Iris detection method, iris detection apparatus, and non-transitory computer-readable recording medium recording iris detection program

Patent metadata

Field	Value
Publication number	US-12400480-B2
Application number	US-202217841905-A
Country	US
Kind code	B2
Filing date	Jun 16, 2022
Priority date	Dec 22, 2020
Publication date	Aug 26, 2025
Grant date	Aug 26, 2025

Abstract

An iris detection method includes acquiring a first image; generating a second image including an eye section of the person from the first image; generating a third image where pixels having a gradation value smaller than a threshold value are represented by a first luminance value and pixels having a gradation value equal to or greater than the threshold value are represented by a second luminance value after binarizing the second image; generating a fourth image by replacing the pixel of the second luminance value come into existence in a first luminance area having the first luminance value and satisfying a predetermined condition with the pixel of the first luminance value in the third image; calculating iris information including information about at least one of a position and a size of the iris of the person by use of the fourth image; and outputting the iris information.

First claim

The invention claimed is:

1. An iris detection method for detecting an iris of a person image taken by an image taking device by a computer of an iris detection apparatus, the iris detection method comprising:
acquiring a first image including a face of a person;
generating a second image including an eye section of the person from the first image;
generating a third image where pixels having a gradation value smaller than a threshold value are represented by a first luminance value and pixels having a gradation value equal to or greater than the threshold value are represented by a second luminance value after binarizing the second image;
generating a fourth image by replacing a pixel in an island-like area having the second luminance value in the third image with a pixel of the first luminance value, the island-like area being surrounded by a first luminance area having the first luminance value;
calculating iris information including information about at least one of a position and a size of the iris of the person by use of the fourth image; and
outputting the iris information, wherein
in the generation of the fourth image,
a plurality of vertical lines parallel to a vertical direction is set in the third image,
an uppermost pixel which is a pixel of the first luminance value and first appears in an upper end side on each of the plurality of vertical lines of the third image and a lowermost pixel which is a pixel of the first luminance value and first appears in a lower end side on each of the vertical lines of the third image are respectively detected,
for each of the vertical lines, it is judged whether a distance between the uppermost pixel and the lower most pixel is longer than a first reference distance, and
a pixel of the second luminance value that is included between the uppermost pixel and the lowermost pixel and is on a vertical line judged to have the distance be longer than the first reference distance is replaced with a pixel of the first luminance value.

2. The iris detection method according to claim 1 , wherein
the first luminance value is greater than the second luminance value, and
in the generation of the fourth image,
the third image is divided in a lateral direction into a plurality of local regions each having a predetermined number of pixels, an average luminance value of each local region is calculated, a center position of the local region having a highest average luminance value is calculated as an estimated iris center position, and
a process of judging whether or not to replace a pixel of the first luminance or not is applied only to a pixel of the second luminance value within a second reference distance from the estimated iris center position on the vertical line.

3. The iris detection method according to claim 2 , wherein
in the calculation of the iris information, a first pixel which has the second luminance value and first appears from the estimated iris center position to a left side in the lateral direction in the third image and a second pixel which has the second luminance value and first appears from the estimated iris center position to a right side in the lateral direction in the third image are respectively detected, and a middle position between the first pixel and the second pixel is calculated as an iris center position in the lateral direction.

4. The iris detection method according to claim 2 , wherein
in the calculation of the iris information, a third pixel which has the second luminance value and first appears from the estimated iris center position to an upper side in a vertical direction in the third image and a fourth pixel which has the second luminance value and first appears from the estimated iris center position to a lower side in the vertical direction in the third image are respectively detected, and a middle position between the third pixel and the fourth pixel is calculated as an iris center position in the vertical direction.

5. The iris detection method according to claim 1 , further comprising:
detecting respective positions of upper and lower eyelids based on the third image.

6. The iris detection method according to claim 5 , wherein
in the detection of the position of the eyelid, the position of the eyelid is detected by performing a morphological gradient operation to the third image.

7. The iris detection method according to claim 1 , wherein
the fourth image is a binary image of one of a left eye and a right eye of the person,
further comprising detecting respective positions of an eye outer corner and an eye inner corner based on the third image.

8. The iris detection method according to claim 7 , wherein
in the detection of the respective positions of the eye outer corner and the eye inner corner in the third image, a position of a leftmost pixel having the first luminance value in the lateral direction is detected as a position of one of the eye outer corner and the eye inner corner, and a position of a rightmost pixel having the first luminance value in the lateral direction is detected as a position of the other of the eye outer corner and the eye inner corner.

9. The iris detection method according to claim 7 , further comprising:
calculating information about both eyes of the person based on the positions of the eye outer corner and the eye inner corner.

10. The iris detection method according to claim 1 , further comprising:
detecting positions of upper and lower eyelids and positions of an eye outer corner and an eye inner corner in the third image, and calculating a distance between the iris center position and the position of the upper eyelid, a distance between the iris center position and the position of the lower eyelid, a distance between the iris center position and the position of the eye outer corner, and a distance between the iris center position and the position of the eye inner corner based on the detection results.

11. The iris detection method according to claim 1 , further comprising:
displaying the iris information in such a manner as to be superimposed on a facial image of the person shown on a display.

12. An iris detection apparatus for detecting an iris of a person image taken by an image taking device, the iris detection apparatus comprising:
a processor; and
a non-transitory memory having stored thereon executable instructions, which cause the processor to perform:
acquiring a first image including a face of a person;
detecting a second image including an eye section of the person from the first image;
generating a third image where pixels having a luminance lower than a threshold value are represented by a first luminance value and pixels having a luminance equal to or higher than the threshold value are represented by a second luminance value after binarizing the second image;
generating a fourth image by replacing a pixel in an island-like area having the second luminance value in the third image with a pixel of the first luminance value, the island-like area being surrounded by a first luminance area having the first luminance value;
calculating iris information including information about at least one of a position and a size of the iris of the person by use of the fourth image; and
outputting the iris information, wherein

in the generation of the fourth image,
a plurality of vertical lines parallel to a vertical direction is set in the third image,
an uppermost pixel which is a pixel of the first luminance value and first appears in an upper end side on each of the plurality of vertical lines of the third image and a lowermost pixel which is a pixel of the first luminance value and first appears in a lower end side o

Assignees

• Swallow Incubate Co Ltd
• Panasonic Holdings Corp

Inventors

• Ohno Toshikazu

Classifications

• G06T2207/30201

  Face · CPC title

• G06T2207/10152

  Varying illumination · CPC title

• G06T7/60

  Analysis of geometric attributes · CPC title

• G06V10/28

  Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns · CPC title

• G06V40/16

  Human faces, e.g. facial parts, sketches or expressions · CPC title