Iris detection method, iris detection device, and program product

Abstract

The iris detection method of the present invention obtains a first image containing a human face; generates a second image containing an area of ​​the human eye from the first image; binarizes the second image to generate a third image, in which pixels having grayscale values ​​less than a threshold are represented by a first brightness value and pixels having grayscale values ​​greater than the threshold are represented by a second brightness value; replaces pixels of the second brightness value in the third image that appear within a first brightness area having the first brightness value and meet a specified condition with pixels of the first brightness value, thereby generating a fourth image; calculates iris information containing information related to at least one of the position and size of the human iris using the fourth image; and outputs the iris information.

Description

Technical Field

[0001] The present invention relates to a technology for detecting human iris. Background Art

[0002] Eye detection technology, which detects eye-related information from images, has attracted significant attention as a key technology for estimating a person's emotions, level of alertness, fatigue, and other human states. Iris information, which relates to the position and size of the iris, is used as fundamental information for detecting other eye-related information and therefore requires high-precision detection. Known patent documents related to iris information include the following.

[0003] For example, Patent Document 1 discloses a technology that determines the iris center based on the brightness of the red channel within a bounding box, sets an initial circle at the iris center, measures the inclination of pixels on the circle, searches for the circle with the maximum inclination while expanding the circle, and calculates the center and radius of the circle with the maximum inclination as the iris center and iris radius.

[0004] Patent document 2 discloses a technology that defines the portion of an image that is darker than an arbitrary threshold value when the image is binarized as an object area, calculates the contour line of the object area for multiple different threshold values, and after calculating the contour lines for all threshold values, determines which threshold value is used to binarize the image and the contour line obtained is the true contour line of the iris granules.

[0005] However, the methods of Patent Documents 1 and 2 reduce the accuracy of iris information detection when external light, background, etc. are reflected on the cornea, and further improvement is needed.

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Publication No. 4723834

[0009] Patent Document 2: Japanese Patent Application Laid-Open No. 11-155838 Summary of the Invention

[0010] The present invention is made to solve the above-mentioned problems, and an object of the present invention is to further improve the detection accuracy of iris information.

[0011] An iris detection method according to one embodiment of the present invention is an iris detection method for an iris detection device for detecting the iris of a person captured by a camera device, wherein a computer of the iris detection device executes the following steps: acquiring a first image including the face of the person; generating a second image including an area of ​​the person's eyes from the first image; binarizing the second image to generate a third image, in which pixels having grayscale values ​​less than a threshold are represented by a first brightness value and pixels having grayscale values ​​greater than the threshold are represented by a second brightness value; replacing pixels of the third image having the second brightness value that appear within a first brightness area having the first brightness value and satisfy a specified condition with pixels of the first brightness value, thereby generating a fourth image; calculating iris information including information related to at least one of the position and size of the person's iris using the fourth image; and outputting the iris information.

[0012] According to the present invention, the detection accuracy of iris information can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is an external view of the iris detection system according to the first embodiment of the present invention.

[0014] Figure 2 This is a block diagram showing an example of the overall configuration of the iris detection system according to the first embodiment of the present invention.

[0015] Figure 3 This is a flowchart showing an example of processing of the iris detection device according to the first embodiment of the present invention.

[0016] Figure 4 This is a flowchart showing an example of iris detection processing.

[0017] Figure 5 is a schematic diagram showing the face area.

[0018] Figure 6 is a schematic diagram showing the eye detection area.

[0019] Figure 7 is a schematic diagram showing an example of a binary image.

[0020] Figure 8 Schematic diagram showing an example of a binary image subjected to narrowing processing.

[0021] Figure 9 is a schematic diagram showing another example of a binary image.

[0022] Figure 10 It is a schematic diagram showing a local area.

[0023] Figure 11 This diagram illustrates the estimated center position of the iris.

[0024] Figure 12 This is a schematic diagram showing a binary image in which a black island region appears within the pupil region.

[0025] Figure 13 Schematic diagram showing a binary image after the coating process.

[0026] Figure 14 Schematic diagram showing a binary image in which the left end pixel and the right end pixel of the pupil area are detected.

[0027] Figure 15 Schematic diagram showing a binary image in which the upper and lower pixels of the pupil area are detected.

[0028] Figure 16 This is a block diagram showing an example of the overall configuration of an iris detection system according to the second embodiment of the present invention.

[0029] Figure 17 This is a flowchart showing an example of processing of the iris detection device according to the second embodiment of the present invention.

[0030] Figure 18 is a schematic diagram showing a binary image before performing the morphological gradient operation.

[0031] Figure 19 Schematic diagrams showing an expanded image and a contracted image obtained by performing expansion and contraction processing on a binary image.

[0032] Figure 20 is a schematic diagram showing a gradient image.

[0033] Figure 21 Schematic diagram showing a binary image in which the outer and inner canthi of the eyes are detected.

[0034] Figure 22 It is a schematic diagram showing an example of a display screen displayed on a monitor.

[0035] Figure 23 This is a schematic diagram for explaining information related to the eyes. DETAILED DESCRIPTION

[0036] The process of obtaining the present invention

[0037] The human eye consists of the white of the eye and the pupil surrounded by the white of the eye. The pupil is further divided into the pupil, which is roughly circular when viewed from the front, and the annular iris surrounding the pupil. When viewed from the front, the cornea is arched in front of the pupil. If external light or background light is reflected on the cornea, this reflection appears as a high-brightness area within the pupil. If a binarization process is applied to an image of an eye where such a high-brightness area appears, a black island area will appear within the white area corresponding to the pupil. The binarization process uses a first brightness value (e.g., white) to represent darker pixels with pixel values ​​less than a threshold and a second brightness value (e.g., black) to represent brighter pixels with pixel values ​​above the threshold. If such a black island area appears within the white area, iris information such as the center position and size of the iris cannot be accurately detected.

[0038] The technology disclosed in Patent Document 1 above determines the presence or absence of highlights by comparing the number of pixels with maximum brightness values ​​in the red channel image within the bounding box of the eye with a threshold. If highlights are determined to be present, the center point of the high-contrast area surrounding the highlights is set as the iris center (paragraph 0076).

[0039] Here, the center of the high-brightness area, such as the external light and background reflected on the cornea, is not necessarily located at the center of the iris area. However, in Patent Document 1, since the center of the high-contrast area is set to the iris center position, there is a problem that the iris center position cannot be accurately detected if the center point of the high-contrast area does not coincide with the iris center position.

[0040] The technique disclosed in Patent Document 2 calculates the contour of the target area using all threshold values ​​and then determines which threshold value is used for binarization to determine whether the contour is the true contour of the iris granules (Claim 2).

[0041] However, Patent Document 2 does not take into account the reflection of external light and background onto the cornea, and therefore has a problem in not being able to detect iris information with high accuracy.

[0042] Here, the inventors of the present invention discovered that when an image containing eyes is binarized, if black pixels appearing in white areas are replaced with white pixels, iris information can be correctly detected in the replaced image, thereby deriving the various embodiments of the present invention shown below.

[0043] One aspect of the present invention relates to an iris detection method for an iris detection device for detecting the iris of a person captured by a camera device, wherein a computer of the iris detection device executes the following steps: acquiring a first image including the person's face; generating a second image including the area of ​​the person's eyes from the first image; binarizing the second image to generate a third image, in which pixels having grayscale values ​​less than a threshold are represented by a first brightness value and pixels having grayscale values ​​greater than the threshold are represented by a second brightness value; replacing pixels of the third image having the second brightness value that appear within a first brightness area having the first brightness value and satisfy a specified condition with pixels of the first brightness value, thereby generating a fourth image; calculating iris information including information related to at least one of the position and size of the person's iris using the fourth image; and outputting the iris information.

[0044] With this configuration, a fourth image is generated by replacing pixels of the second brightness value that appear within a first brightness region with a first brightness value and satisfy a predetermined condition in the third image with pixels of the first brightness value. This process then applies the first brightness value to island regions of the second brightness value that appear within the pupil region corresponding to the first brightness region. Iris information is then calculated using the fourth image, the resulting binary image. This reduces the effects of ambient light and background reflections on the cornea, further improving iris information detection accuracy.

[0045] In the iris detection method, when generating the fourth image, for each of the plurality of vertical lines constituting the third image, the pixel of the first brightness value that first appears from the upper end side of the third image, i.e., the upper end pixel, and the pixel of the first brightness value that first appears from the lower end side of the third image, i.e., the lower end pixel, are detected respectively; and when the distance between the upper end pixel and the lower end pixel is greater than a first reference distance, the pixels of the second brightness value included between the upper end pixel and the lower end pixel are judged to be pixels of the second brightness value that satisfy the prescribed condition.

[0046] With this configuration, pixels of the second luminance value located between the upper and lower pixels on a vertical line where the distance between the upper and lower pixels is greater than the first reference distance are replaced with pixels of the first luminance value. Therefore, this replacement can be performed on the vertical lines that constitute the pupil-corresponding region among the multiple vertical lines constituting the third image. As a result, islands of the second luminance value located within the pupil-corresponding region can be predominantly painted with the first luminance value.

[0047] In the iris detection method, the first brightness value may be greater than the second brightness value, and when generating the fourth image, the third image may be divided horizontally by specified pixels into a plurality of local areas, an average brightness value of each local area is calculated, and the center position of the local area with the largest average brightness value is calculated as the estimated iris center position, and only pixels of the second brightness value within the vertical line within a second reference distance from the estimated iris center position are judged to determine whether the specified condition is met.

[0048] Because the pupil is nearly circular, when the third image is divided horizontally into multiple local areas by predetermined pixel counts, local areas located toward the center of the pupil generally have higher average brightness values, with the local area containing the center of the pupil having the highest average brightness value. With this configuration, the first brightness value is set greater than the second brightness value, and the center position of the local area with the highest average brightness value among the multiple local areas is set as the estimated iris center position. Therefore, this configuration allows for simple and convenient processing to estimate the iris center position.

[0049] Furthermore, it is generally believed that the area corresponding to the pupil is located within a certain distance from the estimated center of the iris. With this configuration, since the aforementioned replacement is performed only on vertical lines located within the second reference distance from the estimated center of the iris, the aforementioned replacement can be performed on vertical lines located in the area corresponding to the pupil. This avoids coating the white part of the eye.

[0050] In the iris detection method, when calculating the iris information, a first pixel having the second brightness value that first appears in the horizontal left direction from the estimated iris center position and a second pixel having the second brightness value that first appears in the horizontal right direction from the estimated iris center position are detected in the fourth image, and a position midway between the first pixel and the second pixel is calculated as the horizontal iris center position.

[0051] With this configuration, in the fourth image, in which the island region of the second brightness value is painted with the first brightness value, starting from the estimated iris center position, a first pixel having the second brightness value is detected horizontally to the left, and a second pixel having the second brightness value is detected horizontally to the right. The center position of the iris is calculated as the middle position between the first and second pixels. Therefore, the horizontal center position of the iris can be calculated with high accuracy.

[0052] In the iris detection method, when calculating the iris information, a third pixel, which is the first pixel with the second brightness value to appear vertically on the upper side from the estimated iris center position, and a fourth pixel, which is the first pixel with the second brightness value to appear vertically on the lower side from the estimated iris center position, are detected from the fourth image, and a position midway between the third pixel and the fourth pixel is calculated as the vertical iris center position.

[0053] According to this configuration, in the fourth image, which has been painted with the first brightness value in the area corresponding to the pupil, a third pixel having the second brightness value is detected vertically upward, and a fourth pixel having the second brightness value is detected vertically downward, starting from the estimated iris center position. The position between the third and fourth pixels is then calculated as the vertical iris center position. Therefore, the vertical iris center position can be calculated with high accuracy.

[0054] In the iris detection method, positions of the upper and lower eyelids may be detected separately based on the third image.

[0055] According to this configuration, since the positions of the upper and lower eyelids are respectively detected based on the third image obtained in the process of calculating the iris information, the positions of the upper and lower eyelids can be detected while calculating the iris information.

[0056] In the iris detection method, when detecting the position of the eyelid, the position of the eyelid may be detected by performing a morphological gradient operation on the third image.

[0057] According to this configuration, since the positions of the upper and lower eyelids are detected by performing the morphological gradient calculation on the binarized third image, the positions of the upper and lower eyelids can be detected with high accuracy.

[0058] In the iris detection method, the third image may be a binary image of one of the left eye and the right eye of the person, and the positions of the outer corner of the eye and the inner corner of the eye may be detected based on the third image.

[0059] According to this configuration, the positions of the outer and inner canthi are detected based on the binarized third image obtained in the calculation of the iris information. Therefore, the positions of the outer and inner canthi can be detected while calculating the iris information.

[0060] In the iris detection method, when detecting the positions of the outer canthus and the inner canthus, in the third image, the position of the pixel at the horizontal left end having the first brightness value is detected as the position of one of the outer canthus and the inner canthus, and the position of the pixel at the horizontal right end having the first brightness value is detected as the position of the other of the outer canthus and the inner canthus.

[0061] With this configuration, in the third image, which is a binary image for either the left or right eye, the position of the horizontally leftmost pixel having the first luminance value is detected as the position of one of the outer or inner corners of the eye, and the position of the horizontally rightmost pixel having the first luminance value is detected as the position of the other of the outer or inner corners. Therefore, the positions of the outer and inner corners of the eye can be easily detected.

[0062] In the iris detection method, information related to the person's eyes may be calculated based on the positions of the outer canthus and the inner canthus.

[0063] According to this configuration, since information related to a person's eyes is calculated based on the positions of the outer canthus and the inner canthus, information that can serve as a basis for determining a disease related to the person's eyes, for example, can be calculated.

[0064] In the iris detection method, the positions of the upper and lower eyelids and the outer and inner corners of the eye can also be detected from the third image, and the distance between the center position of the iris and the position of the upper eyelid, the distance between the center position of the iris and the position of the lower eyelid, the distance between the center position of the iris and the position of the outer corner of the eye, and the distance between the center position of the iris and the position of the inner corner of the eye can be calculated based on the detection results.

[0065] This configuration calculates the distances between the center of the iris and the upper eyelid, the distance between the center of the iris and the lower eyelid, the distance between the center of the iris and the outer canthus, and the distance between the center of the iris and the inner canthus. These distances can be used to estimate a person's emotions and state.

[0066] In the iris detection method, the iris information may be superimposed and displayed on the facial image of the person displayed on a display.

[0067] According to this configuration, since the iris information is displayed superimposed on the facial image of the person displayed on the display, the calculation result of the iris information can be displayed on the facial image in real time.

[0068] Another aspect of the present invention relates to an iris detection device for detecting the iris of a person captured by a camera device, the device comprising: an image acquisition unit for acquiring a first image including the person's face; an eye region detection unit for detecting a second image including an area including the person's eyes from the first image; a binarization unit for binarizing the second image to generate a third image in which pixels having a brightness less than a threshold value are represented by a first brightness value and pixels having a brightness greater than the threshold value are represented by a second brightness value; a replacement unit for replacing pixels having the second brightness value in the third image that appear within a first brightness region having the first brightness value and satisfy a specified condition with pixels having the first brightness value, thereby generating a fourth image; an iris information calculation unit for calculating iris information including information related to at least one of the position and size of the person's iris using the fourth image; and an output unit for outputting the iris information.

[0069] Another aspect of the present invention relates to an iris detection program that causes a computer to function as an iris detection device for detecting the iris of a person captured by a camera device, and causes the computer to function as the following units: an image acquisition unit that acquires a first image including the face of the person; an eye region detection unit that detects a second image including an area including the eyes of the person from the first image; a binarization unit that binarizes the second image to generate a third image in which pixels having a brightness less than a threshold value are represented by a first brightness value and pixels having a brightness greater than the threshold value are represented by a second brightness value; a replacement unit that replaces pixels of the third image having the second brightness value that appear within a first brightness region having the first brightness value and satisfy a predetermined condition with pixels of the first brightness value, thereby generating a fourth image; an iris information calculation unit that calculates iris information including information related to at least one of the position and size of the person's iris using the fourth image; and an output unit that outputs the iris information.

[0070] According to these configurations, the same technical effects as those of the above-mentioned iris detection method can be obtained.

[0071] The present invention can also be implemented as an iris detection system that operates according to such an iris detection program. Moreover, it is needless to say that such a computer program can also be distributed via a computer-readable non-transitory recording medium such as a CD-ROM or a communication network such as the Internet.

[0072] In addition, each embodiment described below is an embodiment of a specific example of the present invention. The numerical values, shapes, components, steps, and the order of the steps shown in the following embodiments are merely examples and are not intended to limit the present invention. Moreover, among the components in the following embodiments, the components not described in the independent claims representing the most general concept are described as arbitrary components. Moreover, for all embodiments, their contents can be arbitrarily combined.

[0073] First embodiment

[0074] Figure 1 This is an external view of iris detection system 100 according to the first embodiment of the present invention. Iris detection system 100 is configured using a portable terminal device such as a smartphone or tablet. However, this is merely an example; iris detection system 100 can also be configured by appropriately combining a desktop computer or cloud server with a camera and a display.

[0075] The iris detection system 100 includes an iris detection device 1, an imaging device 2, and a display 3. The iris detection device 1 calculates iris information of a person U1 captured by the imaging device 2.

[0076] The imaging device 2 is composed of a camera mounted on a portable terminal device and is a camera capable of acquiring color visible light images at a predetermined frame rate.

[0077] Display 3 is comprised of a display device such as a liquid crystal display or an organic EL (ElectroLuminescence) display device incorporated into a portable terminal. Display 3 displays an image of the face of person U1 captured by imaging device 2. Furthermore, display 3 superimposes iris information (described later) calculated by iris detection device 1 on the image of person U1's face.

[0078] Figure 2 This is a block diagram showing an example of the overall configuration of an iris detection system 100 according to the first embodiment of the present invention. The iris detection device 1 includes a processor 10 and a memory 20. The processor 10 is, for example, a CPU (Central Processing Unit). The processor 10 includes an image acquisition unit 11, an eye region detection unit 12, a binarization unit 13, a replacement unit 14, an iris information calculation unit 15, and an output unit 16. The image acquisition unit 11 to the output unit 16 are implemented, for example, by having the processor 10 execute an iris detection program.

[0079] The image acquisition unit 11 acquires images captured by the imaging device 2. Here, the acquired images include the face of the person U1. Hereinafter, images including a face are referred to as facial images. The image acquisition unit 11 sequentially acquires facial images captured at a predetermined frame rate. The facial image is an example of a first image including a person's face.

[0080] The eye region detection unit 12 detects a facial region representing a person's face from the facial image acquired by the image acquisition unit 11. The eye region detection unit 12 can detect the facial region by inputting the facial image into a classifier pre-created for facial region detection. This classifier is, for example, a Haar cascade classifier. The facial region is, for example, a rectangular area having a size sufficient to encompass the entire face.

[0081] The eye region detection unit 12 inputs the facial image into a classifier created in advance to detect the eye detection region from the facial region, thereby detecting the eye detection region. This classifier is composed of, for example, a Haar cascade classifier. The eye detection region is a rectangular region having a size that adds a predetermined margin to the size of the left eye or the right eye. The eye region detection unit 12 detects an eye detection region including the left eye and an eye detection region including the right eye from the facial region. The eye detection region is an example of a region of the second image including a person's eyes. Hereinafter, the eye detection region including the left eye will be referred to as the "left eye detection region," and the eye detection region including the right eye will be referred to as the "right eye detection region." When the two are not distinguished, they are simply referred to as eye detection regions. The left eye refers to the eye on the left side when the person U1 is viewed from the front, and the right eye refers to the eye on the right side when the person U1 is viewed from the front. However, this is merely an example, and the relationship can also be reversed.

[0082] The binarization processing unit 13 binarizes the eye detection area and generates a binary image in which pixels having grayscale values ​​less than a threshold are represented by a first brightness value and pixels having grayscale values ​​greater than the threshold are represented by a second brightness value. The binary image is an example of a third image. When the eye detection area is composed of a color image, the binarization processing unit 13 can convert the eye detection area into a grayscale image having grayscale values ​​of, for example, 0 to 255, and perform binarization processing on the converted grayscale image. As the binarization processing, for example, Otsu's binarization processing can be used. The first brightness value is, for example, white, and the second brightness value is, for example, black. That is, in this embodiment, a binary image is generated in which darker parts are represented by white and lighter parts are represented by black. The brightness value of white is represented by, for example, 255, and the brightness value of black is represented by, for example, 0.

[0083] Here, because the image captured by the imaging device 2 is quantized using 8 bits, the grayscale image has grayscale values ​​ranging from 0 to 255. However, this is merely an example. If the image captured by the imaging device 2 is quantized using another bit number, such as 16 bits, the grayscale image can have grayscale values ​​that can be expressed using that bit number.

[0084] The binarization processing unit 13 may generate binary images for each of the left eye detection region and the right eye detection region.

[0085] The replacement unit 14 performs a color-shifting process that replaces black pixels that appear within a white region (first luminance region) composed of white pixels in a binary image and that meet predetermined conditions with white pixels. The replacement unit 14 performs the color-shifting process on both the left-eye detection region and the right-eye detection region. This generates a binary image in which the black island region that appears within the region corresponding to the pupil within the white region (hereinafter referred to as the pupil region) is colored with white pixels. This binary image subjected to the color-shifting process is an example of a fourth image.

[0086] Specifically, the replacement unit 14 detects, for each of the plurality of vertical lines constituting the binary image, an upper pixel, which is the first white pixel to appear from the upper end of the binary image, and a lower pixel, which is the first white pixel to appear from the lower end of the binary image. Furthermore, when the distance between the upper pixel and the lower pixel is greater than a first reference distance, the replacement unit 14 determines that the black pixels between the upper pixel and the lower pixel satisfy a predetermined condition.

[0087] Furthermore, the replacement unit 14 calculates the average brightness value of each of the plurality of local areas obtained by dividing the binary image horizontally by predetermined pixels, calculates the center position of the local area having the largest average brightness value as the estimated iris center position, and determines whether or not predetermined conditions are satisfied only for black pixels within the vertical line extending from the estimated iris center position to a position within the second reference distance.

[0088] The iris information calculation unit 15 calculates iris information including information related to at least one of the position and size of the person's iris using the painted binary image. The information related to the iris position includes the iris center position. The information related to the iris size includes the iris radius and the iris outer edge.

[0089] Reference Figure 6In this embodiment, the eye includes a white of the eye 103 and a pupil 110 that is circular when viewed from the front and is surrounded by the white of the eye 103. The pupil 110 includes a pupil 101 that is circular when viewed from the front and an iris 102 that is annular and surrounds the pupil 101. In this embodiment, the center positions of the iris 102, the pupil 110, and the pupil 101 are identical. The radius of the iris 102 is the distance from the center position of the iris 102 to the outer edge of the iris 102.

[0090] The output unit 16 generates a display screen in which the iris information calculated by the iris information calculation unit 15 is superimposed on the facial image acquired by the image acquisition unit 11 , and causes the display 3 to display the display screen.

[0091] The memory 20 is used as a work area of ​​the processor 10 and is composed of, for example, a RAM (Random Access Memory).

[0092] Secondly, Figure 2 The processing of the iris detection device 1 shown will be described. Figure 3 This is a flowchart showing an example of the processing of the iris detection device 1 according to the first embodiment of the present invention. Figure 3 The flowchart shown is executed at a predetermined sampling cycle, which is, for example, a frame cycle of the imaging device 2 .

[0093] In step S1, the image acquisition unit 11 acquires a face image from the camera 2. In step S2, the eye region detection unit 12 inputs the face image to a classifier for detecting a face region and detects the face region. Figure 5 is a schematic diagram showing the face area 40. Figure 5 As shown in FIG, the eye region detecting unit 12 detects a rectangular region including the upper part of the forehead, the lower part of the chin, and the hairline of the ears as the face region 40. Here, the face region 40 does not include the entire hair, but may include the entire area of ​​the hair. Figure 5 In FIG, the facial image is an image of person U1 taken from the front and includes the left eye and the right eye.

[0094] In step S3 , the eye region detection unit 12 inputs the face region 40 extracted in step S2 to a classifier for detecting eye detection regions and detects eye detection regions. Figure 6 Schematic diagram showing the eye detection area 50. Figure 6 As shown, the eye detection area 50 is a rectangular area that includes the entire eye and adds some margin to the size of the eye. Figure 6 In the example, eye detection areas 50 for the left eye and the right eye are extracted.

[0095] In step S4, the binarization processing unit 13 converts the eye detection area 50 detected in step S3 into a grayscale image. For example, the conversion to a grayscale image may be performed by calculating the average of the grayscale values ​​of the red, green, and blue components of each pixel constituting the eye detection area 50. However, this is merely an example, and other conversion processes may also be used.

[0096] In step S5 , the binarization processing unit 13 binarizes the eye detection region 50 converted into the grayscale image to generate a binary image 60 . Figure 7 is a schematic diagram showing an example of a binary image 60. Figure 7 In the example of , a binary image 60 is generated in which darker parts such as pupils and eyelashes are represented by white, and lighter parts such as white pupils and skin are represented by black. Figure 7 In the example, the eye information is represented by a white area D1 composed of white pixels. Figure 7 In the example, since there is little external light and background reflected on the cornea, no black island area appears in the white area D1. Figure 12 As shown, a black island region D2 appears.

[0097] In step S6 , the binarization processing unit 13 generates a binary image 70 by applying a narrowing-down process to the binary image 60 to remove unnecessary black areas around the white area D1 . Figure 8 is a schematic diagram showing an example of a binary image 70 that has been subjected to a narrowing process. Figure 8 In the example shown in FIG, a binary image 70 is generated by setting a circumscribed rectangle circumscribing white area D1 in binary image 60 and removing the black area outside the circumscribed rectangle. This removes double eyelids, dark circles under the eyes, moles around the eyes, and glasses around the eyes, improving the accuracy of subsequent processing.

