CN110334579B

CN110334579B - Iris recognition image determining method and device, terminal equipment and storage medium

Info

Publication number: CN110334579B
Application number: CN201910372040.1A
Authority: CN
Inventors: 黄通兵; 王钦民; 王云飞
Original assignee: Beijing 7Invensun Technology Co Ltd
Current assignee: Beijing 7Invensun Technology Co Ltd
Priority date: 2019-05-06
Filing date: 2019-05-06
Publication date: 2021-08-03
Anticipated expiration: 2039-05-06
Also published as: CN110334579A

Abstract

The embodiment of the invention discloses a method and a device for determining an iris identification image, terminal equipment and a storage medium. The method comprises the following steps: displaying an initial gaze identity; determining a target gaze identification based on the initial gaze identification; and taking the target user image when the user gazes at the target gazing identification as an iris recognition image. The method avoids the technical problem of reduced iris recognition precision caused by incomplete iris information when a user image is directly acquired as the iris recognition image, the iris recognition precision of the iris recognition image can be improved by performing iris recognition on the iris recognition image, and the iris recognition image most suitable for performing iris recognition is acquired before the iris recognition is performed, so that the iris recognition time is effectively reduced.

Description

Iris recognition image determining method and device, terminal equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of image processing, in particular to a method and a device for determining an iris recognition image, terminal equipment and a storage medium.

Background

The iris is an oblate circular membrane in the middle of the eye wall, located between the cornea and the crystalline lens. Each iris contains a unique structure of features like crowns, nanocrystals, filaments, spots, structures, pits, rays, wrinkles and streaks. Therefore, identification can be performed based on the iris.

The iris identification method mainly comprises the following steps: image acquisition, preprocessing, feature extraction and feature matching. When the acquired eye image is processed, clear iris information is required to be included in the eye image, so that identity recognition can be effectively performed based on the acquired eye image.

However, in practical applications of iris recognition, when the iris recognition is embedded in devices such as Virtual Reality (VR) or Augmented Reality (AR), the position of the image capturing device in each device is not fixed, which may cause a part of iris information to be lost in an eye image captured by the image capturing device, thereby affecting the accuracy of iris recognition.

Disclosure of Invention

The embodiment of the invention provides a method and a device for determining an iris recognition image, terminal equipment and a storage medium, which are used for improving the accuracy of iris recognition and reducing the time of iris recognition.

In a first aspect, an embodiment of the present invention provides an iris identification image determining method, including:

displaying an initial gaze identity;

determining a target gaze identification based on the initial gaze identification;

and taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

Optionally, the determining a target gaze identifier based on the initial gaze identifier includes:

acquiring a first user image when a user gazes at the initial gazing identification, and extracting first shape information of eyes in the first user image;

and determining a target gazing identification according to the first shape information.

Optionally, the determining a target gaze identifier according to the first shape information includes:

when the difference value of the long axis and the short axis of the first shape information is lower than a first set value, taking the initial gazing mark as a target gazing mark;

and when the difference value of the long axis and the short axis of the first shape information is higher than a first set value, projecting the first shape information to the position of the initial gazing mark to form a first projected closed-loop shape, and determining a target gazing mark based on a first straight line where the short axis of the first projected closed-loop shape is located.

Optionally, the determining a target gaze identifier based on a first straight line where a short axis of the first projected closed-loop shape is located includes:

determining a next gaze identity based on a first line in which a short axis of the first projected closed-loop shape lies;

acquiring a second user image when the user watches the next watching identification;

and determining a target gazing identification according to the second shape information corresponding to the eyes in the second user image.

Optionally, the determining a next gaze identifier based on a first straight line where a short axis of the first projected closed-loop shape is located includes:

and selecting a mark with a first straight line distance greater than a set threshold value from the short axis of the first projection closed-loop shape as a next watching mark.

Optionally, the determining a target gaze identifier according to second shape information corresponding to an eye in the second user image includes:

extracting second shape information of the eyes in the second user image;

when the difference value of the long axis and the short axis of the second shape information is lower than a first set value, determining the next watching identification as a target watching identification;

and when the difference value of the long axis and the short axis of the second shape information is higher than a first set value, projecting the second shape information to the position of the next watching mark to form a second projection closed-loop shape, and taking the intersection point of the first straight line and the second straight line where the short axis of the second projection closed-loop shape is as a target watching mark.

Optionally, the iris recognition image determining method further includes:

an initial gaze identity is determined from the size of the display device.

Optionally, the determining an initial gaze identifier according to a size of the display device includes:

determining vertex information of the display equipment according to the size of the display equipment;

an initial gaze identification is determined based on the vertex information.

In a second aspect, an embodiment of the present invention further provides an iris identification image capturing apparatus, including:

the display module is used for displaying the initial gazing identification;

a target gaze identity determination module to determine a target gaze identity based on the initial gaze identity;

and the image determining module is used for taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

In a third aspect, an embodiment of the present invention further provides a terminal device, including:

one or more processors;

storage means for storing one or more programs;

the one or more programs are executed by the one or more processors, so that the one or more processors implement the iris recognition image determination method provided by the embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the iris recognition image determination method provided by the embodiment of the present invention.

