Face feature aggregation analysis self-learning method and system based on multiple algorithms

Abstract

The invention discloses a face feature aggregation analysis self-learning method and system based on multiple algorithms. The method comprises the following steps: monitoring a face photo and user basic information uploaded by a front-end face recognizer; decrypting the photo, and verifying the legality of the basic information of the user; key point information is detected; performing secondary verification on the user identity information; storing the photos and the feature values into a user feature tracking library; performing similarity calculation on the face feature values; storing in a user feature replacement library, and issuing the newest face photo and feature values regularly according to a service strategy; the front-end recognition device obtains user face base library information and replaces a local recognition library; the system comprises a background computing server, a face recognizer, a management system, an original photo acquisition module, a face detection module, a face recognition module, an aggregation analysis algorithm module and a self-learning replacement module. According to the method, the face feature information is dynamically adjusted along with the change of the time dimension, and the recognition accuracy and the recognition speed are improved.

Description

technical field [0001] The invention relates to image recognition technology, in particular to a multi-algorithm-based face feature aggregation analysis self-learning method and system. Background technique [0002] Face recognition technology in image recognition has achieved large-scale applications in many fields such as security monitoring in key areas, office attendance and access control, and high-speed rail ticket verification. As the establishment and update of the facial feature database in the application of face recognition technology is the basis for guaranteeing the accuracy of face recognition, the current common practice is for users to collect data at the time of initial registration, and then perform supplementary collection when recognition abnormalities occur , this method has cumbersome operation and untimely replacement, which will affect the user experience and even cause recognition errors, especially in application scenarios such as attendance and acc...

AI Technical Summary

Problems solved by technology

As the establishment and update of the facial feature database in the application of face recognition technology is the basis for guaranteeing the accuracy of face recognition, the current common practice is for users to collect data at the time of initial registration, and then perform supplementary collection when recognition abnormalities occur , this method has cumbersome operation and untimely replacement, which will affect the user experience and even cause recognition errors, especially in application scenarios such as attendance and access control in enterprise parks, because the accuracy requirements for using recognition are relatively low , there will be a situation where even if an error is made, it will not be processed for a long time

Images