In-Vivo Skin Capacitive Image Classification Using AlexNet Convolution Neural Network

Abstract

Skin capacitive imaging is a novel technique which has been developed for skin hydration and skin solvent penetration measurements. This research is to assess the performance of deep learning in in-vivo skin capacitive image analysis using AlexNet model. The image classifier has been trained by using pretrained model to implement the specific feature extraction, prediction and classification specifically for the skin characteristics such as hydration level, skin damage level etc. There are over 1000 skin capacitive images used in this study. The objectives of the research are: feature extraction implementation using the pretrained model AlexNet; accuracy assessment of the model; and further improve the system for multiple features classification. The image classification programme shows a good result which has accuracy over 0.98, and the test images were classified correctly comparing with the experimental results of skin hydration, skin damaged level and the gender of the volunteers.