SKIN CANCER IMAGE DETECTION SYSTEM USING THE CONVOLUTIONAL NEURAL NETWORK MODEL

The development of science and technology (IPTEK) in the current era is growing very rapidly various fields such as industry, education, especially health sector. Many technologies can be used, one which artificial intelligence technology. This study aims to detect skin cancer images using CNN so that they efficient precise. research method uses convolutional neural network (CNN) method, namely image processing, a multilayer perceptron (MLP), neurons data are propagated two dimensions. Because this has high accuracy compared fuzzy k-nearest neighbors. results there 7 classes including actinic keratosis, basal cell carcinoma, dermatofibroma, benign melanocytic nevi, vascular lesions melanoma. From testing with rate 99%, 96%, 98%, 100%, 99% respectively. With conclusion produces an average 98% Mobilnetv2, Resnet50 VGG16 models, means model proven more accurate. So it hoped detection system applied for world health.