Face analysis method and device based on adaptive edge enhancement, and storage medium

The invention discloses a face analysis method and device based on adaptive edge enhancement, and a storage medium. The method comprises the following steps: constructing a lightweight deep convolutional neural network; the neural network comprises an encoder, an adaptive edge enhancement module and a decoder; the encoder encodes an input face image to obtain a face feature map with segmentation features; the adaptive edge enhancement module extracts edge features corresponding to the face feature map to obtain a face segmentation map with the edge features; the decoder fuses the segmentation features and the edge features through add operation to obtain segmentation features with adaptive edge features, so that the edge segmentation fineness can be improved; meanwhile, face analysis can be detected in real time at a mobile terminal by adopting a lightweight model, so that the experience feeling of the user in the scene of making up and the like is improved. 本发明公开了一种基于自适应边缘增强的人脸解析方法、装置及存储介质，其包括以下步骤：构建轻量级的深度卷积