[0098] Figure 9 is a schematic diagram showing another example of a binary image 70. Figure 9 In the example shown in FIG, the white area D1 is separated into a white area D11 representing the pupil and a white area D12 representing the eyelashes. Figure 9 When a white area D11 representing the pupil is formed as shown, the midpoints of the top, bottom, left, and right sides of the white area D11 can be determined as the iris center position.

[0099] However, due to the density of the eyelashes of person U1, the degree of makeup around the eyelashes, and the influence of decorations such as false eyelashes and eyelash extensions, Figure 8 As shown in FIG. 1 , the eyelashes and pupil may appear as a single white area D1. In this case, simply determining the iris center position as the midpoint between the upper, lower, left, and right sides of the white area D1 may significantly deviate from the actual iris center position, resulting in reduced iris center position detection accuracy. Therefore, in this embodiment, the iris center position detection accuracy is improved by performing the iris detection process described below.

[0100] In step S7, the replacement unit 14 and the iris information calculation unit 15 calculate the iris information by applying the iris detection process to the binary image 70. The details of the iris information detection process will be described in detail. Figure 4 The flowchart is described below.

[0101] In step S8, the output unit 16 generates a display screen in which the iris information calculated in step S7 is superimposed on the face image acquired in step S1, and displays it on the display 3. Figure 3 The flowchart can make the display 3 display the display screen in which the iris information is superimposed on the facial image in real time.

[0102] Next, the details of the iris detection process will be described. Figure 4 1 is a flowchart showing an example of iris detection processing. In step S40, the replacement unit 14 separates the binary image 70 into a plurality of local areas by separating the image into predetermined pixels in the X direction. Figure 10 Schematic diagram showing the local area 71. The X direction refers to the horizontal direction of the image captured by the camera 2. Figure 10 In the example, the replacement unit 14 divides the binary image 70 into ten equal parts in the horizontal direction. This divides the binary image 70 into ten strip-shaped local regions 71, each longitudinally extending in the Y direction. While the replacement unit 14 divides the binary image 70 into ten local regions 71, this is merely an example. The number of divisions may be an integer between 2 and 9, or an integer between 11 and 11. The Y direction refers to the longitudinal direction (vertical direction) of the image captured by the imaging device 2.

[0103] In step S41, the replacement unit 14 calculates the average brightness value of each of the ten local areas 71. Here, since the brightness value of white is 255 and the brightness value of black is 0, the average brightness value is calculated by, for example, the following formula.

[0104] Average brightness value = Number of white pixels in local area 71 × 255 / Number of pixels in local area 71

[0105] In step S42 , the replacement unit 14 calculates the X coordinate of the estimated iris center position. Figure 11This diagram illustrates the estimated iris center position P3. This estimated iris center position P3 is an estimate of the iris center position and differs from the final calculated iris center position. Due to factors such as double eyelids, thick eyelashes, and false eyelashes, these areas may appear excessively large as the white area D1. In this case, the white of the eye 103 may be covered with paint. To avoid this, the estimated iris center position P3 is calculated in this embodiment.

[0106] exist Figure 11 In the example shown in FIG1 , the fifth local area 71a from the left has the highest average brightness value. Therefore, the replacement unit 14 calculates the X coordinate of the midpoint of local area 71a in the X direction as the estimated iris center position P3. Depending on the width of local area 71 in the X direction, it may not be appropriate to use the midpoint of local area 71 in the X direction as the estimated iris center position P3. In such cases, the left or right end of local area 71 in the X direction may be used as the estimated iris center position P3.

[0107] In step S43, the replacement unit 14 calculates the Y coordinate of the estimated iris center position P3. Figure 11 The replacement unit 14 detects the uppermost endpoint P1 and the lowermost endpoint P2 of the white pixels in the local area 71a and calculates the midpoint between the uppermost endpoint P1 and the lowermost endpoint P2 as the Y coordinate of the estimated iris center position P3. Furthermore, due to the influence of eyelashes and makeup, the uppermost endpoint P1 and the lowermost endpoint P2 may appear in the adjacent local area 71b on the left or the adjacent local area 71c on the right. Alternatively, the replacement unit 14 may calculate the uppermost endpoint and the lowermost endpoint of each of the local areas 71a to 71c, average the three calculated uppermost endpoints to obtain an average uppermost endpoint, and average the three calculated lowermost endpoints to obtain an average lowermost endpoint, and calculate the midpoint between the average uppermost endpoint and the average lowermost endpoint as the Y coordinate of the estimated iris center position P3.

[0108] In step S44, the replacement unit 14 performs a coating process on the binary image 70. In visible light images, external light and background light may sometimes be reflected into the cornea due to factors such as ambient brightness. When this reflection is significant, a brighter area such as white appears within the black or brown pupil. In this case, if the eye image is binarized, a black island region will appear within the pupil, making it impossible to accurately detect iris information. Therefore, in this embodiment, a coating process is performed.

[0109] Figure 12 Schematic diagram showing a binary image 70 in which a black island region D2 appears within the pupil region. Figure 12, the left image shows the binary image 70 for the left eye, and the right image shows the binary image 70 for the right eye. Figure 12 As shown, black island regions D2 appear dispersedly within a white region D1 corresponding to the pupil appearing in the center of both left and right binary images 70. Filling in these black island regions D2 is a filling process.

[0110] The details of the overlay process are as follows. First, the replacement unit 14 sets a vertical line L1 parallel to the Y direction at the X coordinate of the estimated iris center position P3 in the binary image 70. Next, the replacement unit 14 detects the first white pixel that appears from the upper end of the vertical line L1 on the binary image 70 as the upper end pixel P4. Next, the replacement unit 14 detects the first white pixel that appears from the lower end of the vertical line L1 on the binary image 70 as the lower end pixel P5. Next, the replacement unit 14 determines whether the distance between the upper end pixel P4 and the lower end pixel P5 is greater than a first reference distance. If the replacement unit 14 determines that the distance between the upper end pixel P4 and the lower end pixel P5 is greater than the first reference distance, it determines that the black pixel located between the upper end pixel P4 and the lower end pixel P5 on the vertical line L1 satisfies a predetermined condition and replaces the black pixel with a white pixel. On the other hand, if the replacement unit 14 determines that the distance between the upper end pixel P4 and the lower end pixel P5 is less than the first reference distance, it does not perform the replacement on the vertical line L1. As the first reference distance, for example, an appropriate distance based on an assumed iris diameter can be adopted.

[0111] The replacement unit 14 performs this coating process on each vertical line L1 within the range of the left reference distance from the estimated iris center position P3 toward the left in the X direction, and also performs this coating process on each vertical line L1 within the range of the right reference distance from the estimated iris center position P3 toward the right in the X direction. The sum of the left reference distance range and the right reference distance range is an example of a second reference distance. The left reference distance range and the right reference distance range can be, for example, the same range. The second reference distance can be, for example, a distance slightly larger than the assumed iris diameter. This allows the coating process to be applied preferentially to the vertical lines L1 located in the pupil area.

