Face recognition method, device and mobile terminal capable of recognizing face

Abstract

The invention discloses a face recognition method and device. The method comprises collecting images including a face image; acquiring facial features of a face in the images; matching the acquired facial feature in a facial feature database, and determining a match range, a mismatch range or an to-be-recognized range, to which the match result belongs; sending a target person recognition prompt information if the match result belongs to the match range; sending a non-target person prompt information if the match result belongs to the mismatch range; and returning and executing the step of collecting images including the face image until detecting an end instruction or sending the target person recognition prompt information and the non-target person prompt information if the match result belongs to the to-be-recognized range. According to the invention, a processor can recollect the images until the image is recognized accurately when the match result belongs to the to-be-recognized range resulting from the fact that the camera picked up a blur image or the deflection angle between the target person and the camera exceeds a definite angle.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition method, device and mobile terminal capable of recognizing faces. Background technique [0002] As we all know, except for twins and multiple births, the probability of two identical faces is less than one in 70 trillion. Even twins and multiple births will be affected by the acquired environment, climate, and life. Therefore, face recognition technology is a main direction of biometric recognition technology. [0003] In order to recognize faces conveniently, the existing technology provides a face recognition method, which uses a camera to collect images containing faces in the field of view, and then sends the collected images to a computer for image processing to obtain face images. The eigenvalues ​​are finally compared with the eigenvalues ​​in the database to recognize faces. [0004] However, in this solution, the camera collects images at one time. If ...

AI Technical Summary

Problems solved by technology

[0004] However, in this solution, the camera collects images at one time. If the image is blurred because the target person is far away from the camera, or the light is too bright or too dark, the image is overexposed or the brightness is not enough, resulting in blurred images. Clearly, even if the deflection angle between the target person and the camera exceeds the limited angle, the feature value extraction of the face is insufficient, which will lead to the failure of the recognition, and the target person may escape detection by luck.

[0005] In addition, the field of view of the camera can only cover a certain range, and if the target deliberately bypasses the field of view of the camera, it can easily escape detection

Images