Face identification method and device

Abstract

The present invention discloses a face identification method. The method comprises the following steps: receiving the face image of a user to be identified, and extracting a characteristic vector from the face image; matching the characteristic vector and at least two pre-stored compression vectors, and calculating the similarity of the characteristic vector and each compression vector, wherein the compression vector is obtained by compressing at least two corresponding characteristic vectors extracted from at least two face images of the same user; obtaining the maximum value in the at least two calculated similarities; and outputting the user information corresponding to the compression vector corresponding to the maximum value. The invention further discloses a face identification device. The face identification method and device are able to improve the speed and the accuracy of face identification.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition method and device. Background technique [0002] Face recognition is widely used in fields such as security monitoring, secure payment, and clocking in and out of get off work. At present, face recognition is generally performed by matching the face features of the input image with the face features stored in the database. [0003] In the prior art, in order to improve the recognition accuracy, it is sometimes necessary to collect multiple facial photos for each person to obtain more detailed facial information. However, the diversity of individual samples will make the distinction between individuals in the overall sample worse, resulting in a high misjudgment rate in the recognition process, and when the number of photos collected by each person increases, the number of corresponding sample features will also increase. becomes larger, which leads to longer t...

AI Technical Summary

Problems solved by technology

However, the diversity of individual samples will make the distinction between individuals in the overall sample worse, resulting in a high misjudgment rate in the recognition process, and when the number of photos collected by each person increases, the number of corresponding sample features will also increase. becomes larger, which leads to a longer traversal matching time in the face recognition process, affecting the recognition speed

Images