Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face recognition method based on MBLBP and DCT-MB2DPCA

A technology of DCT-BM2DPCA and face recognition, which is applied in the direction of character and pattern recognition, instruments, computer parts, etc., can solve the problem of low recognition rate, achieve the effect of improving recognition accuracy, reducing time, and improving recognition accuracy

Inactive Publication Date: 2018-07-20
HARBIN NORMAL UNIVERSITY
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to propose a face recognition method based on multi-scale block local binary pattern and discrete cosine transform bidirectional module two-dimensional principal component analysis, so that the recognition rate of the existing face recognition algorithm using a single feature extraction method is low The problem

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 based on MBLBP and DCT-MB2DPCA
  • Face recognition method based on MBLBP and DCT-MB2DPCA
  • Face recognition method based on MBLBP and DCT-MB2DPCA

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0030] Specific Embodiment 1: The face recognition method based on multi-scale block local binary pattern and discrete cosine transform bidirectional module two-dimensional principal component analysis described in this embodiment, such as figure 1 As shown, it is implemented according to the following steps:

[0031] Step 1, convert the face image from the spatial domain to the frequency domain by DCT, and then reconstruct the face image by IDCT;

[0032] Step 2. Use The operator performs feature extraction on the face image reconstructed by IDCT to obtain matrix B;

[0033] Step 3, obtain the characteristic matrix through BM2DPCA;

[0034] Step 4: Use the nearest neighbor classifier to identify the test samples.

specific Embodiment approach 2

[0035] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is: if figure 2 (a) and figure 2 Shown in (b), described in step 1, the human face image is converted from the spatial domain to the frequency domain by DCT, and then the reconstruction of the human face image by IDCT is realized according to the following steps:

[0036] Step 1 (1), the face image is converted to the frequency domain by DCT, the input image is first decomposed into 8×8 blocks, and then DCT is performed on each block, and the DCT transformation formula is as follows:

[0037]

[0038] In the formula M×N is the image block size obtained after the input image is transformed by DCT.

[0039] Step one (two), the face image is reconstructed by IDCT, because after the discrete cosine transform, the main information of the image is concentrated in the low-frequency component, so select 10 in the upper left corner of each image block in...

specific Embodiment approach 3

[0044] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one or two is: the use described in step two The operator performs feature extraction on the face image reconstructed by IDCT to obtain matrix B, where, Indicates that the size of the pixel block is 1×1, and the circular 8-neighborhood LBP operator with a radius of 2 is realized according to the following steps:

[0045] Step 2 (1), the face image reconstructed by IDCT is divided into 1 * 1 pixel blocks;

[0046] Step 2 (2), obtain the mapping matrix by calculating the average gray value of each pixel block;

[0047] Step 2 (3), obtain the feature matrix represented by the low resolution of the pixel block by calculating the uniform (8,2) LBP feature of the mapping matrix;

[0048] Step two (four), restore the feature matrix represented by the low resolution, that is, expand each pixel in the matrix into a 1×1 block, and the gray value of each pixel in...

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 relates to a face recognition method based on MBLBP and DCT-MB2DPCA, belongs to the technical field of computer vision process, and solves the problem that the recognition rate is low due to a single feature extract method in an existing face recognition algorithm. Based on a multi-scale block local binary system mode and discrete cosine transform bi-directional module two-dimensionmain component analysis, the face recognition method is achieved by the following steps. A face image is converted from a spatial domain to a frequency domain through DCT, and then the face image is reconstructed through IDCT; feature extract is carried out on the converted face image by using an MBLBP operator; a characteristic matrix is acquired through BM2DPCA; a nearest neighbor classifier isused to recognize a test sample. The face recognition method is applicable to two-dimension face recognition in the fields of safety system, identification, personal equipment login and the like.

Description

technical field [0001] The invention specifically relates to a face recognition method based on multi-scale block local binary patterns and two-dimensional principal component analysis of discrete cosine transform bidirectional modules, which belongs to the technical field of computer vision processing. Background technique [0002] Facial recognition is one of the less invasive biometric authentication methods because it enables user authentication simply based on a priori knowledge of training samples. Face recognition has become one of the hotspots in the research of computer vision and pattern recognition because many fields have a wide demand for face recognition. Face recognition involves knowledge disciplines such as pattern recognition, image processing, psychology, and physiology. Compared with other personal identification methods that use different biometric features such as fingerprints, palm prints, retinas, and irises, face recognition has the advantages of bei...

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): G06K9/00G06K9/62
CPCG06V40/16G06V40/168G06F18/24147G06F18/214
Inventor 于晓艳樊自力荣宪伟李明张子锐
Owner HARBIN NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com