Face recognition algorithm evaluation method and device

Abstract

The embodiment of the invention provides a face recognition algorithm evaluation method and a device, and relates to the technical field of computer information processing. The method comprises the following steps of: calculating a distance between a preset small image position point of a face small image recognized by a face recognition algorithm and a preset annotation position point of an annotated face on a corresponding frame image in a test video sequence where the face small image is located; and determining whether the small human face image is matched with the marked human face on theframe image where the small human face image is located. When the distance is smaller than or equal to a certain preset value, a fact that the face small image is matched with the marked face is determined; and when the distance is greater than a certain preset value, a fact that the small human face image is not matched with the marked human face is determined. Furthermore, by calculating the capture rate, the multi-capture rate, the false shooting rate and the face optimization rate of the face recognition algorithm for the faces in the test video sequence, the method is higher in evaluation accuracy and more comprehensive in evaluation.

Description

technical field [0001] The invention relates to the technical field of computer information processing, in particular to a face recognition algorithm evaluation method and device. Background technique [0002] Face recognition technology is a biometric recognition technology based on human facial feature information. It uses a camera or camera to collect images or video streams containing faces, and automatically detects and tracks faces in the images, and then A series of related technologies for facial recognition of detected faces. [0003] Face recognition algorithm is the core tool of face recognition technology. At present, there are many face recognition algorithms, and the performance of the algorithms varies. When the performance of the algorithm is too poor, it will lead to a high false detection rate. Therefore, before the face recognition algorithm is used in face image recognition, the algorithm performance evaluation will be performed to ensure the algorithm p...

AI Technical Summary

Problems solved by technology

[0003] Face recognition algorithm is the core tool of face recognition technology. At present, there are many face recognition algorithms, and the performance of the algorithms is different. When the performance of the algorithm is too poor, it will lead to a high false detection rate.

Therefore, before the face recognition algorithm is used in face image recognition, the algorithm performance evaluation will be performed to ensure the algorithm performance, but the evaluation methods in the prior art have low accuracy and incomplete evaluation

Images