Living body recognition method, storage medium, and computer device
摘要
說明書
The confidence level is in one-to-one correspondence to the target image, and is used to indicate a confidence level of the target image being a live facial image. A live facial image is an image obtained by acquiring an image of a live face/person. A higher confidence level indicates a higher probability of the corresponding target image being a live facial image. In other words, a higher confidence level indicates a higher probability of the target image being an image obtained by acquiring an image of a live face/person. Understandably, the first confidence level here and the second confidence level to be mentioned later are both confidence levels, but correspond to confidence levels under different feature data conditions.
Specifically, the server may classify the target images according to the extracted facial feature data. When the extracted facial feature data matches the facial feature data of a live facial image, the target image is classed as a live facial image. When the extracted facial feature data matches the facial feature data of a non-live facial image, the target image is classed as a non-live facial image. The first confidence level indicates the degree of matching between the extracted facial feature data and the facial feature data of a live facial image. The higher the degree of matching between the extracted facial feature data and the facial feature data of a live facial image is, the higher the first confidence level will be, that is, the target image is more likely to be a live facial image.