[0112] Figure 13 Schematic diagram showing a binary image 80 after the coating process. Figure 13 The left picture shows Figure 12 The binary image 70 on the left is a binary image 80 to which the coating process is applied. Figure 13 The right figure shows Figure 12 The binary image 70 in the right figure is a binary image 80 to which the coating process is applied. Figure 13 As shown, Figure 12The black island area D2 in the image is painted with white pixels, creating a white area D3 consisting of a single white pixel. Meanwhile, the black island area in the eyelash area is not painted. In other words, the vertical line L1 in the pupil area is painted with the most emphasis.

[0113] In step S45 , the iris information calculation unit 15 detects the left end pixel and the right end pixel of the pupil area. Figure 14 This schematic diagram shows a binary image 80 in which the leftmost pixel P6 (first pixel) and the rightmost pixel P7 (second pixel) of the pupil region are detected. The replacement unit 14 examines changes in luminance values ​​pixel by pixel in the white region D3 of the binary image 80, starting from the estimated iris center position P3 and moving left and right in the X direction. Furthermore, the replacement unit 14 detects the black pixel that appears first on the left side in the X direction as the leftmost pixel P6, and the black pixel that appears first on the right side in the X direction as the rightmost pixel P7.

[0114] In step S46 , the iris information calculation unit 15 calculates the middle position between the left end pixel P6 and the right end pixel P7 as the X coordinate of the iris center position P0 .

[0115] In step S47 , the iris information calculation unit 15 detects the upper end pixel and the lower end pixel of the exit pupil area. Figure 15 This schematic diagram shows a binary image 80 in which the upper pixel P8 (third pixel) and the lower pixel P9 (fourth pixel) of the pupil area are detected. The iris information calculation unit 15 examines changes in luminance values ​​pixel by pixel in the Y direction, starting from the X coordinate of the iris center position P0 and moving upward and downward in the white area D3 of the binary image 80. Furthermore, the replacement unit 14 detects the black pixel that appears first in the upper Y direction as the upper pixel P8, and the black pixel that appears first in the lower Y direction as the lower pixel P9.

[0116] In step S48, the iris information calculation unit 15 calculates the middle position between the upper pixel P8 and the lower pixel P9 as the Y coordinate of the iris center position P0. In this way, the iris center position P0 is calculated.

[0117] In step S49, the iris information calculation unit 15 calculates the iris radius. Here, the iris information calculation unit 15 may calculate the iris radius by taking the distance between the iris center position P0 and the left pixel P6, the distance between the iris center position P0 and the right pixel P7, or the average of the two distances. Alternatively, the iris information calculation unit 15 may calculate the iris radius by taking the distance between the iris center position P0 and the upper pixel P8, the distance between the iris center position P0 and the lower pixel P9, or the average of the two distances. Alternatively, the iris information calculation unit 15 may calculate the iris radius by taking the average of these four distances. If step S49 is completed, the process proceeds to step S49. Figure 3 Alternatively, the iris information calculation unit 15 may calculate the iris outer edge using a circle having the iris center position P0 as the center and the iris radius as the radius.

[0118] Thus, according to the iris detection device 1 of the first embodiment, a binary image 80 is generated by replacing black pixels that appear within the white area D1 and satisfy predetermined conditions with white pixels, and iris information is calculated from the binary image 80. As a result, the black island area D2 that appears within the white area D1, which corresponds to the pupil within the white area, is filled with white pixels. As a result, the effects of external light and background light reflected on the cornea are suppressed, further improving the accuracy of iris information detection.

[0119] Second embodiment

[0120] Figure 16 This is a block diagram showing an example of the overall configuration of an iris detection system 100A according to a second embodiment of the present invention. The iris detection system 100A according to the second embodiment detects the eyelid, outer canthus, and inner canthus of the eye. In the second embodiment, components identical to those in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted.

[0121] The processor 10A of the iris detection device 1A further includes an eyelid detection unit 17 and an outer canthus and inner canthus detection unit 18 , similar to the processor 10 of the iris detection device 1 according to the first embodiment.

[0122] The eyelid detection unit 17 detects the positions of the upper and lower eyelids of the person U1 from the binary image 70 generated by the binarization processing unit 13. The eyelid detection unit 17 can detect the positions of the upper and lower eyelids by applying a morphological gradient operation to the binary image 70. The eyelid detection unit 17 detects the positions of the upper and lower eyelids for the binary image 70 of the left eye and the binary image 70 of the right eye, respectively.

[0123] The outer and inner canthus detection unit 18 detects the positions of the outer and inner canthus of the eye from the binary image 70 generated by the binarization processing unit 13. Here, the outer and inner canthus detection unit 18 detects the positions of the outer and inner canthus of the eye for the binary image 70 of the left eye and the binary image 70 of the right eye, respectively.

[0124] Next, the processing of the iris detection device 1A according to the second embodiment will be described. Figure 17 1A is a flowchart showing an example of processing of the iris detection device 1A according to the second embodiment of the present invention. Figure 17 In the flowchart of Figure 3 The same process is assigned the same process number. Figure 17 Omitted Figure 3 Step S8.

[0125] In step S9 following step S7 , the eyelid detection unit 17 detects the positions of the upper eyelid and the lower eyelid by performing morphological gradient calculation. Figure 18 is a schematic diagram showing a binary image 70 before a morphological gradient operation is performed.

[0126] First, the eyelid detection unit 17 applies dilation processing to the binary image 70. Dilation processing replaces the pixel of interest with a white pixel if at least one white pixel exists near the pixel of interest. Next, the eyelid detection unit 17 applies contraction processing to the binary image 70. Contraction processing replaces the pixel of interest with a black pixel if at least one black pixel exists near the pixel of interest. Figure 19 Schematic diagrams showing an expanded image 81 and a contracted image 82 obtained by performing expansion and contraction processing on a binary image 70 .

[0127] By performing the dilation process, the white area D1 included in the dilated image 81 is expanded compared to the white area D1 included in the binary image 70. By performing the contraction process, the white area D1 included in the contracted image 82 is contracted compared to the white area D1 included in the binary image 70.

[0128] Next, the eyelid detection unit 17 calculates a gradient image by subtracting the contracted image 82 from the expanded image 81 . Figure 20 Schematic diagram showing the gradient image 83 . The gradient image 83 includes the edge E1 of the white area D1 of the binary image 70 .

