INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
In comparison to the identification of skin lesions, skin cancer detection is delicate due to remains, minimal disparity, and comparable visuals as intelligencers, scars, etc. Skin cancer is frequently detected in its early stages because it spreads slowly to other body parts and is therefore easier to cure. There are increasingly more instances of terrible carcinoma, the skin cancer that is most fatal. Skin cancer may be challenging to distinguish from skin lesions because of leftovers, little disparity, and similar visualization to an operation, scar, etc. Hence Skin lesions are automatically detected using methods for lesion detection that take into account performance, efficacy, and delicacy requirements. The proposed approach uses point birth using the ABCD principle, GLCM, and overeater point birth as the goal in the early diagnosis of skin lesions. By removing residues, skin colour, hair, and other impurities, pre-processing is used in the proposed study to enhance the skin lesion's appearance and clarity. Segmentation was done using Geodesic Active Contour (GAC), a tool that splits the lesion apart into sections and is also efficient for point birth. The harmony, border, colour, and perimeter features were rated using the ABCD scale. The textural elements were rooted by using Overeater and GLCM. In identifying 7 different types of skin cancer, classifiers use a variety of machine learning methods, including the classifiers SVM, CNN, KNN, and Naive Bayes. For this design, a total of 10015 pictures of malignant skin lesions, benign skin lesions and other types are downloaded from the HAM10000 dataset. Effective and precise bracketing is achieved. They include ABCD, overeater, GLCM, SVM, CNN, KNN, and naive Bayes.
Keywords:
SKIN CANCER DETECTION USING CNN
Cite Article:
"SKIN CANCER DETECTION USING CNN", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.b470-b477, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304167.pdf
Downloads:
000118753
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn