Unlock instant, AI-driven research and patent intelligence for your innovation.

Human face distinguishing 2D main component analysis process based on minimum mean-square error criterion

A technology of minimum mean square error and principal component analysis, applied in the field of face recognition, can solve problems such as proof of rationality and discussion

Inactive Publication Date: 2007-10-03
罗仁泽
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Jian Y., Zhang D., Aledjandro F., et al. Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Patt. Anal. Mach. Intell., 2004, 26(1) : 131-137, 2DPCA is a pivot selection strategy given under the criterion of maximizing the overall scatter of the projected feature vector. This paper uses experiments to illustrate that selecting the first few pivot features can make the energy loss of the image very small , but it is not theoretically justified
In fact, since the 2DPCA method was proposed, people have not discussed this issue theoretically

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human face distinguishing 2D main component analysis process based on minimum mean-square error criterion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The technical solution of the present invention will be further described through specific implementation below.

[0057] We are in the ORL face database ( http: / / www.uk.research.att.com / facedatabase.html ) were tested. The ORL face database consists of 40 people, each with 10 images, a total of 400 face images. The size of the image is 112×92. For the 10 images of each person, there are changes in posture, expression, and facial details (such as whether to wear glasses); for some images, they may be acquired at different times.

[0058] In the experiment, we gave the recognition rate of the 2DPCA method on the ORL face database, the number of extracted pivot features, the running time, the average total energy of the sample image and the energy lost. Wherein, the set threshold value is 95%. The experimental results are shown in Table 1.

[0059] Number of samples per class /

[0060] It can be seen from the table that under the given threshold condition o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention belongs to the field of image processing, computer vision and pattern recognition technology, and is human face distinguishing 2D main component analysis process based on minimum mean-square error criterion. The 2D main component analysis process based on minimum mean-square error criterion has unique main element selecting strategy, minimal energy loss of image, minimal error between the reconstructed image and the original image. The present invention has less required characteristic main elements and high recognition precision.

Description

Technical field: [0001] The invention belongs to the technical fields of image processing, computer vision and pattern recognition, and in particular relates to a face recognition method. Background technique: [0002] In recent decades, face recognition has been a hot research topic in the fields of computer vision and pattern recognition. For the recognition problem, finding effective image features is the key to solving the problem. In previous studies, image features are mainly divided into: visual features, statistical features, transformation coefficient features and algebraic features. [0003] Two-dimensional principal component analysis (2DPCA) is a cutting-edge technology for image feature extraction, by Yang et al. in the article Jian Y., ZhangD., Aledjandro F., et al.Two-dimensional PCA: a new approach to appearance-based face representation and recognition.IEEE Trans.Patt.Anal.Mach.Intell., 2004, 26(1): 131-137. [0004] The 2DPCA method was proposed to overc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01C11/04
Inventor 罗仁泽冉瑞生
Owner 罗仁泽