Face identification method and system based on multi-visual-angle typical correlation analysis
A typical correlation analysis and face recognition technology, applied in the field of face recognition, can solve problems such as unfavorable discovery of multi-view data structure information, unsatisfactory face recognition effect, poor application effect, etc., to reduce recognition calculation Quantity, good recognition effect, and effect of improving recognition accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] Embodiment 1. The present invention proposes a face recognition method based on multi-view canonical correlation analysis. Refer to figure 1 , including the following steps:
[0049] S1. Preprocessing the face image used for training to obtain low-dimensional multi-view face image information;
[0050] S2. For the preprocessed face image information, calculate the Hessian matrix of each perspective and the Hessian matrix between any two perspectives; wherein, the Hessian matrix contains local information between multi-view data that is finer than the Laplacian matrix Correlation information is more conducive to discovering structural information hidden in multi-view data;
[0051]S3. Based on the above-mentioned Hessian matrix, calculate the covariance matrix of each viewing angle and between two viewing angles respectively, so that the covariance matrix contains the required local correlation information;
[0052] S4. Construct a projective space model on the basis o...
Embodiment 2
[0067] Embodiment 2. A face recognition system based on multi-view canonical correlation analysis, such as Figure 5 shown, including:
[0068] Image storage module: to obtain face image information, said face image information includes face images for training and face images to be identified;
[0069] Image processing module: use feature vectors to represent the acquired face images;
[0070] Model building module: preprocess the face image for training represented by the vector to obtain low-dimensional multi-view face image information, and then analyze the face image according to the multi-view face image information to obtain the projection space;
[0071] Classification and recognition module: project the multi-view face image information in the obtained projection space, and then classify and recognize the face image to be recognized
[0072] First, the face image information is input to the image storage module, and the face image information includes a face image f...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 