International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Automated Skin Cancer Identification through Image Analysis |
|---|---|
| ABSTRACT | In the realm of medical science, groundbreaking strides are being made in the early detection of melanoma, a highly malignant form of skin cancer. With an alarming global annual incidence exceeding one million cases, timely diagnosis is pivotal in saving lives. Understanding that cancer is an aberrant growth of cells, skin cancer is a classification that encompasses Basal Cell Carcinoma, Squamous Cell Carcinoma, and the most critical of them all, Melanoma. Melanoma poses a particularly grave threat due to its propensity to metastasize, significantly reducing the chances of recovery and survival. This paper delves into an intricate approach that seamlessly integrates the realms of image processing and machine learning to elevate the accuracy of melanoma screening. The process encompasses an array of image enhancement techniques, including hair removal, noise reduction, sharpening, and image resolution enhancement, all tailored to the unique characteristics of skin lesions. Furthermore, this study introduces an innovative dimension to the melanoma screening process by incorporating Image Super-Resolution (ISR) techniques. ISR techniques excel at reconstructing high-resolution images or sequences from low-resolution visual inputs. By leveraging these cutting-edge advancements in both image processing and machine learning, this study reports an impressive classification accuracy of 96.5%. |
| AUTHOR | T. SRIVENKAT |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311111 |
| pdf/111_Automated Skin Cancer Identification through Image Analysis.pdf | |
| KEYWORDS |
