Early Detection of Skin Cancer Using Melanoma Segmentation technique

The significance of pattern recognition techniques is widely enhanced in image processing and medical applications. Thus, lesion segmentation method is an essential technique of pattern recognition algorithms to detect the melanoma skin cancer in patients at earliest stage, otherwise, in further stages it becomes one of the deadliest disease and its mortality rate is very high. Therefore, a precise melanoma segmentation technique is introduced based on the Gradient and Feature Adaptive Contour (GFAC) model to detect melanoma skin cancer in earliest stage and diagnosis of dermoscopic images. In the proposed image segmentation technique pre-processing and noise elimination techniques are introduced to decrease noise and make execution faster. This technique helps in separating the required entity from the background and gather the information from the adjacent pixels of similar classes. Multiple Gaussian distributed patterns are adopted to extract efficient features and to get precise segmentation. The proposed GFACmodel is noise free and consist of smoother border. The segmentation model efficiency is tested on PH2 dataset. The superiority of the proposed modified gradient and feature adaptive contour model can be verified against various state-of-art-techniques in terms of segmented image, error reduction and efficient feature extraction.