Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207072,
        author = {Nayan Sahebrao Jadhav},
        title = {Deep Learning-based Multi-Class Skin Disease Detection using CNN and Transfer Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {4309-4313},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207072},
        abstract = {Skin diseases constitute a significant global health burden, with early and accurate diagnosis being critical for effective treatment outcomes. This paper presents a deep learning-based multi-class classification system for automated detection of seven distinct skin disease categories using the HAM10000 benchmark dataset. The proposed methodology integrates classical Convolutional Neural Network (CNN) architectures with state-of-the-art pre-trained transfer learning models, namely ResNet50, DenseNet121, and EfficientNetB0, to evaluate comparative performance under identical experimental conditions. Comprehensive image preprocessing—including hair artifact removal via morphological black-hat filtering and contrast enhancement through Contrast Limited Adaptive Histogram Equalization (CLAHE)—is applied prior to training. Experimental results demonstrate that EfficientNetB0 achieves the highest classification accuracy of 91.8%, outperforming custom CNN (81.3%), ResNet50 (88.2%), and DenseNet121 (89.5%) baselines. The findings underscore the efficacy of transfer learning and domain-specific preprocessing for dermatological image analysis and provide a foundation for clinical decision-support tools.},
        keywords = {Deep learning, convolutional neural networks, transfer learning, skin disease classification, dermoscopic image analysis, computer-aided diagnosis.},
        month = {July},
        }