The embodiment of the invention provides a method, a device, terminal equipment and a storage medium for determining an iris recognition image, wherein an initial gazing identification is displayed firstly, and then a target gazing identification is determined based on the initial gazing identification; and finally, the target user image when the user gazes at the target gazing mark is used as the iris recognition image, so that the technical problem that the iris recognition precision is reduced due to the fact that iris information is possibly incomplete when the user image is directly obtained as the iris recognition image is solved.

Drawings

Fig. 1 is a schematic flowchart of a method for determining an iris recognition image according to an embodiment of the present invention;

fig. 2a is a schematic flowchart of a method for determining an iris recognition image according to a second embodiment of the present invention;

fig. 2b is a schematic view of a display scenario of an initial gaze identifier according to an embodiment of the present invention;

fig. 2c is a schematic image diagram of a first user image acquired during initial gaze identification shown in the user gaze view 2b according to the embodiment of the present invention;

fig. 3a is a schematic flowchart of a method for determining an iris recognition image according to a third embodiment of the present invention;

fig. 3b is a schematic view of a display scene of a next gaze identifier according to an embodiment of the present invention;

fig. 3c is a schematic image diagram of a second user image collected at the time of the next gaze identifier shown in the user gaze view 3b according to the embodiment of the present invention;

fig. 4a is a schematic flowchart of a method for determining an iris recognition image according to a fourth embodiment of the present invention;

FIG. 4b is a diagram illustrating a target gaze identification scenario in an embodiment of the present invention;

fig. 4c is an image schematic diagram of a target user image when the user gazes at the target gaze identifier shown in fig. 4b in the embodiment of the present invention;

fig. 5 is a schematic structural diagram of an iris identification image determining apparatus according to a fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of a terminal device according to a sixth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict. In the following embodiments, optional features and examples are provided in each embodiment, and various features described in the embodiments may be combined to form a plurality of alternatives, and each numbered embodiment should not be regarded as only one technical solution.

Example one

Fig. 1 is a flowchart of an iris recognition image determining method according to an embodiment of the present invention, which may be applicable to a case of determining an iris recognition image, and in particular, may be applicable to a case of determining a target user image for iris recognition, that is, an iris recognition image, before iris recognition, where the method may be performed by an iris recognition image determining apparatus, where the apparatus may be implemented by software and/or hardware and is generally integrated on a terminal device, and in this embodiment, the terminal device includes, but is not limited to: computers, personal digital assistants, and/or cellular telephones.

As shown in fig. 1, a method for determining an iris recognition image according to an embodiment of the present invention includes the following steps:

and S101, displaying an initial gazing mark.

In this embodiment, the initial gaze identification may be understood as an identification that requires the user's gaze for the first time. Such as an initial gaze identifier, an initial gaze trajectory, or textual or visual information that is of interest to the gaze. The initial gaze identification may include location information and display form information. For example, the location information may identify a display location of the initial gaze identification. The display form information may identify the form, such as a point, circle, or text, in which the initial gaze identification is presented when displayed.

This step may display a predetermined initial gaze identity within the user's field of view. When the user acquires the iris recognition image through the display device, the initial gaze identification may be displayed on the display device. The means for the initial gaze identification is not limited herein, and may be determined by one skilled in the art based on the field of view of the user. It should be noted that the initial gaze identifier may also be set randomly, as long as the initial gaze identifier is ensured to be within the field of view of the user.

It is to be understood that, when displaying the initial gaze identifier, a prompt message may be displayed at a set distance from the display location of the initial gaze identifier to prompt the user to gaze the initial gaze identifier. The specific content of the prompt information is not limited as long as the prompt effect can be achieved. The set distance is not limited as long as it is close to the display position of the initial gaze mark.

A target gaze identity can be determined based on the initial gaze identity, thereby facilitating determination of an iris recognition image.

And S102, determining a target gazing identification based on the initial gazing identification.

In this embodiment, the target gaze identifier may be understood as a gaze identifier, a gaze track, text information or image information that may arouse gaze interest, and the like, which is provided for the user to gaze and can acquire an iris recognition image.

After displaying the initial gaze identification, a target gaze identification may be determined based on the initial gaze identification. The target gaze identity may be determined, for example, by analyzing a first user image when the user gazes at the initial gaze identity.

The means of determining the target gaze identity may be: at least two initial gazing identifiers are displayed on a display device in advance, and then a first user image corresponding to each initial gazing identifier is obtained, wherein the first user image can comprise user eyes. And then analyzing each first user image to extract eye feature information, such as features of a pupil position, a pupil shape, an iris position, an iris shape, an eyelid position, an eye corner position, a light spot (also called purkinje spot) position and the like. And then determining the position information of the gazing identification of the direction of the optical axis vertical to the user image based on the determined eye characteristic information and the corresponding initial gazing identification so as to obtain the target gazing identification. Generally, the optical axis and the visual axis have fixed angles, and the visual axis and the watching direction are consistent.

The means of determining the target gaze identity may also be: the method comprises the steps of displaying a predetermined initial gazing identification on display equipment, then determining a next gazing identification based on a first user image when a user gazes at the initial gazing identification, and then determining a gazing identification with an optical axis perpendicular to the direction of a user image based on a second user image and the first user image when the user gazes at the next gazing identification so as to obtain a target gazing identification.

After the target watching identification is determined, the target user image of the target watching identification watched by the user can be used as an iris identification image to carry out iris identification.

