Image processing device, image processing method, and image processing program

Active Publication Date: 2018-05-24
YAZAKI CORP
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent describes an image processing device and method for accurately detecting the pupil or iris in an image, even in a highly disturbed environment. The device uses edge information and gradient magnitude to remove noise and accurately detect the pupil or iris as the main target. The device also detects the upper and lower eyelids, which can be affected by ambient light or makeup, by aligning the eye in a face image and detecting the boundary with the iris. Furthermore, the device uses an arc shape to improve the detection of the entire iris outline. The method and program allow for accurate detection of the pupil or iris, even in disturbed environments, while avoiding the influence of unnecessary features that generate noise.

Problems solved by technology

However, in this method, an edge is unconditionally generated from an object other than a detection target, for example, reflection of light projected on an eyelid, an eyebrow, or an eyeball.
Therefore, deterioration of detection accuracy or erroneous detection may occur.
In a case where a detection position of a black part of an eye deviates, an error occurs during estimation of a gaze.
During binarization or ternarization of image data, a threshold becomes an issue, and the result is likely to be affected by ambient light during capturing.
In a case where an ellipse detection algorithm is used, it is difficult to detect a target itself in a state where an eye moves sideways and a shape of a black part of the eye on a two-dimensional image is significantly collapsed.

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
  • Image processing device, image processing method, and image processing program
  • Image processing device, image processing method, and image processing program
  • Image processing device, image processing method, and image processing program

Examples

Experimental program
Comparison scheme
Effect test

first embodiment

Process of First Embodiment

[0103]In order to suppress the detection position deviation of the iris illustrated in FIG. 7, the image processing device according to the embodiment includes the following

and

[0104]An edge image, which stores information regarding a gradient magnitude and a positive or negative sign of gradient, is generated by filtering a face image to detect an edge in a scanning direction. For example, in a case where an edge is extracted and the data D43 is generated in Step S43 illustrated in FIG. 4, a special edge image, which stores information regarding a gradient magnitude and a positive or negative sign of gradient, is generated.

[0105]A likelihood with respect to a sampling curve is calculated by setting points having a positive gradient as likelihood evaluation targets in a first point group which is positioned on a front side in the scanning direction among the plurality of points constituting the sampling curve, and setting points having a negative gradient...

second embodiment

Process of Second Embodiment

[0130]FIG. 12 illustrates an example of a pattern shape of a particle filter according to a second embodiment. FIGS. 13A and 13B are schematic diagrams illustrating specific examples of processing data in a case where the pattern shape of the particle filter illustrated in FIG. 12 is applied.

[0131]In the second embodiment, “sampling process” illustrated in FIGS. 13A and 13B is performed using a semicircular filter pattern FP illustrated in FIG. 12. That is, the same process as that of the first embodiment is performed except that the shape of the filter pattern changes. Since FIG. 13A is the same as FIG. 6 except that an edge image D73 is illustrated instead of the edge image D92, the detailed description thereof will not be repeated. Further, since FIG. 13B is the same as FIG. 7 except that an edge image D73 is illustrated instead of the edge image D53, the detailed description thereof will not be repeated.

[0132]The filter pattern FP illustrated in FIG. ...

third embodiment

Process of Third Embodiment

[0139]FIG. 15 illustrates an example of a pattern shape of a particle filter according to a third embodiment. FIGS. 16A and 16B are schematic diagrams illustrating specific examples of processing data in a case where the pattern shape of the particle filter illustrated in FIG. 15 is applied.

[0140]In the third embodiment, a “sampling process” illustrated in FIGS. 16A and 16B is performed using the semicircular filter pattern FP2 illustrated in FIG. 15. That is, the same process as that of the first embodiment is performed except that the shape of the filter pattern changes. Since FIG. 16A is the same as FIG. 6 except that an edge image D73 is illustrated instead of the edge image D92, the detailed description thereof will not be repeated. Further, FIG. 16B is the same as FIG. 7 except that an edge image D73 is illustrated instead of the edge image D53, the detailed description thereof will not be repeated.

[0141]The filter pattern FP2 illustrated in FIG. 15 ...

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

An image processing device includes a data processing unit that processes data of a face image which is captured to include a face. The data processing unit generates an edge image by filtering the face image to detect an edge in a scanning direction, extracts a sampling value as the information regarding a gradient magnitude and whether the gradient is positive or negative from each of positions in the edge image corresponding to a plurality of points constituting the sampling curve, calculates a likelihood with respect to the sampling curve by setting points having a positive gradient and a negative gradient as likelihood evaluation targets in a first point group and a second point group, and detects a sampling curve having a maximum likelihood as a pupil or an iris among a plurality of sampling curves.

Description

CROSS REFERENCE TO RELATED APPLICATION[0001]This application is based on Japanese Patent Application Nos. 2016-225728 filed on Nov. 21, 2016, and 2017-176497 filed on Sep. 14, 2017, the contents of which are incorporated herein by reference.BACKGROUND OF THE INVENTION1. Technical Field[0002]The present invention relates to an image processing device, an image processing method, and an image processing program, and particularly relates to a technique which can be used for estimating eye features such as a gaze based on an image obtained by capturing the face of a person.2. Background Art[0003]In the related art, an image processing device that processes data of an image obtained by capturing the face of a person using a camera to identify eye features (for example, JP-A-2012-190351).[0004]An object of a technique disclosed in JP-A-2012-190351 is to accurately detect a pupil region.[0005]The image processing device disclosed in JP-A-2012-190351 includes: a second differentiation unit ...

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): G06K9/00G06T7/13G06T7/73
CPCG06K9/0061G06T7/13G06T7/75G06T2207/30201G06T2207/20076G06V40/171G06V40/193G06V10/446G06V10/752
Inventor HATAKEYAMA, MASAYASAKUMOTO, NAOTAKENAGAI, KAZUSHIGETAKAHASHI, YUKI
Owner YAZAKI CORP
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