DIAGNOSIS AND DETECTION OF SKIN BURN ANALYSIS SEGMENTATION IN COLOUR SKIN IMAGES

Abstract

Skin image is in that the burned skin and non- burned images has to be classified. It is a deadly form of burning. Skin burn may appear as malignant or benign form. 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. 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. Skin burns are the deadly form of cancers in humans. If skin burns is detected at early stages, it can be cured completely. So an early detection of skin cancer can save the patients. Skin burns are of two types- Benign and Malignant Melanoma. Benign melanoma is not a deadly condition, but malignant melanoma is a deadly form. Both resemble same in appearance at the initial stages. Only an expert dermatologist can classify which one is benign and which one is malignant. The SVM based Classification methodology uses Image processing techniques. Main advantage of this computer based SVM classification is that patient does not need to go to hospitals and undergo various painful diagnosing techniques like Biopsy.