Face matching method, system and equipment based on SQL (Structured Query Language) and storage medium

Abstract

The invention discloses an SQL-based face matching method, system and device and a storage medium, and the method comprises the steps: obtaining an SQL statement, and distributing a matching task corresponding to the SQL statement to a plurality of data nodes; and controlling each data node to call a corresponding plug-in module, and executing the matching task according to the face data in the SQL statement to obtain and output a matching result. All nodes of the MPP database cluster can call the plug-in module, the plug-in module is utilized to directly call the comparison function of the SDK module through the SQL query statement to achieve face matching similarity calculation, application development is not needed, data processing steps are simplified, development difficulty is lowered, and efficiency is improved; meanwhile, the delay problem of network transmission can be avoided, the data storage amount is only limited by the disk space of the MPP database, and follow-up capacity expansion operation is facilitated; and each data node is connected with an authentication component, so that the legality of data access is realized based on access of certificate verification, and the security of data transmission is improved.

Description

technical field [0001] The invention relates to the field of database data access, in particular to an SQL-based face matching method, system, device and storage medium. Background technique [0002] In the past few years of the rapid rise of smart phones, its combination lock has undergone upgrades from digital passwords, gesture unlocking to fingerprint recognition, and has developed to today's iris recognition and face recognition. It can be expected that due to the popularity of full screens and the emergence of the safer and more convenient FaceID technology, in the near future, fingerprint recognition will also be abandoned by smartphone manufacturers and complete its historical mission. [0003] Face recognition is a biometric technology for identification based on human facial feature information. The input of the face comparison algorithm is two face features, and the output is the similarity between the two features. At present, face algorithm manufacturers gener...

AI Technical Summary

Problems solved by technology

[0004] Usually the SDK demo provided by the algorithm manufacturer is based on the C++ language, and some dll files, bin files, and model files are placed in the same directory as the dll. If non-C++ developers access it, they still need to write a lot of code by themselves, and the debugging efficiency is low. , high error rate

[0005] In addition, public cloud / private cloud APIs need to call multiple http interfaces, such as face picture data transmission, feature extraction, and feature comparison, to complete a comparison. The performance is low and the experience is poor; the data storage capacity is limited and the expansion cost is high; Data belongs to personal privacy. Generally speaking, SDK only provides docking for application development, and lacks consideration for the security of data in actual application scenarios.

Images