S103, taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

In this embodiment, the target user image may be understood as a user image when the user gazes at the target gaze identifier. An iris recognition image may be understood as an image used for iris recognition. The iris recognition image may be considered as an ideal image for iris recognition, and includes a set amount of features necessary for iris recognition. The setting amount can be determined according to actual conditions, and the iris recognition accuracy is higher as the numerical value of the setting amount is larger. It is understood that the shape of the pupil in the iris recognition image may be a circle or an approximate circle, that is, the shape of the pupil in the iris recognition image may satisfy that the difference between the major axis and the minor axis is lower than the first setting value.

Specifically, when the target user image is acquired in this step, the target gazing identifier may be displayed within the field of view of the user to prompt the user to gaze at the target gazing identifier. When the user performs iris recognition using the display device, a target gaze identification may be displayed on the display device to prompt the user to gaze at the target gaze identification. Then, acquiring a user image through an image acquisition device, and directly taking the user image as a target user image after acquiring the user image; the user image can be analyzed to determine whether the eye features corresponding to the user image meet the set requirements, so that the user is prevented from looking at the target watching identification.

The setting requirement may be determined according to eye feature information corresponding to the user image when the optical axis is perpendicular to the user image, for example, a difference between a long axis and a short axis of the pupil having a circular or approximately circular shape is lower than a first setting value. The first setting value may be set according to actual conditions, and is not limited herein.

In the embodiment, the gazing mark with the optical axis perpendicular to the direction of the user image is used as the target gazing mark, and then the target user image when the user gazes at the target gazing mark is used as the iris recognition image, so that the technical problem of reduced iris recognition accuracy caused by the fact that users with strabismus or eye problems or users with overlarge included angle (kappa angle) between the optical axis and the visual axis use the user image given by the visual axis direction to perform iris recognition can be solved.

The iris identification image determining method provided by the embodiment of the invention comprises the steps of firstly displaying an initial gazing identification, and then determining a target gazing identification based on the initial gazing identification; and finally, the target user image when the user gazes at the target gazing mark is used as the iris recognition image, so that the technical problem that the iris recognition precision is reduced due to the fact that iris information is possibly incomplete when the user image is directly obtained as the iris recognition image is solved.

Example two

Fig. 2a is a schematic flow chart of a method for determining an iris recognition image according to a second embodiment of the present invention, and the second embodiment is optimized based on the above embodiments. In this embodiment, determining the target gaze identifier based on the initial gaze identifier is further embodied as: acquiring a first user image when a user gazes at the initial gazing identification, and extracting first shape information of eyes in the first user image; and determining a target gazing identification according to the first shape information.

Please refer to the first embodiment for a detailed description of the present embodiment.

As shown in fig. 2a, a method for determining an iris recognition image according to a second embodiment of the present invention includes the following steps:

and S201, displaying an initial gazing mark.

Fig. 2b is a schematic view of a display scene of an initial gaze identifier according to an embodiment of the present invention. The rectangular area in fig. 2b may be a field of view of the user, and when determining the iris recognition image, the initial gaze identifier 21 may be displayed within the field of view, and prompt information, such as please look at the point, may be displayed near the initial gaze identifier 21, as follows.

The technical means for predetermining the initial gaze identifier is not limited, and an identifier may be selected from any one of the identifiers within the field of view of the user as the initial gaze identifier, or the initial gaze identifier may be determined based on the size of the display device.

S202, a first user image when the user gazes at the initial gazing identification is obtained, and first shape information of the eyes in the first user image is extracted.

In this embodiment, the first user image may be understood as a user image when the user gazes at the initial gaze identification. The first shape information may be understood as information representing the shape of an eye in the first user image. Wherein the eye shape may be represented by a pupil shape or an iris shape. The first shape information may be information formed by fitting eye contour information of the eye portion in the first user image. Wherein the eye contour information may be determined by the contour of the pupil and/or the contour of the iris. Illustratively, the first shape information includes a circle, an approximate circle, an ellipse, or the like. The first shape information may further include major axis, minor axis, and/or boundary information corresponding to a circle, an approximate circle, or an ellipse, respectively, and the like.

After the initial gazing identification is displayed, the first user image when the user gazes at the initial gazing identification can be obtained through the image acquisition device. In the step, the user image acquired after the initial gazing identification is displayed can be directly used as the first user image, and the user image acquired after the initial gazing identification is displayed and the gazing instruction is confirmed by the user can be used as the first user image. The acquisition means for confirming the gaze instruction is not limited, and may be determined by detecting the pressing state of the physical key or may be acquired by voice recognition.

Fig. 2c is a schematic image diagram of a first user image acquired during initial gaze identification shown in the user gaze view 2b according to the embodiment of the present invention. Fig. 2c shows a first user image when the user 22 gazes at the initial gaze identity. The first user image includes a fresnel ring.

After the first user image is acquired, the first shape information of the eye portion in the first user image may be extracted in this step, and the extracting means is not limited as long as the first shape information corresponding to the first user image can be determined. Illustratively, the pupil contour feature or the iris contour feature of the eye in the first user image is extracted, then the pupil contour feature and the iris contour feature are subjected to closed-loop fitting to form a closed-loop curve, and then the first shape information is obtained based on the closed-loop curve.

The technical means for performing the closed-loop fitting is not limited, and a direct calculation method, a quadratic polynomial fitting method, a standard equation fitting method, and the like may be used. The specific content included in the pupil contour feature or the iris contour feature is not limited, as long as the corresponding pupil contour and iris contour can be represented, such as the pupil edge point coordinate, the pupil center coordinate, the iris edge point coordinate, and the iris center coordinate.

