Analysis of Skin Cancer Classification Using GLCM Based On Feature Extraction in Artificial Neural Network

Skin cancer is the deadliest form of cancers in humans. Skin cancer is commonly known as Melanoma. Skin Cancers are of two typesBenign and Malignant Melanoma. Melanoma can be cured completely if it is detected early. Both benign and malignant melanoma appear in similar. So it is difficult to differentiate both. This is a main problem with the early skin cancer detection. Only an expert dermatologist can classify which one is benign and which one is malignant. The proposed scheme is using Wavelet Transformation for image improvement, denoising and Histogram Analysis and Proposed using classifies the type of approach for Skin Cancer using Artificial Neural Network (ANN) in approach for Skin Cancer. The extraction of texture features in the detected tumor has been achieved by using Gray Level Co-occurrence Matrix (GLCM).These features are given as the input to the Artificial Neural Network, Co-occurrence Matrix, and Back Propagation Network Classifier. It classifies the given data set into cancerous or non-cancerous. INTRODUCTION: Skin is the outermost covering of human body. It is a protective layer of the body which acts as first line of defense against foreign particles entering into the body. There are many diseases or conditions that affect the skin, one such abnormality occurring in skin is skin cancer. Normal cells grow in a controlled way such that new cells replace the old ones. But in the case of cancer, they grow in an abnormal way. Normal cells become cancerous due to the genetic disorders occurring in the nucleus of the cells by external or internal factors Skin cancer at its early stages can be cured. But when it is not recognized at its early stages, it begins to spread to other parts of the body and can be deadly. Skin cancer is collectively called as Melanoma. Melanoma is named after the cell from which it presumably arises, the melanocyte. It is the skin cell producing the melanin pigment, which provides protective shielding from Ultraviolet radiations. Melanoma is of two types: Benign Melanoma and Malignant Melanoma. Benign Melanoma is simply appearance of moles on skin. A normal mole is usually an evenly colored brown, tan, or black spot on the skin. It can be either flat or raised. It can be round or oval. Moles are generally less than 6millimetres. Malignant melanoma is the appearance of sores that cause bleeding. Malignant Melanoma is the deadliest from of all skin cancers. It arises from cancerous growth in pigmented skin lesion. If diagnosed at the right time, this disease is curable. But one of the main problems associated with skin cancer detection is the similarity in appearance of Benign and Malignant Melanomas at its early stages. Malignant melanoma starts as a small mole. Most people ignores it by thinking that, it is just a mole. But if it is unchecked, it starts spreading to the other parts of the body and become fatal. So an early detection is of utmost importance in the treatment of melanoma. International Journal of Emerging Technology in Computer Science & Electronics (IJETCSE) ISSN: 0976-1353 Volume 13 Issue 4 –MARCH 2015. 370 AUTOMATED EARLY SKIN CANCER DETECTION SYSTEM: