Classification of Melanoma using TransferLearning and Deep Learning NeuralNetworks
Vishal Goyal · NORMA · 2020
The world is suffering from many fatal skin disease, one such disease causing fatalities is Melanoma skin cancer which is being researched from the past many years. Different Deep learning Neural Networks have achieved optimistic results in identifying the Melanoma. However, due to the similar optics of malignant and benign tumor images, it becomes very difficult to get precise results and so a huge improvement is needed. This project helps the automatic classification of melanoma images using deep learning and transfer learning models. Image Augmentation and pre-processing are performed on the images for the model to achieve better accuracy and at last, all the applied models are evaluated based on accuracy and loss. After comparison, it was observed that MobileNet, LeNet, and ResNet achieved better accuracy as compared to CNN and AlexNet. Highest accuracy of 75.38% was achieved by MobileNet. Area: Deep Neural Network, AlexNet, LeNet, ResNet-50, MobileNet, CNN, Image Processing, BlackHat Filter, Adam Optimization.