[0129] Next, the eyelid detection unit 17 detects the uppermost position of edge E1 as the upper eyelid position P10. Alternatively, the eyelid detection unit 17 may detect the intersection of a vertical line L1 passing through the iris center position P0 and the upper edge E1 as the upper eyelid position P10. Furthermore, the eyelid detection unit 17 may detect the intersection of a vertical line L1 passing through the iris center position P0 and the lower edge E1 as the lower eyelid position P11. This allows detection of the lower eyelid position, which exhibits a subtle brightness change and is difficult to clearly represent in the binary image 70. Alternatively, the eyelid detection unit 17 may detect the portion of the upper edge E1 connecting the left and right ends of the gradient image 83 as the upper eyelid line.

[0130] In step S10 , the outer canthus and inner canthus detecting unit 18 detects the position of the outer canthus and the position of the inner canthus. Figure 21 This is a schematic diagram showing a binary image 70 in which the outer and inner corners of the eye are detected. Since the frame of the binary image 70 is the circumscribed rectangle of the white area D1, the X coordinate of the left end of the white area D1 in the binary image 70 is the X coordinate of the left end of the binary image 70 (X11), and the X coordinate of the right end of the white area D1 is the X coordinate of the right end of the binary image 70 (X12). These two X coordinates have already been calculated when the binary image 70 is generated. Here, the outer and inner corner detection unit 18 calculates the position P12 of the outer corner of the eye and the position P13 of the inner corner of the eye using the two already calculated X coordinates. In addition, since Figure 21 This is a binary image 70 for the left eye. The left end of the white region D1 is at a position P12 of the outer corner of the eye, and the right end of the white region D1 is at a position P13 of the inner corner of the eye.

[0131] Specifically, the outer canthus and inner canthus detection unit 18 searches for white pixels, pixel by pixel, starting from the bottom of the binary image 70 toward the top. Furthermore, the outer canthus and inner canthus detection unit 18 determines the Y coordinate of the first white pixel detected as the Y coordinate of the outer canthus position P12. Similarly, the outer canthus and inner canthus detection unit 18 searches for white pixels, pixel by pixel, starting from the bottom of the binary image 70 toward the top. Furthermore, the outer canthus and inner canthus detection unit 18 determines the Y coordinate of the first white pixel detected as the Y coordinate of the inner canthus position P13. In this way, the outer canthus position P12 and the inner canthus position P13 are detected.

[0132] In step S11 , the output unit 16 generates a display screen by superimposing the iris information on the facial image calculated in step S1 and superimposing the outer corner position P12 and the inner corner position P13 on the facial image, and displays the screen on the display 3 . Figure 22is a schematic diagram showing an example of a display screen G1 displayed on display 3. On display screen G1, the iris center position P0 is superimposed and displayed at the center of the pupil. Furthermore, the upper eyelid position P10, the lower eyelid position P11, the outer corner of the eye position P12, and the inner corner of the eye position P13 are superimposed and displayed on the facial image of person U1. Furthermore, a circle L4 representing the outer edge of the iris is superimposed and displayed on the facial image. This circle L4 is calculated using the iris radius included in the iris information. Furthermore, a rectangle L3 passing through the upper eyelid position P10, the outer corner of the eye position P12, the inner corner of the eye position P13, and the lower eyelid position P11 is superimposed and displayed on the facial image.

[0133] As a result, the display screen G1 can display information related to the eyes of the person U1 , including iris information, in real time with respect to the facial image captured by the imaging device 2 .

[0134] The present invention can adopt the following modified examples.

[0135] (1) In the first and second embodiments, the first luminance value is white and the second luminance value is black in the binary images 60 , 70 , and 80 . However, the present invention is not limited thereto. The first luminance value may be black and the second luminance value may be white.

[0136] (2) The iris information calculation unit 15 can also calculate the following information related to the eyes. Figure 23 Schematic diagram for explaining information related to the eye. The information related to the eye includes distance a, distance b, distance c, distance d, and distance e.

[0137] Distance a is the distance between upper eyelid position P10 and iris center position P0. Distance a is calculated by subtracting the Y coordinate of upper eyelid position P10 from the Y coordinate of iris center position P0.

[0138] Distance b is the distance between the lower eyelid position P11 and the iris center position P0. Distance b is calculated by subtracting the Y coordinate of the iris center position P0 from the Y coordinate of the lower eyelid position P11.

[0139] Distance c is the distance between the outer corner of the eye (P12) and the iris center (P0). For the left eye, distance c is calculated by subtracting the X coordinate of the iris center (P0) from the X coordinate of the outer corner of the eye (P12).

[0140] Distance d is the distance between inner corner position P13 and iris center position P0. In the case of the left eye, distance d is calculated by subtracting the X coordinate of inner corner position P13 from the X coordinate of iris center position P0.

[0141] Distance e is the distance between the upper and lower eyelids. Distance e is calculated by dividing the Y coordinate of the upper eyelid position P10 by the Y coordinate of the lower eyelid position P11.

[0142] This makes it possible to estimate the emotion and state of the person U1.

[0143] (3) The iris information calculation unit 15 can also calculate information related to the person U1's eyes. This information related to the eyes includes the distance between the outer corners of the eyes, the distance between the inner corners of the eyes, and the distance between the pupils. The distance between the outer corners of the eyes is the distance between the left and right outer corners of the eyes. The distance between the outer corners of the eyes is calculated by subtracting the X coordinate of the outer corner position P13 of the right eye from the X coordinate of the outer corner position P13 of the left eye.

[0144] The distance between the inner corners of the right and left eyes is calculated by subtracting the X coordinate of the inner corner position P12 of the right eye from the X coordinate of the inner corner position P12 of the left eye.

[0145] The distance between the pupils is the distance between the left and right iris centers P0. It is calculated by dividing the X coordinate of the right eye's iris center P0 by the X coordinate of the left eye's iris center P0.

[0146] Furthermore, the iris information calculation unit 15 may calculate the distance between inner corners of the eyes / the distance between pupils and the distance between outer corners of the eyes / the distance between inner corners of the eyes as information on the eyes of the person U1 .

[0147] (4) Due to the increased brightness of the pupil area caused by the reflection of external light, the iris diameter may be detected to be larger or smaller than the size originally estimated as the iris diameter. In this case, the iris information cannot be correctly detected. Here, the iris information calculation unit 15 may also calculate the iris diameter and the distance between the outer corner of the eye and the inner corner of the eye, and calculate the ratio of the iris diameter to the distance between the outer corner of the eye and the inner corner of the eye. If the ratio is not within a predetermined reference ratio range, it is determined that the detection of the pupil area has failed. In this case, the iris information calculation unit 15 may output an error signal to the output unit 16 instead of outputting the iris information.

