Face image recognition method and device

A face image and recognition method technology, applied in the field of image recognition, can solve the problems of low amount of information, limited ability to improve recognition results, low recognition rate of face images, etc.

Active Publication Date: 2015-11-25
HANVON CORP
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, in the existing decision-making layer fusion recognition method, since the decision-making layer is at the end of the recognition process, the amount of information obtained is small, and the ability of the fusion algorithm to improve the recognition results is easily subject to corresponding limitations. Therefore, the existing decision-making layer fusion The recognition method has a low recognition rate for face images

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 image recognition method and device
  • Face image recognition method and device
  • Face image recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] An embodiment of the present invention provides a recognition method of a face image, such as figure 1 shown, including the following steps:

[0029] 101. Perform feature matching and classification on the first face image collected by near-infrared light and the face images in the preset near-infrared light registration set, and obtain the categories corresponding to the top M candidates with the highest matching scores in the first group and matching scores.

[0030] Specifically, the first human face image collected by near-infrared light is matched with the face images in the preset near-infrared light registration set, and the nearest neighbor classifier is used for classification. The matching scores in the categories corresponding to the top M candidates with the highest matching scores in the first group may be calculated by using cosine distance or Euclidean distance.

[0031] The calculation formula of the cosine distance is shown in the following formula (1...

Embodiment 2

[0072] An embodiment of the present invention provides a recognition device for a face image, such as image 3 As shown, it includes: a first processing unit 11 , a second processing unit 12 , a normalization unit 13 , a combination unit 14 and a determination unit 15 .

[0073] Among them, the first processing unit 11 is used to perform feature matching and classification on the first face image collected by near-infrared light and the face images in the preset near-infrared light registration set, and obtain the highest matching score of the first group The categories and matching scores corresponding to the top M candidates of ;

[0074] The second processing unit 12 is configured to perform feature matching and classification on the second human face image collected by visible light and the human face image in the preset visible light registration set, and obtain the top M candidate correspondences with the highest matching score in the second group. category and matching...

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 embodiment of the invention provides a face image recognition method and device, belonging to the technical field of image recognition and aiming to improve the face image recognition rate. The face image recognition method comprises the following steps: matching the characteristics of the first face image acquired through the near-infrared light and the face image in the preset near infrared light registration set and classifying to obtain the categories and the matching scores of the top M candidates with the highest of matching scores in the first group; matching the characteristics of the first face image acquired through the visible light and the face image in the preset visible light registration set and classifying to obtain the categories and the matching scores of the top M candidates with the highest of matching scores in the second group; normalizing the matching scores of the top M candidates with the highest of matching scores in the first group and the matching scores of the top M candidates with the highest of matching scores in the second group respectively; and merging the same categories to obtain the N categories and the scores which corresponds to the N categories, and taking the categories with the highest scores as the recognition results. The face image recognition method and device are mainly used for face image recognition.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a face image recognition method and device. Background technique [0002] At present, when recognizing human face images, visible light technology and near-infrared light technology are commonly used to collect human face images. [0003] Among them, visible light is a light source that can be perceived by human eyes, and is also the most common light source in daily life. The collection of visible light images (images collected by visible light) is completed under the irradiation of visible light. Therefore, when collecting visible light images, it is greatly affected by factors such as lighting conditions. [0004] Near-infrared light is a kind of invisible light. When using near-infrared light to collect face images, the thermal radiation coefficient generated by the temperature of the face skin is significantly different from the thermal radiation coefficient of th...

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): G06K9/00
Inventor 黄磊许力刘昌平
Owner HANVON CORP
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