Classification of Skin Disease Using Transfer Learning in Convolutional Neural Networks

Automatic classification of skin disease plays an important role in healthcare especially dermatology. Dermatologists can determine different diseases with the help android device and use Artificial Intelligence. Deep learning requires a lot time to train due number sequential layers input data involved. Powerful computer involving Graphic Processing Unit is ideal approach training process its parallel processing capability. This study gathered images 7 types prevalent Philippines for system. There are 3400 composed like chicken pox, acne, eczema, Pityriasis rosea, psoriasis, Tinea corporis vitiligo that was used testing convolutional network models. transfer using pre-trained weights from neural models such as VGG16, VGG19, MobileNet, ResNet50, InceptionV3, InceptionResNetV2, Xception, DenseNet121, DenseNet169, DenseNet201 NASNet mobile. The MobileNet model achieved highest accuracy, 94.1% VGG16 lowest 44.1%.