A Convolutional Neural Network Model for Mushroom Toxicity Recognition

Irvanizam Irvanizam; Muhammad Subianto; Muhammad Salsabila Jamil

doi:10.60084/ijds.v3i2.359

Authors

Irvanizam Irvanizam Department of Informatics, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia
Muhammad Subianto Department of Informatics, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia
Muhammad Salsabila Jamil Department of Informatics, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia

DOI:

https://doi.org/10.60084/ijds.v3i2.359

Keywords:

Amanita caesarea, Amanita phalloides, Cantharellus cibarius, Omphalotus olearius, CNN

Abstract

Mushroom poisoning remains a public health concern, often caused by misidentifying toxic species that visually resemble edible ones. This study investigates the feasibility of using a Convolutional Neural Network (CNN) to classify five mushroom species, Amanita caesarea, Amanita phalloides, Cantharellus cibarius, Omphalotus olearius, and Volvariella volvacea into toxic and non-toxic categories based on image data. A dataset of 137 images was collected and preprocessed through resizing, normalization, and data augmentation. A modified AlexNet-based CNN was trained and evaluated using accuracy, precision, recall, and F1-score. The best-performing model achieved a validation accuracy of 0.40, indicating limited discriminative capability. These findings highlight that the dataset size is insufficient for training a CNN from scratch and that the model cannot reliably distinguish species with subtle morphological differences. The study concludes that larger datasets, improved image quality, and transfer learning approaches are essential for achieving practical and deployable mushroom classification performance.

Downloads

Download data is not yet available.

References

Ahmed, A. F., Mahmoud, G. A.-E., Hefzy, M., Liu, Z., and Ma, C. (2023). Overview on the Edible Mushrooms in Egypt, Journal of Future Foods, Vol. 3, No. 1, 8–14. doi:10.1016/j.jfutfo.2022.09.002.
Ayimbila, F., and Keawsompong, S. (2023). Nutritional Quality and Biological Application of Mushroom, Current Nutrition Reports, Vol. 12, No. 2, 290–307. doi:10.1007/s13668-023-00468-x.
Fransson, P., Robertson, A. H. J., and Campbell, C. D. (2023). Carbon Availability Affects Already Large Species-Specific Differences in Chemical Composition of Ectomycorrhizal Fungal Mycelia in Pure Culture, Mycorrhiza, Vol. 33, 303–319. doi:10.1007/s00572-023-01128-2.
Boonrung, S., Kanjak, T., Sombatwong, J., Vichuma, P., and Salee, N. (2023). Optimization of Culture Conditions for Mycelial Growth of the Wild Edible Mushroom Phlebopus Portentosus PPBR01, Naresuan University Journal: Science and Technology, Vol. 31, No. 2, 121–129. doi:10.14456/nujst.2023.20.
Procházka, P., Soukupová, J., Tomšík Jr., K., Mullen, K. J., and Čábelková, I. (2023). Climatic Factors Affecting Wild Mushroom Foraging in Central Europe, Forests, Vol. 14, No. 2, 382. doi:10.3390/f14020382.
Liu, X., Yin, B., Meng, L., Zhao, X., Wang, J., Liu, R., Hu, L., Wang, X., Liu, Y., and Ma, Y. (2025). Investigation of the Impact of Soil Physicochemical Properties and Microbial Communities on the Successful Cultivation of Morchella in Greenhouses, Horticulturae, Vol. 11, No. 4, 356. doi:10.3390/horticulturae11040356.
Hawksworth, D. L., and Lücking, R. (2017). Fungal Diversity Revisited: 2.2 to 3.8 Million Species, Microbiology Spectrum, Vol. 5, No. 4. doi:10.1128/microbiolspec.FUNK-0052-2016.
Pahlevi, O., and Sriyadi, S. (2025). Comparative Analysis of Machine Learning Model Performance for Classification of Edible or Non-Edible Mushrooms, Jurnal Teknik Komputer, Vol. 11, No. 2, 80–87.
Manikanteswari, D. S. L., and Kalyani, C. S. (2024). Classification of Edible and Poisonous Mushrooms Using Machine Learning Algorithms, International Journal for Multidisciplinary Research (IJFMR), Vol. 6, No. 2, 1–8.
Lin, Z., Shen, J., Zhang, P., and Xie, T. (2022). Application of Machine Learning in Mushroom Edibility Identification Model, World Scientific Research Journal, Vol. 8, No. 1, 24–32. doi:10.6911/WSRJ.202201_8(1).0005.
Bal, A., Anil, M., Yilmaz, I., Akata, I., and Atilla, O. D. (2016). An Outbreak of Non-Fatal Mushroom Poisoning with Omphalotus Olearius among Syrian Refugees in Izmir, Turkey, Toxin Reviews, Vol. 35, Nos. 1–2, 1–3. doi:10.3109/15569543.2016.1169548.
Permatananda, P. A. N., Pandit, I. G. S., and Putra, I. P. (2025). Ulasan: Beberapa Jamur Liar Yang Berpotensi Menyebabkan Keracunan Di Indonesia, AL-Kauniyah Jurnal Biologi, Vol. 18, No. 1, 42–56.
Putra, I. P. (2021). Kasus-Kasus Keracunan Chlorophyllum Cf. Molybdites Di Indonesia, Jurnal Pembelajaran Dan Biologi Nukleus, Vol. 7, No. 1, 186–194.
Karami Matin, B., Amrollahi-Sharifabadi, M., Rezaei, S., Heidari, A., and Kazemi-Karyani, A. (2022). Epidemiology and Economic Burden of an Outbreak of Cyclopeptide-Containing Mushroom Poisoning in the West of Iran, Frontiers in Public Health, Vol. 10, 910024. doi:10.3389/fpubh.2022.910024.
Tempo.co. (2019). Survei Kepemilikan Smartphone, Indonesia Peringkat Ke-24.
Rangel, G., Cuevas-Tello, J. C., Nunez-Varela, J., Puente, C., and Silva-Trujillo, A. G. (2024). A Survey on Convolutional Neural Networks and Their Performance Limitations in Image Recognition Tasks, Journal of Sensors, Vol. 2024, 2797320. doi:10.1155/2024/2797320.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., and Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, Vol. 115, No. 3, 211–252. doi:10.1007/s11263-015-0816-y.
Rahmadhani, U. S., and Marpaung, N. L. (2023). Klasifikasi Jamur Berdasarkan Genus Dengan Menggunakan Metode CNN, Jurnal Informatika: Jurnal Pengembangan IT, Vol. 8, No. 2, 169–173. doi:10.30591/jpit.v8i2.5229.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). ImageNet Classification with Deep Convolutional Neural Networks, Communications of the ACM, Vol. 60, No. 6, 84–90. doi:10.1145/3065386.