Finding the Differences in Capillaries of Taste Buds between Smokers and Non-Smokers Using the Convolutional Neural Networks

Taste function and condition may be a tool that exhibits rapid deficit to impress the subject with an objectively measured effect of smoking on his/her own body, because smokers exhibit significantly lower taste sensitivity than non-smokers. This study proposed visual method measure capillaries buds capillaroscopy classified difference between non-smokers through convolutional neural networks (CNNs). The dataset was collected from 26 human subjects low high magnification directly; which 13 were smokers, other acquired consisted 2600 images. results gradient-weighted class activation mapping (grad-cam) enabled us understand in Through results, it found CNNs gave good performance 79% accuracy. It discussed there shortage extracted features when conventional methods such as structural similarity index (SSIM) scale-invariant feature transform (SIFT) used classify.