Two-dimension human face image recognizing method
A face image and recognition method technology, which is applied in the field of pattern recognition and computer vision, can solve problems such as time-consuming, time-consuming, and inability to overcome the influence of illumination changes on images, and achieve the effect of increased speed and high recognition rate
- Application Information
AI Technical Summary
Problems solved by technology
 The face database in the present embodiment is taken from the three-dimensional face data of 200 Europeans, and each face data includes about 100,000 vertices, and the coordinates (x, y, z) and texture (R, G, B) Known.
 The two-dimensional face image recognition method in this embodiment includes: building a three-dimensional face deformation model, three-dimensional reconstruction of the face image, generating a virtual image of posture and illumination changes, design of a change-limited classifier, and face image recognition.
 As shown in Figure 1, the corresponding steps are specifically introduced below:
 Step 101: Establish a 3D face deformation model based on a known 3D face database.
 The specific process includes:
 Step 101a: Obtain raw data such as coordinates (x, y, z) and textures (R, G, B) of vertices of all faces in the database, and perform quantization processing on the raw data.
 A variety of methods ca...
 In this embodiment, two face databases are taken as examples to illustrate the process of two-dimensional face image recognition in the present invention.
 Face database 1 is a subset of the CMU PIE face database, which contains 67 facial images, each with 8 poses. Use a frontal face image for registration. The database is a two-dimensional image database used for data input in the registration phase.
 The second face database is a 3D face database from 488 Chinese people, which is obtained by a 3D scanner. After preprocessing, a 3D deformation model of a face can be established according to Step 101 of Embodiment 1. The specific implementation of the following process is divided into three stages: training, registration, and recognition, as shown in Figure 6, Figure 7 and Figure 8. The specific process is introduced as follows:
 Step 201: training phase.
 For the input frontal face, the face area is automatically detected first.
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction