<![CDATA[Skin diseases are common health problems that require early diagnosis to prevent serious complications. This study aims to develop an automatic skin disease image classification system using a transfer learning approach based on Convolutional Neural Networks (CNN). Image datasets were obtained from Kaggle and underwent preprocessing stages including resizing, normalization, and augmentation. Four CNN architectures were evaluated: VGG16, ResNet50, MobileNetV2, and InceptionV3, implemented using Python and the Keras library on the Google Colab platform. The dataset was split into three training and testing ratios (90:10, 80:20, and 70:30) to assess the impact of data proportion on model performance. Models were trained by modifying the output layer to match the number of classes, and evaluated using accuracy, precision, recall, F1-score, confusion matrix, and ROC curve metrics. The results show that a 70:30 ratio yielded the most optimal training performance. InceptionV3 achieved the highest validation accuracy at 80.04%, but experienced overfitting, while VGG16 demonstrated better generalization to test data. This study proves that transfer learning with CNN is effective in improving the accuracy of automatic skin disease diagnosis and has the potential to become an efficient diagnostic solution, especially in areas with limited medical infrastructure.]]>
Copyrights © 2025
