., "Nondestructive chicken egg fertility detection using CNN-transfer learning algorithms," J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 3, pp. 854–871, 2023, doi: 10.26555/jiteki.v9i3.26722.
[34] S. Saifullah, R. Drezewski, A. Yudhana, and A. P. Suryotomo, "Automatic Brain Tumor Segmentation: Advancing U-Net With ResNet50 Encoder for Precise Medical Image Analysis," IEEE Access, vol. 13, pp. 43473–43489, 2025, doi: 10.1109/ACCESS.2025.3547430.
[35] S. Saifullah and R. Drezewski, "Brain Tumor Segmentation Using Ensemble CNN-Transfer Learning Models: DeepLabV3plus and ResNet50 Approach," in In: Franco, L., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2024. ICCS 2024. Lecture Notes in Computer Science, vol 14835. Springer, Cham., 2024, pp. 340–354.
[36] M. Abdullahi et al., "A systematic literature review of visual feature learning: deep learning techniques, applications, challenges and future directions," Multimed. Tools Appl., Jul. 2024, doi: 10.1007/s11042-024-19823-3.
[37] T. Dhar, N. Dey, S. Borra, and R. S. Sherratt, "Challenges of Deep Learning in Medical Image Analysis—Improving Explainability and Trust," IEEE Trans. Technol. Soc., vol. 4, no. 1, pp. 68–75, Mar. 2023, doi: 10.1109/TTS.2023.3234203.
[38] M. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700, 2019.
[39] L. Arora et al., "Ensemble deep learning and EfficientNet for accurate diagnosis of diabetic retinopathy," Sci. Rep., vol. 14, no. 1, p. 30554, Dec. 2024, doi: 10.1038/s41598-024-81132-4.
[40] S. Song, Q. Guo, X. Duan, X. Shi, and Z. Liu, "Research on Pork Cut and Freshness Determination Method Based on Computer Vision," Foods, vol. 13, no. 24, p. 3986, Dec. 2024, doi: 10.3390/foods13243986.
[41] "Study on Pig Body Condition Scoring Based on Deep Learning Model EfficientNet-B0," Acad. J. Comput. Inf. Sci., vol. 6, no. 6, 2023, doi: 10.25236/AJCIS.2023.060625.
[42] S. Ha, "Image classification of pork primal cuts using an enhanced efficientnet architecture," in Fifth International Conference on Computer Vision and Data Mining (ICCVDM 2024), Oct. 2024, p. 3, doi: 10.1117/12.3048052.
[43] M. Altalhan, A. Algarni, and M. Turki-Hadj Alouane, "Imbalanced Data Problem in Machine Learning: A Review," IEEE Access, vol. 13, pp. 13686–13699, 2025, doi: 10.1109/ACCESS.2025.3531662.
[44] L. Yijing, G. Haixiang, L. Xiao, L. Yanan, and L. Jinling, "Adapted ensemble classification algorithm based on multiple classifier system and feature selection for classifying multi-class imbalanced data," Knowledge-Based Syst., vol. 94, pp. 88–104, Feb. 2016, doi: 10.1016/j.knosys.2015.11.013.
[45] I. D. Mienye and Y. Sun, "A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects," IEEE Access, vol. 10, pp. 99129–99149, 2022, doi: 10.1109/ACCESS.2022.3207287.
[46] M. Ennab and H. Mcheick, "Advancing AI Interpretability in Medical Imaging: A Comparative Analysis of Pixel-Level Interpretability and Grad-CAM Models," Mach. Learn. Knowl. Extr., vol. 7, no. 1, p. 12, Feb. 2025, doi: 10.3390/make7010012.
[47] H. Ding, H. Hou, L. Wang, X. Cui, W. Yu, and D. I. Wilson, "Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety," Foods, vol. 14, no. 2, p. 247, Jan. 2025, doi: 10.3390/foods14020247.
[48] A. D. Saputra, D. Hindarto, B. Rahman, and H. Santoso, "Comparison of Accuracy in Detecting Tomato Leaf Disease with GoogleNet VS EfficientNetB3," SinkrOn, vol. 8, no. 2, pp. 647–656, 2023, doi: 10.33395/sinkron.v8i2.12218.
[49] Y. Lv, J. Wang, G. Gao, and Q. Li, "LW-DCGAN: a lightweight deep convolutional generative adversarial network for enhancing occluded face recognition," J. Electron. Imaging, vol. 33, no. 05, Oct. 2024, doi: 10.1117/1.JEI.33.5.053057.
[50] S. Chatterjee, D. Hazra, Y.-C. Byun, and Y.-W. Kim, "Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation," Mathematics, vol. 10, no. 9, p. 1541, May 2022, doi: 10.3390/math10091541.
[51] A. Michele, V. Colin, and D. D. Santika, "Mobilenet convolutional neural networks and support vector machines for palmprint recognition," Procedia Comput. Sci., vol. 157, pp. 110–117, 2019, doi: 10.1016/j.procs.2019.08.147.
[52] S. Zhao, B. Zhang, J. Yang, J. Zhou, and Y. Xu, "Linear discriminant analysis," Nat. Rev. Methods Prim., vol. 4, no. 1, p. 70, Sep. 2024, doi: 10.1038/s43586-024-00346-y.
[53] S. Ghosh, A. Dasgupta, and A. Swetapadma, "A Study on Support Vector Machine based Linear and Non-Linear Pattern Classification," in 2019 International Conference on Intelligent Sustainable Systems (ICISS), Feb. 2019, pp. 24–28, doi: 10.1109/ISS1.2019.8908018.
[54] N. Syam and R. Kaul, "Random Forest, Bagging, and Boosting of Decision Trees," in Machine Learning and Artificial Intelligence in Marketing and Sales, Emerald Publishing Limited, 2021, pp. 139–182.
[55] P. Das and A. Ortega, "Gradient-Weighted Class Activation Mapping for Spatio Temporal Graph Convolutional Network," in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, pp. 4043–4047, doi: 10.1109/ICASSP43922.2022.9746621.
[56] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization," Int. J. Comput. Vis., vol. 128, no. 2, pp. 336–359, Feb. 2020, doi: 10.1007/s11263-019-01228-7.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ahmad Taufiq Akbar, Shoffan Saifullah, Hari Prapcoyo, Bambang Yuwono, Heru Cahya Rustamaji
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Please find the rights and licenses in Register: Jurnal Ilmiah Teknologi Sistem Informasi. By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.
1. License
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author(s)' Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User/Public Rights
Register's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, Register permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and Register on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
Copyright and other proprietary rights relating to the article, such as patent rights,
The right to use the substance of the article in own future works, including lectures and books,
The right to reproduce the article for own purposes,
The right to self-archive the article (please read out deposit policy),
The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Register: Jurnal Ilmiah Teknologi Sistem Informasi).
5. Co-Authorship
If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. Register will not be held liable for anything that may arise due to the author(s) internal dispute. Register will only communicate with the corresponding author.
6. Royalties
Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that Register entitles the author(s) to no royalties or other fees.
7. Miscellaneous
Register will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. Register's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.
