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

A multi-task based iris detection and perspective classification method

A classification method and multi-task technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as low efficiency and poor iris recognition accuracy, and achieve the effect of ensuring accuracy and improving accuracy.

Active Publication Date: 2019-02-26
北京万里红科技有限公司
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of poor accuracy and low efficiency of iris recognition in the iris image recognition process in the prior art, the present invention provides a multi-task-based iris detection and viewing angle classification method, the purpose of which is to achieve multi-task-based iris The detection and viewing angle classification method can accurately locate the iris area, and can effectively identify the orientation of the iris, improving the accuracy of iris recognition

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
  • A multi-task based iris detection and perspective classification method
  • A multi-task based iris detection and perspective classification method
  • A multi-task based iris detection and perspective classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Embodiment one: if figure 1 As shown, the present application provides a multi-task-based method for iris detection and viewing angle classification, which includes: step S101 to step S104.

[0041] Step S101, acquiring an iris image to be detected.

[0042] In this embodiment, the image recognition device acquires the iris image to be detected. The iris image may be collected by the image recognition device, or the collected iris image may be sent to the image recognition device by electronic devices such as mobile phones, PCs, and notebooks. Specifically, an iris image may be collected by an iris image collection device (such as an iris optical imaging device). In actual application, the iris image to be detected may also be acquired by the image recognition device from a preset iris image database through a preset interface.

[0043] Specifically, the image recognition device may be electronic equipment such as a mobile phone, a PC, a notebook, and a server. In pr...

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 multi-task iris detection and visual angle classification method, comprising the following steps: S101, acquiring an iris image to be detected; S102, inputting the iris imageto First-Net detector to obtain a first output result; S103, inputting the first output result to Second-net detector to obtain a second output result; S104, inputting the second output result to Ultimate-net detector. After merging the overlapping iris candidate frames with non-maximal suppression algorithm, the remaining iris candidate frames, the probability corresponding to the remaining iriscandidate frames, and the probability that the remaining iris candidate frames belong to different iris perspectives are obtained. The invention has the advantages that the multi-task convolution neural network is used for detecting the iris image and the method for classifying the five angles of view of the iris. On the one hand, it ensures the accuracy of iris image detection, on the other hand, it improves the accuracy of iris classification from five angles of view.

Description

technical field [0001] The invention relates to the technical field of iris detection, in particular to a multi-task-based iris detection and viewing angle classification method. Background technique [0002] Iris recognition technology is an identification technology based on biometric features, which mainly includes several steps of image: image acquisition, image preprocessing, image pattern matching and decision making. Among them, image pattern matching is the key to iris recognition technology. [0003] However, the existing iris recognition technology generally has the following problems: 1. The result of iris recognition is wrong because the orientation of the iris cannot be determined or the accuracy of the determined orientation is poor; 2. The efficiency and accuracy of iris recognition are low. Contents of the invention [0004] In order to solve the problem of poor accuracy and low efficiency of iris recognition in the iris image recognition process in the pr...

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): G06K9/00G06N3/04
CPCG06V40/197G06V40/19G06N3/045
Inventor 张小亮戚纪纲王秀贞
Owner 北京万里红科技有限公司
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

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