Classification of mushroom types based on digital image processing using convolutional neural network
DOI:
https://doi.org/10.35335/mandiri.v13i4.387Keywords:
Classification, CNN, EfficientNet-B4, MushroomAbstract
In this research, a classification of mushroom types based on digital image processing using a Convolutional Neural Network (CNN) is conducted. The method employs the EfficientNet-B4 architecture as the base model utilizing transfer learning and fine-tuning processes. The dataset consists of 3000 types of mushrooms, each categorized into 10 classes with 300 images per class. The CNN model is implemented using the Python programming language on Google Colab editor. Performance evaluation is carried out using accuracy, precision, recall, and F1-Score metrics to measure the model's performance. A comparison is made between all models with various training parameters, including identical and different settings. Additionally, the ratio of data splits, whether identical or different, is considered. Model 1, which utilizes a custom freeze layer and a data split ratio of 80% for training, 10% validation, and 10% testing, achieved the highest accuracy (90.00%), precision (90.09%), recall (89.63%), and F1-Score (89.59%) compared to other models. Therefore the implementation of a custom freeze layer to reduce the$ number of trainable parameters significantly impacts the accuracy level of the trained and tested model. Moreover, the determination of the data split ratio also slightly influences the accuracy level of the trained and tested model.
References
Abraham, B. S., Bhanu, D. G., Thomas, A., & Anitha, J. (2023). Comparative Analysis of Glaucoma Diagnosis on Retinal Fundus Images Using AI Techniques. 2023 4th International Conference on Signal Processing and Communication (ICSPC), 386–390.
Acharya, D., Guda, R. K. S., & Raovenkatajammalamadaka, K. (2022). Enhanced efficientnet network for classifying laparoscopy videos using transfer learning technique. 2022 International Joint Conference on Neural Networks (IJCNN), 1–9.
Apriayani, S. (2023). Pengembangan buku saku keanekaragaman hayati tumbuhan obat di desa mekar bersatu sebagai bahan ajar Biologi Kelas X MA Darul Muhajirin.
Baykal, E., Dogan, H., Ercin, M. E., Ersoz, S., & Ekinci, M. (2020). Transfer learning with pre-trained deep convolutional neural networks for serous cell classification. Multimedia Tools and Applications, 79, 15593–15611.
Chen, X., Pu, X., Chen, Z., Li, L., Zhao, K., Liu, H., & Zhu, H. (2023). Application of EfficientNet‐B0 and GRU‐based deep learning on classifying the colposcopy diagnosis of precancerous cervical lesions. Cancer Medicine, 12(7), 8690–8699.
Dai, Q., Guo, Y., Li, Z., Song, S., Lyu, S., Sun, D., Wang, Y., & Chen, Z. (2023). Citrus Disease Image Generation and Classification Based on Improved FastGAN and EfficientNet-B5. Agronomy, 13(4), 988.
Denandra, R., Fariza, A., & Prayogi, Y. R. (2023). Eye Disease Classification Based on Fundus Images Using Convolutional Neural Network. 2023 International Electronics Symposium (IES), 563–568.
Ghoshal, N., Anas, M., & Roy, S. S. (2023). Chest X-Ray Image Classification of Pneumonia Disease Using EfficientNet and InceptionV3. In Deep Learning Applications in Image Analysis (pp. 173–186). Springer.
Haksoro, E. I., & Setiawan, A. (2021). Pengenalan jamur yang dapat dikonsumsi menggunakan metode transfer learning pada convolutional neural network. Jurnal ELTIKOM: Jurnal Teknik Elektro, Teknologi Informasi Dan Komputer, 5(2), 81–91.
Huang, Z., Su, L., Wu, J., & Chen, Y. (2023). Rock Image Classification Based on EfficientNet and Triplet Attention Mechanism. Applied Sciences, 13(5), 3180.
Justaniah, E., Aldabbagh, G., Alhothali, A., & Abourokbah, N. (2022). Classifying Breast Density from Mammogram with Pretrained CNNs and Weighted Average Ensembles. Applied Sciences, 12(11), 5599.
