Abstract :

The study of fungi at the microscopic level is crucial for identifying pathogenic and beneficial species, which has applications in medicine, agriculture, and biotechnology. Traditional mycological examination relies on manual observation, which is time-consuming and prone to human error. This research proposes a deep learning-based approach to automate the identification and classification of microscopic fungi from image datasets. Using convolutional neural networks (CNNs) and image preprocessing techniques, the system can accurately detect fungal structures and provide rapid diagnostic results. Experimental results demonstrate high precision and recall, indicating the model’s efficiency in realtime applications. The proposed framework not only reduces the examination time but also improves the reliability of fungal identification. This approach paves the way for integrating AI in laboratory diagnostics.