<![CDATA[This research aims to develop an image processing-based classification system for helminths eggs using Convolutional Neural Network (CNN) with a transfer learning and finetuning approach. Helminths eggs are important indicators in the diagnosis of helminth diseases in humans. However, the manual classification of helminths eggs requires significant time and effort. Therefore, an automated system that can classify helminths eggs with high accuracy would be highly beneficial in the diagnosis of these diseases. In this study, experiments were conducted using three CNN architectures that have proven effective in image classification tasks, namely EfficientNetB0, MobileNetV3, and ResNet50. Transfer learning method was employed by utilizing pre-trained models on large-scale image datasets. Subsequently, fine tuning was performed on the last layers of the models to adapt them to the helminths egg data. Testing was conducted using a dataset of helminths eggs collected from IEEE Dataport. The experimental results show that all three CNN architectures were able to classify helminths eggs with high accuracy, with EfficientNet-B0 achieving the highest accuracy (95.36%). The developed system in this study has the potential to be used in the efficient and accurate diagnosis of helminth diseases.]]>
Copyrights © 2025