S203, determining a target gazing identification according to the first shape information.

Specifically, after the first shape information is determined, the step may first determine whether the first shape information meets a setting requirement, and when the first shape information meets the setting requirement, the initial gaze identifier may be directly used as the target gaze identifier.

When the first shape information does not meet the setting requirement, a next gaze identification may be determined based on the first shape information to determine a target gaze identification based on the initial gaze identification and the next gaze identification or directly based on the next gaze identification.

And S204, taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

After the target gazing identification is determined, the target user image when the user gazes at the target gazing identification can be used as the iris recognition image.

It should be noted that, when the target gaze identifier is the initial gaze identifier, the target user image is the first user image, and this step may directly use the first user image as the iris recognition image.

The iris identification image determining method provided by the embodiment of the invention embodies the operation of determining the target gazing identification. The method can display an initial gazing identification firstly, then obtain a first user image when a user gazes at the initial gazing identification, further determine a target gazing identification based on first shape information of eyes in the first user image, and take the target user image when the target gazing identification is gazed as an iris recognition image. Compared with the method for randomly displaying the iris recognition images corresponding to the at least two gazing identification determination target gazing identifications, the method effectively improves the accuracy of iris recognition image determination.

The present embodiment further provides an alternative embodiment, in which the target gaze identification is determined from the first shape information, the optimization comprises:

when the difference value of the long axis and the short axis of the first shape information is lower than a first set value, taking the initial gazing mark as a target gazing mark; and when the difference value of the long axis and the short axis of the first shape information is higher than a first set value, projecting the first shape information to the position of the initial gazing mark to form a first projected closed-loop shape, and determining a target gazing mark based on a first straight line where the short axis of the first projected closed-loop shape is located.

When determining the target gaze identity, the first shape information may be analyzed to determine that the initial gaze identity is the target gaze identity; or proceed to determine a target gaze identification based on the first shape information.

When the difference between the major axis and the minor axis of the first shape information is lower than the first set value, the eye feature information of the first user image may be considered to satisfy the requirement of the eye feature in the iris recognition image. The initial gaze identification may be used as a target gaze identification and the first user image may be used as an iris recognition image accordingly.

When the difference between the major axis and the minor axis of the first shape information is higher than the first setting value, it may be considered that the current initial gaze identifier is not the target gaze identifier, and then the target gaze identifier needs to be further determined based on the first shape information. In particular, the first shape information may be projected at the initial gaze identification location to form a first projected closed loop shape.

For example, when the difference between the major axis and the minor axis of the first shape information is higher than the first setting value, the projection of the first shape information to the initial gaze identification position may be embodied as: the center of the first shape information is placed at the initial gaze identification location, and the angle after the projection of the first shape information may be determined based on the included angle of the short axis or the long axis and the horizontal direction, or the short axis or the long axis and the vertical direction.

It will be appreciated that the shape of the eyes in the user image is circular if the image capture device is facing the user's eyes before the user moves. When the eyes of the user move, the included angle between the boundary point of the eyes and the image acquisition device in the moving direction is reduced, the projection corresponding to the eyes is reduced, the short direction of the eyes is an elliptical short axis, and the direction of the short axis is parallel to the connecting line of the two gazing marks before and after moving.

When the first shape information is projected to the position of the mobile gazing mark, the straight line of the short axis of the first projected closed-loop shape passes through the mobile gazing mark, namely the target gazing mark. Therefore, the straight line where the target watching identification is located can be determined based on the straight line where the first projection closed-loop shape short shaft is located, and therefore the target watching identification can be further determined.

EXAMPLE III

Fig. 3a is a schematic flow chart of a method for determining an iris recognition image according to a third embodiment of the present invention, and the second embodiment is optimized based on the above embodiments. In this embodiment, the target gaze identity is determined based on a first line in which a short axis of the first projected closed-loop shape is located, and the optimization includes: determining a next gaze identity based on a first line in which a short axis of the first projected closed-loop shape lies; acquiring a second user image when the user watches the next watching identification; and determining a target gazing identification according to the second shape information corresponding to the eyes in the second user image.

Further, the present embodiment further optimizes the following steps: an initial gaze identity is determined from the size of the display device.

For a detailed description of the present embodiment, please refer to the above embodiments.

As shown in fig. 3a, a method for determining an iris recognition image according to a third embodiment of the present invention includes the following steps:

s301, determining an initial gazing identification according to the size of the display equipment.

In the present embodiment, the display device may be understood as a device that acquires an iris recognition image. The dimensions may be characterized by length, width, or resolution. The present embodiment may determine the initial gaze identity based on the size of the display device before displaying the initial gaze identity. Such as setting the initial gaze identity at a boundary location of the display device to improve subsequent extraction of the first shape information. Because when the initial gaze identifier is set at the boundary position of the display device, the eye features in the corresponding user image, such as the pupil shape, can form an obvious ellipse in which the difference between the major axis and the minor axis is greater than the set value, and the effect is better when the first shape information extraction is performed on the obvious ellipse. The specific value of the set value is not limited, and those skilled in the art can set the value according to the actual application scenario.

The boundary position may be a boundary of the display device or a distance position set from the boundary of the display device.

