Human image identification method and human image identification apparatus

Abstract

The invention provides a human image identification method and a human image identification apparatus. The human image identification method comprises: acquiring facial image data of a to-be-identified user; comparing the acquired facial image data and facial image data of each user stored in a database one by one, and calculating a matching degree score of each comparison result; comparing a maximum value in the matching degree scores with a first threshold, and when the maximum value is less than the first threshold, optimizing the maximum value; and comparing an optimized result with the first threshold, and when the optimized result is greater than or equal to the first threshold, determining that the to-be-identified user is matched with a user stored in the database and corresponding to the maximum value.

Description

technical field

[0001] The present invention relates to a portrait recognition method and a portrait recognition device, in particular to a portrait recognition method and a portrait recognition device which improve the portrait recognition rate. Background technique

[0002] In the portrait recognition system, portrait recognition is performed by calculating the matching degree between the facial image of the user to be recognized and the facial images of each user stored in the database. For the degree of match represented by a score, a higher score indicates a better match. If the score representing the degree of matching is greater than or equal to a certain threshold, it is considered that the user to be identified is the same person as the corresponding user stored in the database.

[0003] But this score will be affected by objective conditions such as lighting, angle, clarity, etc., which will affect the result of the judgment. At present, some methods have been pr...

Images