Three-dimensional human ear recognition method based on key point and local feature

Abstract

The invention discloses a three-dimensional human ear recognition method based on key points and local features, which comprises the following steps: (1) carrying out target detection on a two-dimensional side face image with background information, obtaining a square human ear region and extracting three-dimensional point cloud of a corresponding region; (2) carrying out key point detection in the three-dimensional human ear point cloud according to the internal shape signature characteristics; (3) performing iterative closest point registration on the extracted key points and human ear key points in a standard posture, and cutting by using a cuboid template to remove redundant areas such as skin and hair; (4) extracting a neighborhood point set around the key point, and calculating a feature vector of a covariance matrix as a local feature; and (5) removing the mismatching point pairs, and finally measuring the similarity of the two ears by using the number of successfully matched key points. According to the method, redundant areas such as skin and hair around human ears can be effectively removed, the key points and the local characteristics can comprehensively describe the structural characteristics of the three-dimensional human ears, and the recognition performance is high.

Description

technical field [0001] The invention belongs to the technical field of human ear recognition, in particular to a three-dimensional human ear recognition method based on key points and local features, in particular to a human ear recognition method using the local features of key points on the surface of the human ear. Background technique [0002] In modern society, more and more people pay more and more attention to accurate and reliable personal identity verification. Identity verification has important applications in many occasions, such as access control systems, video surveillance, and human-computer interaction. Biometric recognition is a classic problem in the field of machine vision and pattern recognition, and human ear recognition technology is a research hotspot in recent years. Compared with other biological characteristics such as human face, human ear is more similar to rigidity and is not affected by changes in expression, age and makeup, etc. Influenced by v...

AI Technical Summary

Problems solved by technology

[0003] 3D human ear recognition uses the spatial shape information of the human ear for identity authentication, and is not affected by factors such as lighting, makeup, and expression. Compared with face recognition, it has greater advantages, but it still faces challenges brought about by occlusion problems. It will cause the loss of the three-dimensional data of the human ear and affect the recognition effect

Images