Face Recognition Method Based on Multiple Linear Regression Associative Memory
A multiple linear regression, associative memory technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as disturbing daily life, being involved in criminal events, stealing private information, etc.
Inactive Publication Date: 2020-12-04
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY +1
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the development of the big data era, people usually save their daily photos or even ID photos in the database, which is easy for hackers to steal private information for trafficking or criminal activities. In this way, people's private information is leaked, and daily Life is easily disturbed or even involved in criminal incidents, which can easily cause a lot of inconvenience
[0003] In order to hide and save the face information, people often use the face feature matrix to save it, but as people use it, this protection method is also unreliable, and the saved face pictures are easy to be cracked, and the information will also cause Bad communication that disturbs people's lives a lot
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0066] The specific implementation manner and working principle of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0067] from figure 1 It can be seen that a method for face recognition based on multiple linear regression associative memory includes the following steps:
[0068] S1: Collect face images, process the face images into binary images by setting the brightness threshold of the binary image, and obtain the input matrix and output matrix of the associative memory;
[0069] The binary image brightness threshold K=(0, 1, 2, 3...255); in this embodiment, K=100 is set.
[0070] In step S1, m pieces of human face pictures are included, and each piece of said human face picture and each piece of said binary image are composed of N rows and M columns of pixels, then the number of pixels n=N× M;
[0071] Let face picture matrix data be the input matrix Γ=(X of associative memory 1 , X 2 ,...,X m ),in, Re...
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
Login to View More Abstract
The invention discloses a method for face recognition based on multiple linear regression associative memory, comprising the following steps: S1: collecting a face picture, converting the face picture into a binary picture, and obtaining an associative memory input matrix and an output matrix; S2: Build a multiple linear regression face recognition model, and simplify the multiple linear regression face recognition model to obtain a multiple linear regression simplified face recognition model with unknown regression parameters; S3: Calculate the multiple linear regression simplified face recognition model Unknown regression parameters, and finally determine the multiple linear regression face recognition model; S4: recognize the face picture. Beneficial effects: the associative memory and the multiple linear regression model are combined to convert the face picture into parameters, the safety factor is high, the reliability is good, the recognition effect is good, the protection effect of the face picture is good, and the privacy is high.
Description
technical field [0001] The invention relates to the technical field of image data preservation, in particular to a face recognition method based on multiple linear regression associative memory. Background technique [0002] With the development of the big data era, people usually save their daily photos or even ID photos in the database, which is easy for hackers to steal private information for trafficking or criminal activities, so that people's private information is leaked, and daily Life is easily disturbed or even involved in criminal incidents, which can easily cause a lot of inconvenience. [0003] In order to hide and save the face information, people often use the face feature matrix to save it, but as people use it, this protection method is also unreliable, and the saved face pictures are easy to be cracked, and the information will also cause Bad communication has disturbed people's lives a lot. Contents of the invention [0004] In view of the above proble...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06N3/04G06V40/172
Inventor 韩琦刘晋谯自强吴政阳刘洋翁腾飞黄军建
Owner CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY