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

Human eye detecting method and apparatus

A detection method and technology of detection equipment, which are applied in the directions of equipment, instruments, and applications for testing eyes, and can solve problems such as low efficiency

Inactive Publication Date: 2009-03-04
CANON KK
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is inefficient because there are too many possible eye regions (candidate eyes) in one image

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
  • Human eye detecting method and apparatus
  • Human eye detecting method and apparatus
  • Human eye detecting method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0054] see image 3 , which shows the flow chart of the first embodiment of the human eye detection method of the present invention. The method begins with a read step 102, where a digital or analog image to be processed is read from an image source. The image source can be of any type, such as a storage device in a PC, a camera, and the like.

[0055] Then in the analysis step 104, the image is analyzed by means of the method disclosed in the Chinese patent application 00127067.2 to generate a list of candidate eye regions. If the image read in at said reading step 102 is an analog image, it is digitized prior to analysis. The analysis step 104 can also be implemented by other known methods, such as region growing method, region segmentation method and hybrid method.

[0056] In a selection step 106, an unverified candidate eye region is randomly or sequentially selected from the list. Then there is a neighborhood area determination step 108, in which a neighborhood area ...

no. 2 example

[0068] In the second embodiment, the method of the present invention further includes steps as described below. Such as Figure 4 As shown, the detection step 402 includes referring to image 3 All steps described. Then in the face determining step 404 , the candidate face regions are determined according to the remaining candidate eye regions obtained in the detecting step 402 . There are many methods for determining candidate face regions from candidate eye regions. For example, a candidate face region can be determined from a candidate eye region according to the inherent relative positions of the eyes on the human face. For another example, according to the symmetry of a pair of eyes, and / or the distance between a pair of eyes and / or the general relative position of the eyes in the image, the candidate eye regions can be paired, and then can be based on a pair of eyes in Intrinsic relative positions on human faces determine candidate face regions.

[0069] Next is the...

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 present invention uses the following steps to survey eyes in given image: reading in image, analysing the image to obtain candidate eye zone listing as unchecked candidate eye zone being selected, confirming an adjacent area for selected candidate eye zone and calculating adjacent area size S to obtain dark field, counting dark field and recording the counting value as N, comparing specific value N / S with preset first threshold and determining abovesaid candidate eye zone to be false eye zone to delete it out from listing if specific value N / S is less than the first threshold, otherwise candidate eye zone being true one to keep it in listing, repeating abovesteps till all candidate eye zone being checked and to output listing for post-processing.

Description

technical field [0001] The invention relates to an image processing method, in particular to a human eye detection method for detecting human eyes in an image. The present invention also relates to a human eye detection device, a human eye detection system and a storage medium in which human eye detection program codes are stored. Background technique [0002] Today, image recognition technology is used in many technical fields, such as satellite image analysis, automation, moving image compression, and surveillance systems. So far, there have been many techniques for recognizing objects in images, such as template matching, statistical pattern recognition, structural pattern recognition, and neural network methods. [0003] One type of object to be recognized is the human body itself, especially a human face. Haiyuan Wu's article "Face Detection and Rotations Estimation Using Color Information" (the 5 th In IEEE International Workshop on Robot and Human Communication, 1...

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): G06K9/00G06K9/36G06T1/00A61B3/00
CPCG06K9/00597G06V40/18
Inventor 陈新武纪新王立冰
Owner CANON KK
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