Method for adjusting universal three-dimensional human face model

Abstract

The invention discloses a method for adjusting a universal three-dimensional human face model, belongs to the technical field of computer image processing, and mainly relates to three-dimensional human face reconstruction technology in three-dimensional human face recognition technology in biological feature recognition. Based on the universal three-dimensional human face model, the method adjusts the three-dimensional human face model by estimating three-dimensional coordinates of human face feature points in two orthogonal two-dimensional human face images, and finally obtains a three-dimensional specific human face model. The method applies an active shape model, Procrustes analysis and symmetry structural feature of a human face to the process of adjusting the universal three-dimensional human face model. The method estimates the human face feature points through the active shape model, and adjusts the three-dimensional human face model through the Procrustes analysis and the symmetry structural feature of the human face. Compared with common methods based on images, the method of the invention not only improves the accuracy of adjusting the model, but also improves the speed of adjusting the model in certain degree, and has strong commonality in three-dimensional human face reconstruction based on the images.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and mainly relates to the three-dimensional human face reconstruction technology in the three-dimensional human face recognition technology in biological feature recognition. Background technique [0002] As one of the biometric authentication technologies, face recognition has attracted extensive attention from researchers because it is not invasive to the person and can complete the identification and authentication process without the authentication object being aware of it. At present, some commercial face recognition systems have also appeared. However, when the imaging conditions are uncertain, such as different lighting conditions and different postures, the performance of the face recognition system may drop to 60% to 70%. In many practical application conditions, the performance of each recognition system often falls short of to 50%. Therefore, eliminating the impact ...

AI Technical Summary

Problems solved by technology

Although this method has high precision, it requires expensive 3D scanning equipment, and the amount of calculation is very large, so it is not suitable for practical applications

Images