The display device may include a display device, such as a display screen, and may further include a light source, an image capture device, and a driving device. Wherein, the light source can be an infrared LED light source. Since the infrared LED light source does not affect the vision of the eye. The infrared LED light sources can comprise 2 groups or more than 2 groups, and each group at least comprises one infrared LED light source. The infrared LED light sources can be arranged in a set mode, such as a circle, a triangle and the like. The light source can illuminate to shoot human eye information, and then the human eye information is reflected to the image acquisition device through the cornea to be used as parameters for eyeball tracking and sight line estimation;

an image acquisition device, such as an infrared camera device, an infrared image sensor, a camera or a video camera. The image acquisition device can shoot user images required by eyeball tracking and iris recognition, such as target user images when a user gazes at a target gazing mark;

a driving device: driving the image acquisition device and the infrared LED light source, performing image preprocessing or communicating with other equipment and the like.

And S302, displaying an initial gazing mark.

S303, acquiring a first user image when the user gazes at the initial gazing identification, and extracting first shape information of eyes in the first user image.

The process of acquiring the first user image may be that the infrared light source irradiates the eyes of the user, the image acquisition device photographs the eyes, and the reflection point of the light source on the cornea, that is, the light spot, is correspondingly photographed, thereby acquiring the eye image with the light spot as the first user image.

S304, judging whether the difference value of the long axis and the short axis of the first shape information is lower than a first set value, if so, executing S305; if not, go to S306.

When determining the target gaze identity based on the first shape information, it may be determined whether a difference between a major axis and a minor axis of the first shape information is lower than a first set value. If so, the initial gaze identity may be taken as the target gaze identity, i.e., S305 is performed. If not, a next gaze identity may be further determined to derive a target gaze identity, i.e. S306 may be performed.

And S305, taking the initial gazing identification as a target gazing identification, and executing S309.

S306, projecting the first shape information to the position of the initial gaze identifier to form a first projected closed-loop shape, and determining a next gaze identifier based on a first straight line where a short axis of the first projected closed-loop shape is located.

When the difference between the major axis and the minor axis of the first shape information is lower than the first set value, the step may project the first shape information to the initial gaze identification position to form a first projected closed-loop shape. The projection means can refer to the technical means adopted in the projection in the second embodiment, and details are not described here.

Wherein the first projected closed-loop shape may be understood as a projected shape of the first shape information at the gaze identification location. When the first projection closed-loop shape is projected, it is required to ensure that the center of the first projection closed-loop shape is the initial gaze identification position, and the angle of the first projection closed-loop shape is the same as the angle of the first shape information formed by fitting the eyes in the first user image.

After the first projected closed-loop shape is determined, a next gaze identification may be determined based on a first line along which a short axis of the first projected closed-loop shape lies. Specifically, because the first straight line where the short axis of the first projected closed-loop shape is located passes through the target gaze identifier, any identifier outside the first straight line may be selected as the next gaze identifier, so as to determine the target gaze identifier based on the next gaze identifier.

And S307, acquiring a second user image when the user gazes at the next gazing identification.

After the next gaze identity is determined, the next gaze identity may be displayed within the user's field of view and in the same plane as the initial gaze identity. When the iris recognition image is acquired through the display device, a next gaze identifier may be displayed on the display device, and then a second user image when the user gazes at the next gaze identifier is acquired. The means for acquiring the second user image may refer to the means used for acquiring the first user image, and is not described herein again.

Fig. 3b is a schematic view of a display scene of a next gaze identifier according to an embodiment of the present invention. The rectangular area in fig. 3b may be a field of view range of the user, and when determining the iris recognition image, the next gaze identifier 31 may be displayed within the field of view range, and prompt information, such as please look at the point, may be displayed near the next gaze identifier 31, as follows.

Fig. 3c is an image schematic diagram of a second user image acquired at the time of the next gaze identifier shown in the user gaze view 3b according to the embodiment of the present invention. Fig. 3c shows a second user image when the user 32 is looking at the next gaze identity. The second user image includes a fresnel ring.

And S308, determining a target gazing identification according to the second shape information corresponding to the eyes in the second user image.

The second shape information may be understood to represent eye shape information in the second user image. Wherein the eye shape may be represented by a pupil shape or an iris shape.

The means for determining the second shape information of the eye in the second user image may refer to the technical means for determining the first shape information, which is not described herein in detail.

The step may determine the target gaze identifier according to the second shape information, for example, when a difference between a major axis and a minor axis of the second shape information is lower than a first set value, the next gaze identifier may be directly used as the target gaze identifier, otherwise, the target gaze identifier may be determined based on the first straight line and the second shape information.

S309, taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

When the next gazing mark is the target gazing mark, the second user image can be directly used as an iris recognition image; otherwise, the target gazing identification can be displayed, and the target user image when the user gazes at the target gazing identification is used as the iris recognition image.

The iris identification image determining method provided by the third embodiment of the invention embodies the operation of determining the initial gazing identification and the operation of determining the target gazing identification according to the first straight line where the short axis of the first projection closed-loop shape is located. By using the method, the initial gazing identification is determined based on the size of the display equipment, and the eyes in the first user image are closer to an obvious ellipse when the first user image is extracted, so that the fitting effect can be improved, and the target gazing identification can be determined more accurately. When the target watching identification is determined, the second shape information corresponding to the next watching identification is determined based on the first straight line, and the target watching identification can be accurately obtained, so that the efficiency of obtaining the iris recognition image is improved.

