An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network

TL;DR

This paper introduces an automatic facial acne diagnosis method using convolutional neural networks, incorporating skin detection and multi-class classification, with evaluation showing effectiveness of pre-trained VGG16 features.

Contribution

The study proposes a novel CNN-based approach with specialized classifiers for skin detection and acne classification, improving on previous methods' classification types.

Findings

VGG16 outperforms custom CNN in feature extraction.

Pre-trained VGG16 classifiers show high robustness.

Effective skin and acne classification demonstrated.

Abstract

In this paper, we present a new automatic diagnosis method of facial acne vulgaris based on convolutional neural network. This method is proposed to overcome the shortcoming of classification types in previous methods. The core of our method is to extract features of images based on convolutional neural network and achieve classification by classifier. We design a binary classifier of skin-and-non-skin to detect skin area and a seven-classifier to achieve the classification of facial acne vulgaris and healthy skin. In the experiment, we compared the effectiveness of our convolutional neural network and the pre-trained VGG16 neural network on the ImageNet dataset. And we use the ROC curve and normal confusion matrix to evaluate the performance of the binary classifier and the seven-classifier. The results of our experiment show that the pre-trained VGG16 neural network is more effective in extracting image features. The classifiers based on the pre-trained VGG16 neural network achieve the skin detection and acne classification and have good robustness.