Copyright © 2025 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{189450,
        author = {Prajwal P and Manohar V Nelli and Manjunath V Poojari and Mannan Faiz and Nithish T R},
        title = {Melanoma Cancer Detection Using Deep Learning and Image Processing},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {5790-5793},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189450},
        abstract = {Melanoma is one of the most aggressive and life- threatening forms of skin cancer, and its survival rate strongly depends on early diagnosis. Conventional diagnostic methods such as visual inspection, dermoscopy, and biopsy are time- consuming and highly dependent on clinical expertise. Recent advancements in deep learning have enabled automated medical image analysis systems to assist dermatologists by providing accurate and consistent diagnostic support.
This paper presents an automated melanoma detection system using deep learning and image processing techniques. Dermoscopic images undergo preprocessing, ESRGAN-based super- resolution, lesion segmentation, and Region of Interest (ROI) extraction before classification. Transfer learning–based deep learning models including CNN, ResNet-50, EfficientNet-B0, and MobileNetV2 are trained to classify lesions into melanoma and non-melanoma categories. Extensive data augmentation is applied to address class imbalance. Experimental results show that MobileNetV2 achieves reliable accuracy while remaining computationally efficient.},
        keywords = {Melanoma Detection, Deep Learning, Image Processing, Transfer Learning, CNN},
        month = {December},
        }