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

Face recognition method and system

A face recognition system and face recognition technology, which is applied in the field of biometric identification, can solve problems such as difficult to judge and decline in the accuracy of face recognition, and achieve the effect of precise recognition and high recognition

Active Publication Date: 2015-12-23
CHINA UNITED NETWORK COMM GRP CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the existing grayscale comparison method, the results obtained when the face is compared in the same environment are relatively accurate, but if the environment change

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
  • Face recognition method and system
  • Face recognition method and system
  • Face recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a schematic flow chart of a face recognition method provided by Embodiment 1 of the present invention, such as figure 1 As shown, the method includes the following steps:

[0026] Step 101. Extract respectively a plurality of feature curves of each face image to be recognized and a standard face image, the feature curves can characterize a face, and any feature curve extracted from each face image to be recognized is consistent with that from Corresponding to a characteristic curve extracted from the corresponding position of the standard face image.

[0027] Wherein, those skilled in the art can understand that the number of feature curves extracted from each face image to be recognized is the same as that of the standard face image. The characteristic curve capable of representing a human face refers to a curve capable of representing and distinguishing human face features. A standard face image can be understood as a face template.

[0028] The fol...

Embodiment 2

[0069] figure 2 A schematic flow chart of a face recognition method provided by Embodiment 2 of the present invention, as figure 2 As shown, the method includes the following steps:

[0070] Step 201. Set the colors of pixels of non-face color in each face image to be recognized to be the same color.

[0071] Specifically, the color of each pixel in each face image to be recognized is compared with the face color comparison table in the database, and the face color comparison table covers all preset colors of human faces and their corresponding colors. Code, the code is a six-digit hexadecimal value, for all pixels whose color does not meet the face color comparison table, its color is set to the same color, for example, it is uniformly set to white, so that each face image to be recognized Noise removal of non-face color in to eliminate interference.

[0072] Step 202. Extract multiple characteristic curves of each face image to be recognized and the standard face image ...

Embodiment 3

[0102] image 3 A schematic structural diagram of a face recognition system provided by Embodiment 3 of the present invention, as shown in image 3 As shown, the system includes a first extraction module 21 , a first calculation module 31 and a first determination module 41 .

[0103] The first extraction module 21 is used to respectively extract a plurality of feature curves of each face image to be recognized and a standard face image, the feature curves can represent a face, and any feature extracted from each face image to be recognized The curves all correspond to a characteristic curve extracted from the corresponding position of the standard face image.

[0104] Those skilled in the art can understand that the number of feature curves extracted by the first extraction module 21 from each face image to be recognized and the standard face image is the same. The characteristic curve capable of representing a human face refers to a curve capable of representing and distin...

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 provides a face recognition method, which comprises the following steps: respectively extracting various characteristic curves of to-be-recognized face images and a standard face image, wherein the characteristic curves can characterize faces, and any characteristic curve extracted from each to-be-recognized face image corresponds to one characteristic curve extracted from a corresponding position of the standard face image; carrying out pixel-by-pixel scanning from one end to the other end of each characteristic curve, and sequentially calculating the offset between two adjacent pixels, so that a linear radian offset array corresponding to the characteristic curve is formed; and respectively comparing the corresponding linear radian offset arrays of the standard face image and each to-be-recognized face image, and according to comparison results, determining whether each to-be-recognized face image is similar to the standard face image. Accordingly, the invention also provides a face recognition method. The face recognition method and system disclosed by the invention can adapt to the requirements of environmental changes, so that even if the environment changes, the accuracy of recognition is not reduced.

Description

technical field [0001] The invention relates to the technical field of biological feature recognition, in particular to a face recognition method and a face recognition system. Background technique [0002] With the continuous progress of society and the urgent need for fast and effective identity verification technology, biometric technology has developed rapidly in recent years. As an inherent attribute of human beings, with strong self-stability and individual differences, biological characteristics have become the most ideal basis for identity verification. At present, biometric identification technologies mainly include: face recognition, fingerprint recognition, retinal recognition, iris recognition, gait recognition and vein recognition. Compared with other recognition methods, face recognition has been widely researched and applied because of its direct, friendly, convenient and other characteristics, which are easy to be accepted by users. [0003] Existing face r...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/168G06F18/22
Inventor 郭强
Owner CHINA UNITED NETWORK COMM GRP CO LTD