Method for automatically positioning characteristic points of three-dimensional face

Abstract

The invention discloses a method for automatically positioning the characteristic points of a three-dimensional face, which comprises the following steps of: (1) positioning the pose of a three-dimensional face model; (2) dividing the subspace of a top point; (3) counting a histogram of the subspace; (4) acquiring the characteristic descriptor of the top point; (5) constructing a characteristic point template of the three-dimensional face; and (6) positioning the characteristic points of the three-dimensional face. The invention has the advantages of breaking through the limitation that only a few characteristics of the three-dimensional face can be automatically positioned through the description of partial curved surface and increasing the accuracy and the generality of the method for positioning the characteristic points of the three-dimensional face.

Description

technical field [0001] The invention relates to a method for automatically locating feature points of a three-dimensional human face based on template matching, in particular to a method for describing local features of a three-dimensional curved surface based on space division and histogram statistics, and improving the automatic positioning of feature points of a three-dimensional human face General and precise methods. Background technique [0002] With the development of 3D imaging technology and 3D acquisition equipment, 3D data acquisition has become more concise and accurate, which has promoted the rapid development of 3D face processing. Among them, the feature points of the 3D face are the reference points for the precise alignment of face data, as well as the anchor points of some algorithms and become one of the limiting conditions for the algorithm to be solved. It is one of the core tasks of the 3D face preprocessing stage. [0003] In view of the fact that the...

AI Technical Summary

Problems solved by technology

[0003] In view of the fact that the accuracy of the feature point positioning of the 3D face will directly affect the accuracy of some 3D face methods, manual calibration is often required, which has become one of the bottlenecks restricting the fully automated processing of the 3D face application field.

The existing automatic positioning method of feature points of 3D face is based on the structural features of the face surface and designed for specific feature points. It can only automatically locate a few face feature points, such as positioning based on curvature and silhouette. methods, etc., obviously cannot meet the actual needs of some research fields

At the same time, 3D data often contains a lot of noise and outliers, which also limits the accuracy of some methods for automatic positioning of feature points of 3D faces.

Images