Facial feature extraction method and face recognition method based on large-scale image data

A technology of image data and face features, applied in the field of image recognition, can solve problems such as robust face image features, and achieve the effects of reducing correlation, facilitating parallel computing, and improving accuracy

Active Publication Date: 2013-02-20
BEIJING KUANGSHI TECH
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to overcome the above-mentioned classical human face image feature extraction method for the serious correlation problem of facial posture and expression, propose a kind of human face feature extraction method and face recognition method based on large-scale image data, thereby obtain A more robust face image feature suitable for various scenes and applications

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
  • Facial feature extraction method and face recognition method based on large-scale image data
  • Facial feature extraction method and face recognition method based on large-scale image data
  • Facial feature extraction method and face recognition method based on large-scale image data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be described in detail below in conjunction with the accompanying drawings and specific examples.

[0029] First describe the two database establishment processes of the present invention to establish the celebrity face database and the "background" human face database. The detailed procedure includes the figure 1 The following steps are described in .

[0030] Step S11: Collect N celebrity names with relative popularity as keywords of the search engine.

[0031] Step S12: Use the collected celebrity names to search for face images on the Internet, download and store the top N image results obtained for each keyword into a local file system. The search results for each celebrity are stored in a separate file path.

[0032] Step S13: Manually screen all the detected face images under the file path of each celebrity, remove the wrongly detected "faces", and store the faces that are human faces but do not belong to the celebrity into the "back...

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 a facial feature extraction method and a face recognition method based on large-scale image data. The facial feature extraction method comprises the following steps of: 1) establishing a face image database A, wherein each person has face images with multiple expressions, postures and illumination, and establishing a face image database B; 2) performing face detection on each image in the databases A and B, and outputting a rectangular frame comprising the face, and pixel coordinates of the two eyes; 3) correcting and zooming each face image, generating an image with a set standard format, and extracting a bottom texture feature vector; 4) training a classifier capable of recognizing each person a by utilizing a support vector machine algorithm for the person a in the database A; and 5) generating a new face image into an image with a set standard format, judging the bottom texture feature vector of a new face by utilizing each classifier, and establishing a vector according to a criteria score to serve as a feature vector of the new face image. According to the extraction method, the robustness of an extracted face feature is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and relates to a face image analysis and processing method, in particular to a face feature extraction method and a face recognition method based on large-scale image data, which can be applied to face recognition / face verification / face search and other applications as the basic face feature extraction unit. Background technique [0002] Feature extraction of face images is a hotspot in computer vision research, and its technical research results are widely used in various tasks such as face recognition / face verification / face search / facial expression analysis. Its basic task is to generate a vector representation for the input face image, so that the information of the face identity can be well preserved and the information irrelevant to the face identity can be eliminated. Its basic goal is that the face image input of the same person produces vector outputs that are as similar as p...

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): G06K9/46G06K9/64G06K9/00
Inventor 印奇曹志敏唐文斌杨沐
Owner BEIJING KUANGSHI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap