Two-dimensional linear discrimination human face analysis identificating method based on interblock correlation
A face recognition and correlation technology, which is applied in the field of pattern recognition, can solve the problems of unfavorable face recognition, little help in determining the main component, and splitting the pixel correlation in local areas of the face.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0065] The following takes the FERET face database as an example to illustrate the implementation process of this method.
[0066] Choose 60 people in the FERET library, each with 6 images, a total of 360 images form the training and test face library, including faces under different expressions, light, occlusion, etc. The image size is 112×92.
[0067] Randomly select 3 images / person from the library for training, and the remaining 3 images / person for testing. The random sampling experiment was repeated 30 times, and the average recognition rate was taken as the final recognition rate. The specific implementation process is as follows:
[0068] 1. Database construction stage
[0069] (1) Image standardization
[0070] Preprocess the image, including light normalization and size normalization. After preprocessing, the gray levels of all images are unified to the standard level, and the gray levels are relatively clear (because of the histogram equalization). The image size after p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 