Kaplale, A. H., Rumondor, M., & Tangapo, A. M. (2022). Toksisitas Makrofungi Beracun dari Divisi Basidiomycota. Journal of Biotechnology and Conservation in Wallacea, 2(1), 1–15.
Khosi’in, K. (2021). BUKU AJAR MATA KULIAH KEANEKARAGAMAN MAKHLUK HIDUP (KINGDOM FUNGI) BERBASIS KEARIFAN LOKAL DI TAMAN NASIONAL BUKIT BARISAN SELATAN BENGKULU. CV. ELSI PRO.
Lestandy, M., Hanifah, P. K., & Irfan, M. (2022). Deteksi Dini Kanker Payudara menggunakan Metode Convolution Neural Network (CNN). Inspiration: Jurnal Teknologi Informasi Dan Komunikasi, 12(1), 65. https://doi.org/10.35585/inspir.v12i1.2667
López, A. R., Barea-Sepúlveda, M., Barbero, G. F., Ferreiro-González, M., López-Castillo, J. G., Palma, M., & Espada-Bellido, E. (2022). Essential mineral content (Fe, Mg, P, Mn, K, Ca, and Na) in five wild edible species of Lactarius mushrooms from Southern Spain and Northern Morocco: Reference to daily intake. Journal of Fungi, 8(12), 1292.
Mbakop, S., Tagne, G., Lagache, A., Youcef-Toumi, K., & Merzouki, R. (2023). Integrated design of a bio-inspired soft gripper for mushrooms harvesting. 2023 IEEE International Conference on Soft Robotics (RoboSoft), 1–6.
Miller, S. L., & Buyck, B. (2002). Molecular phylogeny of the genus Russula in Europe with a comparison of modern infrageneric classifications. Mycological Research, 106(3), 259–276.
Mosayyebi, F., Seyedarabi, H., & Afrouzian, R. (2023). Gender Recognition in Masked Facial Images Using Efficientnet and Transfer Learning Approach. Available at SSRN 4328048.
Pratiwi, H. A., Cahyanti, M., & Lamsani, M. (2021). Implementasi deep learning flower scanner menggunakan metode convolutional neural network. Sebatik, 25(1), 124–130.
Purkayastha, R., & Mohapatra, S. (2023). A Conceptual Model for Analysis of Plant Diseases Through EfficientNet: Towards Precision Farming. In Innovations in Machine and Deep Learning: Case Studies and Applications (pp. 401–417). Springer.
Ragab, M., & Albukhari, A. (2022). Automated Artificial Intelligence Empowered Colorectal Cancer Detection and Classification Model. Computers, Materials & Continua, 72(3).
Rahman, N., & Das, S. K. (2022). A Fusion of Three Custom-Tailored Deep Learning Architectures for Waste Classification. 2022 4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 1–6.
Rao, M. V. S. R., Puligundla, S., Ekkala, N. S., & Chebrolu, S. (2023). Image Classification of Ischemic Stroke Blood Clot Origin using Stacked EfficientNet-B0, VGG19 and ResNet-152. 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), 304–310.
Venugopal, V., Raj, N. I., Nath, M. K., & Stephen, N. (2023). A deep neural network using modified EfficientNet for skin cancer detection in dermoscopic images. Decision Analytics Journal, 100278.
Yamamoto, S., Kinugasa, H., Hamada, K., Tomiya, M., Tanimoto, T., Ohto, A., Toda, A., Takei, D., Matsubara, M., & Suzuki, S. (2022). The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists: A pilot study. Journal of Gastroenterology and Hepatology, 37(8), 1610–1616.
Zhao, X., Li, K., Li, Y., Ma, J., & Zhang, L. (2022). Identification method of vegetable diseases based on transfer learning and attention mechanism. Computers and Electronics in Agriculture, 193, 106703.
Zhu, C.-Y., Wang, Y.-K., Chen, H.-P., Gao, K.-L., Shu, C., Wang, J.-C., Yan, L.-F., Yang, Y.-G., Xie, F.-Y., & Liu, J. (2021). A deep learning based framework for diagnosing multiple skin diseases in a clinical environment. Frontiers in Medicine, 8, 626369.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ira Puspita Sari, Luluk Elvitaria
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