Further, the determining a next gaze identifier based on a first line in which a short axis of the first projected closed-loop shape lies includes: and selecting a mark with a first straight line distance greater than a set threshold value from the short axis of the first projection closed-loop shape as a next watching mark.

It is to be understood that when determining the next gaze identifier based on the first line, an identifier having a distance from the first line along which the short axis of the first projected closed-loop shape lies that is greater than a set threshold may be selected as the next gaze identifier. Setting the threshold value can be set by a person skilled in the art according to actual conditions, and is not limited herein.

The greater the distance between the next gaze identifier and the first line is, the greater the offset between the next gaze identifier and the first line is, so that the higher the accuracy of determining the intersection point of the first line and the second line determined by the second shape information as the target gaze identifier is.

Further, determining an initial gaze identity based on the size of the display device, the optimizing comprising:

determining vertex information of the display equipment according to the size of the display equipment; an initial gaze identification is determined based on the vertex information.

Wherein vertex information may be understood as coordinate information of the vertices of the display device. For example, vertices of a display device include, but are not limited to: upper left corner, upper right corner, lower left corner and lower right corner.

When the position information of the initial gazing identification is determined according to the size of the display device, the initial gazing identification can be further limited to be located at the vertex position of the display device, and the graph formed by the eyes in the first user image is closer to an obvious ellipse, so that the extraction effect is more accurate when the first shape information in the first user image is extracted.

After determining the size of the display device, vertex information of the display device may be determined based on the size of the display device. The means for determining the vertex information is not limited, and the vertex information may be determined based on the minimum value and the maximum value in the length and width directions of the display device, for example. The vertex information is not limited to the coordinate information of which vertex in the display device.

After determining the vertex information, the vertex information may be directly used as an initial gaze identifier, or the initial gaze identifier may be set at a position in the display device that is a preset value from the vertex information. The selection of the preset value is not limited herein, and can be set by a person skilled in the art according to the size of the display device.

Example four

Fig. 4a is a schematic flow chart of a method for determining an iris recognition image according to a fourth embodiment of the present invention, and the fourth embodiment is optimized based on the foregoing embodiments. In this embodiment, determining a target gaze identifier according to second shape information corresponding to an eye in the second user image, and optimizing includes:

extracting second shape information of the eyes in the second user image;

when the difference value of the long axis and the short axis of the second shape information is lower than a second set value, determining the next watching identification as a target watching identification;

and when the difference value between the long axis and the short axis of the second shape information is higher than a second set value, projecting the second shape information to the position of the next watching sign to form a second projected closed-loop shape, and taking the intersection point of the first straight line and the second straight line where the short axis of the second projected closed-loop shape is as a target watching sign.

As shown in fig. 4a, a method for determining an iris recognition image according to a fourth embodiment of the present invention includes the following steps:

s401, determining an initial gazing identification according to the size of the display equipment.

And S402, displaying the initial gazing identification.

S403, acquiring a first user image when the user gazes at the initial gazing identification, and extracting first shape information of the eye in the first user image.

S404, judging whether the difference value of the long axis and the short axis of the first shape information is lower than a first set value, if so, executing S405; if not, go to step S406.

S405, taking the initial gazing identification as a target gazing identification, and executing S412.

S406, projecting the first shape information to the position of the initial gaze identifier to form a first projected closed-loop shape, and determining a next gaze identifier based on a first straight line where a short axis of the first projected closed-loop shape is located.

And S407, acquiring a second user image when the user gazes at the next gazing identification.

And S408, extracting second shape information of the eyes in the second user image.

When the target gaze identifier is determined according to the second shape information corresponding to the eye in the second user image, the second shape information of the eye in the second user image may be extracted first. For example, the eye of the second user image may be fitted first, and the specific fitting means may refer to technical means adopted when determining the first shape information, which is not described herein again.

S409, judging whether the difference value of the long axis and the short axis of the second shape information is lower than a second set value, if so, executing S410; if not, S411 is executed.

After the second shape information is determined, it may be determined whether a difference between a major axis and a minor axis of the second shape information is lower than a second set value, and if so, the next gaze identifier may be considered as the target gaze identifier, i.e., S410 is performed. If not, the target gaze identity may be further determined, i.e., S411 may be performed.

It should be noted that specific values of the first setting value and the second setting value are not limited, and those skilled in the art can set the values according to actual situations. The first set value and the second set value may be equal or different.

And S410, determining the next gaze identifier as a target gaze identifier, and executing S412.

The target fixation mark can be represented by coordinates, and the coordinates of the target fixation mark and the next fixation mark can be regarded as the same.

S411, projecting second shape information to the position of the next watching sign to form a second projected closed-loop shape, and taking the intersection point of the first straight line and a second straight line where the short axis of the second projected closed-loop shape is as a target watching sign.

When the difference value between the major axis and the minor axis of the second shape information is lower than a second set value, the second shape information may be projected to a next gaze identification position to obtain a second projected closed-loop shape.

The determining means of the second projected closed-loop shape can refer to the determining means of the first projected closed-loop shape, and is not limited herein.

After the second projected closed-loop shape is obtained, the step may use an intersection point of the first straight line and a second straight line where the second projected closed-loop shape is located as the target gaze identifier. It can be understood that the target gaze identifier is located on a straight line on which the short axis of the projected closed-loop shape is located, and therefore an intersection point of the first straight line and the second straight line is the target gaze identifier. The projected closed-loop shape comprises a first projected closed-loop shape and/or a second projected closed-loop shape.

