Method and device for living body recognition and method and device for constructing living body recognition model

A technology for identifying models and living bodies, applied in biometric recognition, character and pattern recognition, instruments, etc., can solve the problems affecting the recognition accuracy of biometric recognition systems, presenting attacks, etc., to achieve convenient and rapid collection/acquisition, convenient application, The effect of high recognition accuracy

Inactive Publication Date: 2022-03-11
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Since information about the above-mentioned biometric features is easy to obtain, there will be various forms of presentation attacks, which may affect the recognition accuracy of the biometric feature recognition system

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
  • Method and device for living body recognition and method and device for constructing living body recognition model
  • Method and device for living body recognition and method and device for constructing living body recognition model
  • Method and device for living body recognition and method and device for constructing living body recognition model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Presentation attack methods can be roughly divided into: two-dimensional presentation attacks, including: two-dimensional static paper and electronic photos, two-dimensional dynamic images, videos, etc.; three-dimensional presentation attacks, including: three-dimensional mask attack and high-precision three-dimensional head model attack Wait. There are also great differences in the attack cost, the difficulty of detection, and the frequency of attacks of various types of attacks.

[0030] When implementing the disclosed concept, it is found that for various types of presentation attacks, some methods need to capture living objects (such as real irises) and non-living objects (such as electronic screens, photos, etc.) Or iris on paper, etc.), this method requires additional equipment for modification, high complexity, low collection efficiency, and cannot be easily applied.

[0031] Some methods are to use common color or grayscale imaging equipment to collect biometri...

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 living body identification and living body identification model construction method and device. The method and device are also applied to a scene that a model-based computer system or electronic equipment performs true prosthesis identification detection on biological characteristics. The living body recognition method comprises the following steps: acquiring a group of image focus stack sequences focused at different depths of an object to be recognized obtained by shooting the same observation point position; based on a feature extraction model, performing feature extraction on each image in the image focus stack sequence to obtain a feature vector of each image in the same feature space; analyzing differences among the feature vectors of the images to obtain a feature difference distribution sequence of the images related to the image focus stack sequence; and inputting the feature difference distribution sequence into a pre-trained living body identification model, and identifying whether the to-be-identified object is a living body biological feature or a non-living body biological feature. The method has the advantages of high identification accuracy, simplicity in operation and convenience in application.

Description

technical field [0001] The present disclosure relates to the technical field of biological feature detection and recognition and the field of artificial intelligence, and in particular to a method and a device for living body recognition and building a living body recognition model. Background technique [0002] At present, with the development of artificial intelligence (AI) technology, biometric identification technology is becoming more and more reliable, such as human face, iris, fingerprint, palmprint and other biological characteristics are used for secure login of electronic devices (such as mobile phones, computers, etc.), An important verification method for secure payment, etc. [0003] Since information about the above-mentioned biometric features is easy to obtain, there will be various forms of presentation attacks, which may affect the recognition accuracy of the biometric feature recognition system. For example by utilizing certain artifacts of the aforementi...

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): G06V40/40G06V10/774G06K9/62
CPCG06F18/214
Inventor 王云龙孙哲南骆正权任民卫建泽
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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