Living body recognition method, storage medium, and computer device
摘要
說明書
S304. Extract facial feature data of a facial image in the target image.
The facial feature data is data that is used to reflect facial features. The facial feature data reflects one or more types of feature information such as a person's gender, a facial profile, a hairstyle, glasses, a nose, a mouth, and a distance between facial organs.
In an embodiment, the facial feature data may include facial texture data. The facial texture data reflects texture features and pixel point depths of facial organs such as a nose, ears, eyebrows, a cheek, or a lip. The facial texture data may include distribution of color values of pixel points of the facial image and distribution of luminance values of pixel points of the facial image.
Specifically, after acquiring the target image, the server may extract facial feature data of the facial image in the target image according to a preset image feature extraction policy. The preset image feature extraction policy may be a preset image feature extraction algorithm or a pre-trained feature extraction machine learning model.
S306. Perform face liveness recognition according to the facial feature data to obtain a first confidence level. The first confidence level denotes a first probability of recognizing a face liveness.