Fig. 4b is a schematic view of a scene of target gaze identification in an embodiment of the present invention. The intersection point of the first straight line of the short axis of the first projected closed-loop shape 41 determined by the initial gaze indicator and the second straight line of the short axis of the second projected closed-loop shape 42 determined by the next gaze indicator in fig. 4b is the target gaze indicator 43. The target gaze identity 43 may be displayed in a display device.

And S412, taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

When the next gazing mark is the target gazing mark, a second user image obtained by directly gazing the next gazing mark by the user can be determined as an iris recognition image. When the target gazing mark is at the intersection point position, the target gazing mark can be displayed firstly, and then the target user image when the user gazes at the target gazing mark is used as the iris recognition image.

Fig. 4c is an image schematic diagram of a target user image when the user gazes at the target identification shown in fig. 4b in the embodiment of the present invention. Referring to fig. 4c, the pupil in the user 44 is circular and can include a set amount of features necessary for iris recognition, and the target user image can be an iris recognition image.

The technical solution of the embodiment of the present invention is exemplarily described as follows:

iris recognition requires clearer and more stable iris information, and iris information in a user image obtained in the absence of guidance is not complete enough, so that the recognition accuracy is reduced. The guiding case may be considered as the acquisition of an iris recognition image by the target gaze identification provided in the present embodiment.

In the actual use process, especially when the iris recognition is embedded into equipment such as VR/AR, the iris recognition is only one auxiliary application in the project, the used equipment camera, namely the image acquisition device, has an indefinite position, and partial images lose iris information, so that the iris recognition is not friendly enough, and the iris recognition precision is low.

In view of the above situations, the present embodiment provides a guidance scheme for prompting the user to gaze through an indication identifier in a scene, i.e., an initial gaze identifier, so as to obtain an iris recognition image, so that the best iris image can be provided in the fixed device.

The technical scheme of the embodiment can be considered as that the iris recognition image is obtained through the prompt mark, namely the target fixation mark, so as to carry out iris recognition on the iris recognition image.

Specifically, a user is prompted to watch an initial watching identification at the upper left corner of the display device in a view field to obtain a corresponding first user image, then a first projection closed-loop shape is placed at the position of the initial watching identification based on the first user image, and a next watching identification which is not located on the first straight line is determined based on a first straight line where a short axis of the first projection closed-loop shape is located. And prompting the user to watch the next watching identification in the view field, and correspondingly acquiring a second user image of the next watching identification watched by the user. The location of the initial gaze identification may be at a minimum and/or maximum location in the horizontal and/or vertical direction of the display device. As long as it can be ensured that the horizontal and vertical coordinate ranges of the initial gazing identifier all include the coordinates of the target gazing identifier. E.g., upper left, upper right, lower left, and lower right.

Then, according to the specific relation (the optical axis and the visual axis are fixed in angle, and the visual axis and the annotation direction are consistent) existing between the eyeball rotation and the fixation position, the approximate position of the target fixation mark in the direction of the optical axis vertical to the eye diagram (the user image) is calculated, and the user is prompted to fix the mark so as to collect the target user image. And finally, taking the target user image as an iris recognition image for iris recognition.

In addition, when the target watching identification is determined, user images corresponding to a plurality of watching identifications can be collected, eyeball angles corresponding to the images and the optical axis vertical to the images are calculated according to the watching identifications, the corresponding user images and the specific relation existing between the eyeball rotation and the watching positions, and the eyeballs of the users are rotated to the angles through the watching guidance.

When the technical scheme provided by the embodiment is used for collecting the iris recognition image, the user is guided to watch the target watching identification, the optical axis is used as an image searching basis, and the collected iris recognition image can provide more complete iris information, so that the iris recognition precision is improved, and the waste of computing resources caused by multiple times of iris recognition is reduced.

According to the iris identification image determining method provided by the fourth embodiment of the invention, the operation of determining the target watching identification according to the second shape information corresponding to the eye part in the second user image is embodied, and by using the method, after the second shape information is determined, whether the next watching identification is used as the target watching identification or the intersection point of the first straight line and the second straight line is used as the target watching identification can be determined, so that the target watching identification determining efficiency is improved.

EXAMPLE five

Fig. 5 is a schematic structural diagram of an iris recognition image determining apparatus according to a fifth embodiment of the present invention, which may be adapted to determine an iris recognition image, and in particular, may be adapted to determine a target user image for iris recognition, that is, an iris recognition image, before iris recognition, where the apparatus may be implemented by software and/or hardware and is generally integrated on a terminal device.

As shown in fig. 5, the apparatus includes: a display module 51, a target gaze identity determination module 52 and an image determination module 53;

the display module 51 is configured to display an initial gaze identifier;

a target gaze identity determination module 52 for determining a target gaze identity based on the initial gaze identity;

and the image determining module 53 is configured to use the target user image when the user gazes at the target gazing identifier as an iris recognition image.

In this embodiment, the apparatus first displays an initial gaze identifier through the display module 51; then determining, by the target gaze identification determination module 52, a target gaze identification based on the initial gaze identification; and finally, the image determining module 53 takes the target user image when the user gazes at the target gazing identification as an iris recognition image.

