Classification of Skin Lesions in Digital Images for the Diagnosis of Skin Cancer

According to modern research skin cancer is increasing day by day, early detection of skin cancer can increase the survival rate up to a larger extend. Image processing techniques play an important role to detect the skin malignancies in its initial stages. This paper presents an image proceeding te...

Full description

Saved in:

Bibliographic Details
Published in:	2020 International Conference on Smart Electronics and Communication (ICOSEC) pp. 162 - 166
Main Authors:	Shahana sherin, k c, Shayini, R
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-09-2020
Subjects:	Classifiers Feature extraction Image color analysis Image processing Image segmentation Lesions Melanoma Nevus Skin
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	According to modern research skin cancer is increasing day by day, early detection of skin cancer can increase the survival rate up to a larger extend. Image processing techniques play an important role to detect the skin malignancies in its initial stages. This paper presents an image proceeding techniques to classify skin lesion image into melanoma or nevus. Input image undergoes image pre-processing stages such as smoothing or blurring, segment the lesion part using most faster and accurate multi thresholding approach, extract the features of the lesion by an 18-feature vector and pre-trained ANN is used as the classifier to distinguish between melanoma and nevus. The proposed system takes 166 selected images from the PH 2 data set.
DOI:	10.1109/ICOSEC49089.2020.9215271