Authors :
Isha Salunkhe; Jermin Shaikh; Dipika Harshad Mankar
Volume/Issue :
Volume 8 - 2023, Issue 9 - September
Google Scholar :
https://tinyurl.com/57z3pxnx
Scribd :
https://tinyurl.com/3m3jmzdb
DOI :
https://doi.org/10.5281/zenodo.8426043
Abstract :
Previous research articles have covered
several methods used for identifying and categorizing
malignancies of the skin, including image pre-processing,
picture division, extraction of features, and classification.
Skin illness is the most frequent human disease in
general. Cancer is a group of disorders that may
manifest itself practically everywhere in the body.
Cancer is, at its most basic, a disease of the genes in our
body's cells. Detecting dangerous skin disorders,
particularly cancer, demands the identification of
pigmented lesions on the skin. Image detection
approaches and computer categorization abilities can
help enhance skin cancer diagnosis accuracy. Skin
cancer is one of the most common and potentially fatal
types of cancer in the globe. A timely and correct
diagnosis is critical for optimal therapy and patient
outcomes. This work proposes a unique method to
dermatological diagnostics based on the integration of
machine learning and image processing techniques for
the early identification of skin cancer. The fundamental
goal of this research is to create a dependable and
efficient skin cancer detection system that can aid
dermatologists and other healthcare professionals in
making appropriate diagnostic judgments. To train and
test our machine learning models, we use a varied
collection of skin lesion photos including a wide
spectrum of benign and malignant instances.
Keywords :
Melanoma, Support Vector Machine, CNN, Skin Lesion, Machine Learning.
Previous research articles have covered
several methods used for identifying and categorizing
malignancies of the skin, including image pre-processing,
picture division, extraction of features, and classification.
Skin illness is the most frequent human disease in
general. Cancer is a group of disorders that may
manifest itself practically everywhere in the body.
Cancer is, at its most basic, a disease of the genes in our
body's cells. Detecting dangerous skin disorders,
particularly cancer, demands the identification of
pigmented lesions on the skin. Image detection
approaches and computer categorization abilities can
help enhance skin cancer diagnosis accuracy. Skin
cancer is one of the most common and potentially fatal
types of cancer in the globe. A timely and correct
diagnosis is critical for optimal therapy and patient
outcomes. This work proposes a unique method to
dermatological diagnostics based on the integration of
machine learning and image processing techniques for
the early identification of skin cancer. The fundamental
goal of this research is to create a dependable and
efficient skin cancer detection system that can aid
dermatologists and other healthcare professionals in
making appropriate diagnostic judgments. To train and
test our machine learning models, we use a varied
collection of skin lesion photos including a wide
spectrum of benign and malignant instances.
Keywords :
Melanoma, Support Vector Machine, CNN, Skin Lesion, Machine Learning.
