Biocharacteristics fusioned identity distinguishing and identification method

Abstract

This invention relates to a sorter integration and mode identification field characterizing in obtaining characters of man-face, iris, on-line signature and off-line handwriting of a user by various collecting devices then sending them to corresponding certification sub-modules to pick up the characters and match with the molding boards and outputting the matched marks to be normalized and sent to an identification combined module to get the final identification result by confidence integration or sent to a certification module to be imaged to a multi-dimension space to be sorted by a sorter to get a final result or to be certified and combined to get the final identification result.

Description

technical field [0001] The invention belongs to the field of classifier integration and pattern recognition, but it also includes the contents of the fields of face recognition, iris recognition and character recognition. Background technique [0002] Identity authentication is a difficult problem in protecting information security. Traditional authentication methods often use passwords, certificates or some existing specific knowledge as the user's authority to enter the system. However, because the password is easy to be forgotten and modified, and the certificate is inconvenient to carry and easy to lose, there are major defects and potential safety hazards in the traditional authentication method. With the increasing demand in the field of security, automatic biometric authentication and identification systems are becoming more widespread and efficient. Many banks, airports and other areas have already adopted biometric-based products. Commonly used biometric features...

AI Technical Summary

Problems solved by technology

However, these systems also face many problems. For example, the face recognition system is very sensitive to factors such as illumination, posture and expression; It is likely that the quality of the collected user's iris sample is too poor or the user is invalid due to ophthalmic diseases; Online signature samples have an impact; and for offline handwriting recognition systems, even for the same user, the signature and handwriting will have large differences in different periods and in different states of the user, not to mention the challenges it faces. The problem of counterfeiting and counterfeiting

Images