The embodiment provides an iris identification image acquisition device, which can display an initial gazing mark at first; then determining a target gaze identity based on the initial gaze identity; and finally, the target user image when the user gazes at the target gazing mark is used as the iris recognition image, so that the technical problem that the iris recognition precision is reduced due to the fact that iris information is possibly incomplete when the user image is directly obtained as the iris recognition image is solved.

Further, the target gaze identification determination module 52 optimizes including:

Further, the target gaze identity determination module 52, when determining the target gaze identity from the first shape information, optimizes including:

Further, the target gaze identity determination module 52, when determining the target gaze identity based on the first line on which the short axis of the first projected closed-loop shape is located, optimizes by:

Further, the target gaze identity determination module 52, when determining the next gaze identity based on the first line on which the short axis of the first projected closed loop shape lies, optimizes including:

Further, when determining the target gaze identifier according to the second shape information corresponding to the second user image, the target gaze identifier determining module 52 optimizes the target gaze identifier by:

fitting the second user image to obtain second shape information corresponding to the second user image;

extracting second shape information of the eyes in the second user image;

Further, the apparatus further comprises: an initial gaze identity determination module to: an initial gaze identity is determined from the size of the display device.

Further, the initial gaze identity determination module is further configured to:

an initial gaze identification is determined based on the vertex information.

The iris identification image acquisition device can execute the iris identification image acquisition method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

EXAMPLE six

Fig. 6 is a schematic structural diagram of a terminal device according to a sixth embodiment of the present invention. As shown in fig. 6, a terminal device provided in the sixth embodiment of the present invention includes: one or more processors 61 and storage 62; the processor 61 in the terminal device may be one or more, and one processor 61 is taken as an example in fig. 6; storage 62 is used to store one or more programs; the one or more programs are executed by the one or more processors 61, so that the one or more processors 61 implement the iris recognition image determination method according to any one of the embodiments of the present invention.

The terminal device may further include: an input device 63 and an output device 64.

The processor 61, the storage device 62, the input device 63 and the output device 64 in the terminal equipment may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 6.

The storage device 62 in the terminal device, as a computer-readable storage medium, may be used to store one or more programs, which may be software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the iris recognition image determination methods provided in the first, second, third, and fourth embodiments of the present invention (for example, the modules in the iris recognition image determination device shown in fig. 5 include the display module 51, the target gaze identification determination module 52, and the image determination module 53). The processor 61 executes various functional applications and data processing of the terminal device by executing software programs, instructions and modules stored in the storage device 62, that is, implements the iris recognition image determination method in the above-described method embodiments.

The storage device 62 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. Further, the storage device 62 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage device 62 may further include memory located remotely from the processor 61, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input means 63 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the terminal device, and the input means 63 may include an image capture means. The output device 64 may include a display device such as a display screen and a light source.

And, when the one or more programs included in the above-mentioned terminal device are executed by the one or more processors 61, the programs perform the following operations:

displaying an initial gaze identity; determining a target gaze identification based on the initial gaze identification; and taking the target user image when the user gazes at the target gazing identification as an iris recognition image.

EXAMPLE seven

A seventh embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program for executing an iris recognition image determination method when executed by a processor, the method including:

Optionally, the program may be further configured to perform an iris recognition image determination method according to any embodiment of the present invention when executed by a processor.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. A computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take a variety of forms, including, but not limited to: an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An iris identification image determination method, comprising:

displaying an initial gaze identity;

taking a target user image when the user gazes at the target gazing identification as an iris recognition image;

the determining a target gaze identification based on the initial gaze identification comprises:

determining a target gazing identifier according to the first shape information;

the determining a target gaze identity from the first shape information comprises:

when the difference value of the long axis and the short axis of the first shape information is higher than a first set value, projecting the first shape information to the position of the initial gazing mark to form a first projected closed-loop shape, and determining a target gazing mark based on a first straight line where the short axis of the first projected closed-loop shape is located;

the determining a target gaze identification based on a first line in which a short axis of the first projected closed-loop shape lies comprises:

2. The method of claim 1, wherein determining a next gaze identification based on a first line along which a short axis of the first projected closed-loop shape lies comprises:

and selecting a mark as a next watching mark, wherein the distance between the mark and a first straight line where the short axis of the first projection closed-loop shape is located is greater than a set threshold value.

3. The method of claim 1, wherein determining a target gaze identification from second shape information corresponding to an eye in the second user image comprises:

extracting second shape information of the eyes in the second user image;

4. The method of claim 1, further comprising:

an initial gaze identity is determined from the size of the display device.

5. The method of claim 4, the determining an initial gaze identification as a function of a size of a display device, comprising:

an initial gaze identification is determined based on the vertex information.

6. An iris identification image acquisition apparatus, comprising:

the display module is used for displaying the initial gazing identification;

the image determining module is used for taking a target user image when the user gazes at the target gazing identification as an iris recognition image;

the target watching identification determining module is further used for acquiring a first user image when a user watches the initial watching identification, and extracting first shape information of eyes in the first user image;

when determining the target gazing identification according to the first shape information, the method comprises the following steps:

when determining the target gaze identification based on the first straight line where the short axis of the first projected closed-loop shape is located, the method comprises:

7. A terminal device, comprising:

one or more processors;

storage means for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the iris recognition image determination method as claimed in any one of claims 1-5.

8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out an iris identification image determination method as claimed in any one of claims 1 to 5.