[0148] Industrial applicability

[0149] According to the present invention, since iris information can be calculated correctly, it has practical value in the technical field of iris detection.

Claims

1. An iris detection method, comprising: Let the computer of the iris detection device perform the following steps: acquiring a first image containing the face of the person; generating a second image of a region containing the person's eyes from the first image; Binarizing the second image to generate a third image, wherein pixels having grayscale values ​​less than a threshold are represented by first brightness values, and pixels having grayscale values ​​greater than the threshold are represented by second brightness values; replacing pixels of the third image, which are present in a first brightness region having the first brightness value and satisfy a predetermined condition, with pixels of the first brightness value, thereby generating a fourth image; calculating iris information including information related to at least one of a position and a size of an iris of the person using the fourth image; outputting the iris information, When generating the fourth image, for each of the multiple vertical lines constituting the third image, the pixel of the first brightness value that first appears from the upper end side of the third image, i.e., the upper end pixel, and the pixel of the first brightness value that first appears from the lower end side of the third image, i.e., the lower end pixel, are detected respectively. When the distance between the upper end pixel and the lower end pixel is greater than the first reference distance, the pixels of the second brightness value contained between the upper end pixel and the lower end pixel are judged as pixels of the second brightness value that meet the specified conditions.

2. The iris detection method according to claim 1, wherein: The first brightness value is greater than the second brightness value, When generating the fourth image, the third image is divided into a plurality of local areas by dividing the third image in the horizontal direction according to specified pixels, and the average brightness value of each local area is calculated. The center position of the local area having the largest average brightness value is calculated as the estimated iris center position, and only the pixels of the second brightness value within the vertical line within a second reference distance from the estimated iris center position are judged to determine whether the specified condition is met.

3. The iris detection method according to claim 2, wherein: When calculating the iris information, a first pixel having the second brightness value that first appears in the horizontal direction on the left side from the estimated iris center position and a second pixel having the second brightness value that first appears in the horizontal direction on the right side from the estimated iris center position are detected in the fourth image, and a position between the first pixel and the second pixel is calculated as the horizontal iris center position.

4. The iris detection method according to claim 2 or 3, characterized in that: When calculating the iris information, the third pixel, which is the first pixel with the second brightness value to appear vertically on the upper side from the estimated iris center position, and the fourth pixel, which is the first pixel with the second brightness value to appear vertically on the lower side from the estimated iris center position, are detected from the fourth image, and a position midway between the third pixel and the fourth pixel is calculated as the vertical iris center position.

5. The iris detection method according to any one of claims 1 to 3, characterized in that: The positions of the upper and lower eyelids are also detected based on the third image.

6. The iris detection method according to claim 5, characterized in that: When detecting the position of the eyelid, the position of the eyelid is detected by performing a morphological gradient operation on the third image.

7. The iris detection method according to any one of claims 1 to 3, characterized in that: The third image is a binary image of one of the left eye and the right eye of the person, The positions of the outer canthus and the inner canthus of the eye are also detected based on the third image.

8. The iris detection method according to claim 7, wherein: When detecting the positions of the outer corner of the eye and the inner corner of the eye, in the third image, the position of the pixel at the horizontal left end having the first brightness value is detected as the position of one of the outer corner of the eye and the inner corner of the eye, and the position of the pixel at the horizontal right end having the first brightness value is detected as the position of the other of the outer corner of the eye and the inner corner of the eye.

9. The iris detection method according to claim 7, wherein: Information related to the person's eyes is also calculated based on the positions of the outer canthus and the inner canthus.

10. The iris detection method according to any one of claims 1 to 3, characterized in that: The positions of the upper and lower eyelids and the outer and inner corners of the eyes are also detected from the third image, and based on the detection results, the distance between the center position of the iris and the position of the upper eyelid, the distance between the center position of the iris and the position of the lower eyelid, the distance between the center position of the iris and the position of the outer corner of the eye, and the distance between the center position of the iris and the position of the inner corner of the eye are calculated.

11. The iris detection method according to any one of claims 1 to 3, characterized in that: The iris information is also displayed superimposed on the face image of the person displayed on the display.

12. An iris detection device for detecting the iris of a person photographed by a camera, characterized in that include: an image acquisition unit, configured to acquire a first image including the face of the person; an eye region detecting unit configured to detect a second image including a region of the person's eyes from the first image; a binarization processing unit, binarizing the second image to generate a third image, wherein pixels having brightness less than a threshold are represented by a first brightness value, and pixels having brightness greater than the threshold are represented by a second brightness value; a replacing unit for replacing pixels of the third image, which are present in a first luminance region having the first luminance value and satisfy a predetermined condition, with pixels of the first luminance value, thereby generating a fourth image; an iris information calculation unit that calculates iris information including information related to at least one of a position and a size of the person's iris using the fourth image; and an output unit, outputting the iris information, When generating the fourth image, for each of the multiple vertical lines constituting the third image, the pixel of the first brightness value that first appears from the upper end side of the third image, i.e., the upper end pixel, and the pixel of the first brightness value that first appears from the lower end side of the third image, i.e., the lower end pixel, are detected respectively. When the distance between the upper end pixel and the lower end pixel is greater than the first reference distance, the pixels of the second brightness value contained between the upper end pixel and the lower end pixel are judged as pixels of the second brightness value that meet the specified conditions.

13. A program product comprising an iris detection program for causing a computer to function as an iris detection device for detecting the iris of a person photographed by an imaging device, wherein: The iris detection program enables the computer to function as: an image acquisition unit, configured to acquire a first image including the face of the person; an eye region detecting unit configured to detect a second image including a region of the person's eyes from the first image; a binarization processing unit, binarizing the second image to generate a third image, wherein pixels having brightness less than a threshold are represented by a first brightness value, and pixels having brightness greater than the threshold are represented by a second brightness value; a replacing unit for replacing pixels of the third image, which are present in a first luminance region having the first luminance value and satisfy a predetermined condition, with pixels of the first luminance value, thereby generating a fourth image; an iris information calculation unit that calculates iris information including information related to at least one of a position and a size of the person's iris using the fourth image; and an output unit, outputting the iris information, When generating the fourth image, for each of the multiple vertical lines constituting the third image, the pixel of the first brightness value that first appears from the upper end side of the third image, i.e., the upper end pixel, and the pixel of the first brightness value that first appears from the lower end side of the third image, i.e., the lower end pixel, are detected respectively. When the distance between the upper end pixel and the lower end pixel is greater than the first reference distance, the pixels of the second brightness value contained between the upper end pixel and the lower end pixel are judged as pixels of the second brightness value that meet the specified conditions.

Images