Face attendance checking method, device and equipment based on self-learning and storage medium

Abstract

The invention discloses a face attendance checking method, device and equipment based on self-learning and a computer readable storage medium. The method comprises the following steps: carrying out face image quality analysis on continuous frame number image data to obtain a plurality of frames of to-be-identified face images, carrying out feature point positioning on the to-be-identified face images, extracting a face feature vector in each frame of to-be-identified face image through a preset convolutional neural network model, and storing the face feature vectors in a face feature list; clustering the face feature list to obtain a face feature matrix; carrying out matching analysis on the face feature vectors of each row in the face feature matrix by adopting a pre-constructed KNN modelto obtain a matching result of each face feature vector in each row, and storing the matching result into an identification similarity matrix; and according to the recognition similarity matrix, a face attendance result is obtained, and face recognition is carried out on multi-person multi-frame images by adopting an image quality analysis method in combination with a face feature clustering method, so that the face recognition precision in the face attendance process can be effectively improved.

Description

technical field [0001] The present invention relates to the field of computer image processing, in particular to a method, device, equipment and computer-readable storage medium for face attendance checking based on self-learning. Background technique [0002] The traditional attendance method is fingerprint check-in. Fingerprint check-in will undoubtedly cause congestion due to queuing during the peak hours of work. With the continuous advancement of artificial intelligence technology, face-based attendance has become a reality. An important technology involved in face attendance is face image matching. [0003] At present, in the process of using ordinary cameras to check attendance, many people often appear in the camera at the same time, and the camera will capture all the frames of the attendanceee from entering the door to disappearing from the camera. In addition, due to weather changes and the change of wearing glasses and hats by the attendees, the recognition rate...

AI Technical Summary

Problems solved by technology

[0003] At present, in the process of using ordinary cameras to check attendance, many people often appear in the camera at the same time, and the camera will capture all the frames of the attendanceee from entering the door to disappearing from the camera. In addition, due to changes in the weather and changing glasses and hats by the attendees, the recognition rate will decrease and the recognition results will be diversified.

Images