Partitioning method and device for iris region in iris image

An iris image and iris technology, applied in the field of pattern recognition and computer vision, can solve problems such as difficulty in designing effective feature pixel classification, and achieve the effect of ensuring accuracy, saving time and improving work efficiency

Active Publication Date: 2017-05-31
天津中科智能识别有限公司
View PDF3 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods often need to pre-process lighting, blur, etc., an

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
  • Partitioning method and device for iris region in iris image
  • Partitioning method and device for iris region in iris image
  • Partitioning method and device for iris region in iris image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] Based on the multi-scale fully convolutional neural network-based iris region segmentation method and device in the iris image provided by the present invention, it can be applied in the airport entry-exit management system for long-distance iris recognition.

[0094] The present invention can be applied to long-distance recognition scenes. With the wide application of iris recognition technology, the demand for long-distance iris recognition system is more and more extensive. The long-distance iris recognition system does not require the user to cooperate too much in the collection, and only needs to approach the collection area. Using the technical solution provided by the invention, the airport entry and exit management system can automatically collect the user's iris photos. Due to the long distance and the user is often on the move, the collected iris images not only have poor imaging quality, but also often have squinting, occlusion and other situations. The airp...

Embodiment 2

[0096] A method and device for segmenting iris regions in iris images based on multi-scale fully convolutional neural networks provided by the present invention can be applied in security systems based on iris recognition.

[0097] The present invention can be widely applied to the scene of using the iris for identity authentication and identification. For example, in a masked theft case in a certain city, the criminals were recorded by the monitoring system at the scene of the crime. Although the suspect is masked, his eye area still leaks. The police can effectively segment out the iris region through the multi-scale fully convolutional neural network iris segmentation method of the present invention. By extracting the features of the effective iris area and comparing it with the iris in the police database, the suspect was found immediately. Thanks to the assistance of the iris recognition-based security system, the police were able to locate the suspect within hours.

...

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 partitioning method for an iris region in an iris image. The partitioning method comprises the following steps: 1, building a multi-scale convolutional neural network; 2, annotating preset key points in a preselected iris image in advance; 3, inputting the iris image with the annotated preset key points into the convolutional neural network, and training the convolutional neural network to converge a model of the convolutional neural network; 4, inputting a to-be-tested iris image needing iris region partitioning into the trained convolutional neural network to obtain a binary code pattern of the to-be-tested iris image, wherein the binary code pattern is a finally partitioned iris region. According to the partitioning method for the iris region in the iris image, which are disclosed by the invention, the iris region in the iris image acquired under a non-controllable scene can be timely and accurately partitioned, so that the requirement of a user for iris partitioning can be met, and the working efficiency of the user can be improved.

Description

technical field [0001] The invention relates to the technical fields of pattern recognition and computer vision, in particular to a method and device for segmenting iris regions in iris images. Background technique [0002] At present, with the continuous development of human science and technology, iris recognition technology is becoming more and more popular in people's daily life. Iris recognition is a biometric recognition method that uses the invariance and uniqueness of iris texture to identify identities. It has been successfully It is used in national security, border control, banking and finance, access control and attendance, and mobile terminals. It can be said that whether in artificial intelligence research or public security applications, iris recognition technology has always been a cutting-edge and popular technology, and has a pivotal position. [0003] For iris recognition technology, many technical challenges are encountered in practical application. Esp...

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): G06K9/00G06K9/46G06N3/02
CPCG06N3/02G06V40/193G06V10/462
Inventor 谭铁牛孙哲南李海青张曼张琪刘年丰
Owner 天津中科智能识别有限公司
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