• A.IMMAGULATE

Non-melanoma is the most common form of skin cancer. Early detection of skin cancer has the possible to reduce mortality and morbidity. The main objective of this research work is to focus on Non-Melanoma skin cancers and classify the types of it. There are five types of Non-melanoma skin cancers namely Actinic Keratosis (AK), Basal Cell Carcinoma (BCC), Melanocytic Nevus / mole (MN), Squamous Cell Carcinoma (SCC), and Seborrhoeic Keratosis (SK). The database contains allthe above mentioned five types of skin lesion diseases images and it is used to perform three different stages namely preprocessing the image, feature extraction for each image and classification of skin cancer. In preprocessing stage the input images are resized and adjusted and in feature extraction task 29 different features are extracted for all images in the given database. Finally the classification task is performed using Support Vector Machine (SVM) and Active Support Vector Machine (ASVM). The experimental result shows that Active Support Vector Machine performs well in finding out the Non-Melanoma skin cancer accurately and efficiently.

Skin cancer, Actinic Keratosis (AK), Basal Cell Carcinoma (BCC), Melanocytic Nevus / mole (MN), Squamous Cell Carcinoma (SCC), Seborrhoeic Keratosis (SK), Support Vector Machine (SVM) and Active Support Vector Machine (ASVM).

"CATEGORIZATION OF NON-MELANOMA SKIN LESION DISEASES USING SUPPORT VECTOR MACHINE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.242-247, April-2019, Available :http://www.jetir.org/papers/JETIR1904645.pdf

"CATEGORIZATION OF NON-MELANOMA SKIN LESION DISEASES USING SUPPORT VECTOR MACHINE ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp242-247, April-2019, Available at : http://www.jetir.org/papers/JETIR1904645.pdf