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

Recognition equipment of video identity and recognitionmethod ofvideo identity

A recognition method and identity technology, applied in the field of image recognition, can solve the problems of recognition accuracy interference, uncontrollable acquisition environment, low face stability, etc., and achieve high labor costs, ideal output effects, and guaranteed initiative. Effect

Inactive Publication Date: 2020-02-21
上海汇付支付有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Face recognition technology usually has the following disadvantages: Instability: Compared with other biometrics, such as fingerprints and irises, the stability of the face is not high
Uncontrollability of the acquisition environment: When collecting images, the lighting conditions and the background of the characters are often uncontrollable, and these factors will interfere with the recognition accuracy

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
  • Recognition equipment of video identity and recognitionmethod ofvideo identity
  • Recognition equipment of video identity and recognitionmethod ofvideo identity
  • Recognition equipment of video identity and recognitionmethod ofvideo identity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Neural network algorithm is a general term for a class of computer algorithms that imitate biological neural networks. It is composed of several artificial neuron nodes (referred to as "neurons") interconnected. Neurons are connected in pairs through synapses, and synapses record the strength (weight) of connections between neurons. The human brain responds to various stimuli such as vision and hearing through billions of neurons and trillions of synapses. The learning process, that is, the process in which neurons change the way they connect to each other, enables humans to respond to stimuli. To make a reasonable response, the neural network simulates the working process of the human brain.

[0053] Convolutional neural network is an efficient recognition method that has been developed in recent years and has attracted widespread attention. In the 1960s, Hubel and Wiesel discovered that its unique network structure can effectively reduce the complexity of the feedbac...

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 recognition equipment of video identity and a recognitionmethod ofvideo identity. A computer recognition (image recognition and voice recognition) technology is applied to therecognition of the video identity to form a comprehensive and multi-strategy way combined with deep learning, and the risk to the transaction by the video identity recognition error can be effectivelyprevented. By combining the voice recognition, the identity card face recognition, living body recognition, a traditional identity card and real-name verification, the method mainly comprises the steps of entering identity information, constructing a voice recognition model, constructing a face living body recognition model, online verifying voice recognition, online verifying identity card information and online verifying face recognition and the like, and the recognition equipment and method are the equipment and method capable of more flexibly and reliably recognizing the video identity byutilizing the deep learning technology.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method and equipment for video identity recognition Background technique [0002] At present, video identity recognition is mainly through single-strategy speech recognition or face recognition. Face contrast recognition, as a mature biometric technology, has been applied to remittance user registration, user verification and other scenarios. However, face contrast The recognition system can only recognize the faces in the collected images, but cannot judge the authenticity of the collected face images, so it is extremely vulnerable to various deliberate attacks. Once these attacks are successful, the security of user accounts and funds may be threatened, and the consequences and losses may be very serious. In order to solve this problem, face recognition technology emerged as the times require. This technology aims to distinguish whether the face images coll...

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
IPC IPC(8): G10L17/04G10L17/22H04L29/06G06K9/00G06K9/62G10L17/02
CPCG10L17/02G10L17/04G10L17/22H04L63/0861H04L63/0876G06V40/16G06V40/161G06V40/168G06F18/214
Inventor 周晔穆海洁裔隽
Owner 上海汇付支付有限公司
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