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

Automatic human face identification method based on personal image

A recognition method, automatic face technology, applied in the field of automatic face recognition, to achieve the effect of improving performance

Inactive Publication Date: 2005-07-06
NANJING UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem in the prior art that each object to be identified needs multiple images to perform face recognition, and to provide a method for automatic face recognition that only needs one image for each object to be identified. To assist in improving the performance of digital face image detection and recognition devices

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
  • Automatic human face identification method based on personal image
  • Automatic human face identification method based on personal image
  • Automatic human face identification method based on personal image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0010] like figure 1 As shown, the digital face image detection and recognition device obtains a digital grayscale image through a digital image input device, and then uses eye positioning information to obtain a face area. Then it is processed by the recognition mechanism, which usually includes feature extraction of the face image and comparison with the existing images in the face image database.

[0011] The method of the present invention is as figure 2 shown. Step 10 is the initial action. Step 11 judges whether the recognition mechanism has been trained, if so, execute step 17; otherwise, execute step 12. Step 12 acquires a training image. Step 13 generates the added projection image of the image, and the added projection image is the image obtained after processing with the specially designed processing method of the present invention, and this step will be combined in the following part image 3 Make a specific introduction.

[0012] Although there is only one ...

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 invention discloses an automatic face recognition method based on one image per person, which includes obtaining a digital grayscale image through a digital image input device and using eye positioning information to obtain the face area. The method is characterized in that the method includes the following steps: (1) If the recognition mechanism has not been trained well, perform step (2), otherwise go to step (4); (2) Generate a projected image of the training image; (3) Use principal component analysis technology to generate features of the projected image space; (4) receive the image to be recognized; (5) generate the projected image of the image to be recognized; (6) compare the projected image of the image to be recognized and the projected image of the training image in the projected image feature space; (7) Use the object corresponding to the training image with the greatest comparison similarity as the recognition result. The advantage of the present invention is that only one image per person can be used for automatic face recognition, thereby assisting in improving the performance of the digital face image detection and recognition device.

Description

1. Technical field [0001] The invention relates to a digital face image detection and recognition device, in particular to a method for automatic face recognition that only requires one training image for each object to be recognized. 2. Background technology [0002] The digital face image detection and recognition device can be widely used in identity document recognition, building access control, computer login control, credit card holder identification, criminal tracking, accident detection, etc. Compared with the method of identity identification using human features, it is more friendly and convenient to use face for identification. However, in some specific applications, such as the public security organs chasing fugitives, there is often only one image available for each object to be identified, and the current digital face image recognition technology needs to prepare multiple images for each object to be identified for use. This makes it difficult for existing dig...

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 Patents(China)
IPC IPC(8): A61B5/1171G06K9/00
Inventor 周志华
Owner NANJING UNIV