Three-dimensional face identification method with topology robustness

Abstract

The invention discloses a three-dimensional face identification method with topology robustness. The three-dimensional face identification method with the topology robustness comprises the following steps of S1, carrying out preprocessing on three-dimensional face data in a test sample and three-dimensional face data of a training set and a test set in a three-dimensional face database, S2, building a model (X, dx) of a preprocessed three-dimensional face in a metric space, S3, calculating the similarity of the three-dimensional face by using the discretization Hausdorff distance as the similarity criterion of appearance matching of the three-dimensional face, and S4, determining a three-dimensional face identification result. According to the three-dimensional face identification method with the topology robustness, due to the facts that complementation between the advantages of the Euclidean distance method and the advantages of the geodesic distance method is achieved, a new ranging method with geometry meaning, namely, the dispersion distance method is formed in a combined mode, the dispersion distance can show the average distance between two points on a curved surface instead of only showing the shortest path, and the topology robustness is achieved, the geometric structural characteristics of the face can be kept, and the problem that the identification rate is reduced due to changes of expressions and changes of topology geometric structures is completely solved.

Description

technical field [0001] The invention relates to a topologically robust three-dimensional face recognition method, which is specifically a three-dimensional face recognition method that transforms a three-dimensional face into a metric space composed of scattered distances, and performs shape matching through similarity calculation to complete recognition. method. Background technique [0002] Although image-based two-dimensional face recognition technology is becoming more and more mature and has achieved good recognition results under certain constraints, experimental studies have shown that changes in illumination, posture, makeup, expression, age, etc. will significantly reduce Performance of 2D face recognition algorithms. The geometric structure of the face reflects important and unique personal identity information, which can be regarded as the key basis for the robustness and accuracy of 3D face recognition. Generally speaking, the Euclidean distance is used to des...

AI Technical Summary

Problems solved by technology

However, in the process of mapping the geometric structure of the face from the high-dimensional non-Euclidean space to the low-dimensional Euclidean space, the topological connectivity in the geometric structure of the three-dimensional face is affected by the change of the coordinate system, which makes the geodesic distance change greatly. The ground distance changes greatly and loses the robustness of the internal geometric structure of the face, and loses the robustness of the geodesic distance to expression changes

As a conclusion, it is theoretically impossible to map the geometric shape structure in the metric space to the finite-dimensional Euclidean space without distorting the topological geometry structure of the shape

In addition, the introduction of topological noise due to lack of data in the process of acquiring face data by 3D scanning cannot be fundamentally avoided.

Images