Human eye image recognition method and device based on image processing and self-service terminal

Abstract

The invention provides a human eye image recognition method and device based on image processing and a self-service terminal. The method comprises the steps: obtaining to-be-detected face image data of a user, and obtaining eye image data from the to-be-detected face image data through an eye detection model; extracting a plurality of key point positions in the eye image data through a feature extraction method; according to the distance between the key point positions, matching the eye image data with face image data stored by a user in a predetermined face database to obtain matching similarity; and obtaining a human eye image recognition result of the to-be-detected human face image data according to a comparison result of the matching similarity and a preset threshold.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to an image processing-based human eye image recognition method, device and self-service terminal. Background technique [0002] During the epidemic, users need to take off their masks when using self-service teller machines or other smart devices to conduct transactions. During the epidemic, there is a greater risk, and in daily life, users may also wear masks due to flu, facial injuries, etc. Due to the situation, there are certain risks and inconveniences in allowing users to take off their masks during the transaction. [0003] Traditional facial recognition cannot identify and confirm the user's identity when the user covers part of the face. Therefore, the industry needs a method that can reduce unnecessary risk sources and improve the fluency of verification during the process of user facial recognition. The method can reduce the infection or unnecessary troubles caused by th...

AI Technical Summary

Problems solved by technology

[0002] During the epidemic, users need to take off their masks when using self-service teller machines or other smart devices to conduct transactions. During the epidemic, there is a greater risk, and in daily life, users may also wear masks due to flu, facial injuries, etc. There are certain risks and inconveniences in allowing users to take off their masks during transactions

[0003] Traditional facial recognition cannot recognize and confirm the user's identity when the user covers part of the face. Therefore, the industry needs a method that can reduce unnecessary risk sources and improve the fluency of verification during the process of user facial recognition. The method can reduce the infection or unnecessary trouble caused by the above situation as much as possible, improve the safety of identity recognition, and improve the comfort of user experience

Images