CN110210333A - A kind of focusing iris image acquiring method and device automatically - Google Patents

Abstract

The invention relates to the technical field of image acquisition, in particular to an automatic focusing type iris image acquisition method and device, which is applied to a controller. The controller is electrically connected to a motor and a camera, the camera is arranged on a carrier, and the motor is used to drive the carrier to move, The method includes: acquiring a first face image collected by a camera, using an angle between a main optical axis of the camera and a horizontal plane when the camera captures the first face image as a first angle, and processing the first face image to obtain The first human eye position of the first face image, according to the first angle, the first human eye position and the first preset position, calculate the first deflection angle, control the carrier to drive the camera to rotate the first deflection angle, and finally control the The iris image is obtained by shooting with the camera, and the present invention can accurately shoot the iris at the shooting position by using one camera, which improves the convenience and cost performance of iris image collection.

Description

An auto-focusing iris image acquisition method and device

technical field

The present invention relates to the technical field of image acquisition, in particular to an automatic focusing type iris image acquisition method and device.

Background technique

Iris recognition mainly includes five key steps: image acquisition, image preprocessing, iris segmentation, iris feature extraction, and feature classification. The clarity of the iris image collected in the first step will directly affect the accuracy and speed of iris recognition. Therefore, it is very important to quickly acquire an iris image with sufficient sharpness within a certain period of time. In the prior art, two or more fixed-focus cameras are usually used for iris image acquisition. However, this method is not only troublesome to operate, but also It is not convenient enough, but also increases the cost of hardware, and the cost performance is not high.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an auto-focusing iris image acquisition method and device, which aims to improve the convenience and cost-effectiveness of iris image acquisition.

In order to achieve the above object, the present invention provides the following technical solutions:

An auto-focusing iris image acquisition method is applied to a controller, wherein the controller is electrically connected to a motor and a camera, the camera is arranged on a carrier, and the motor is used to drive the carrier to move, and the method includes the following steps: :

acquiring the first face image collected by the camera, and taking the angle between the main optical axis of the camera and the horizontal plane when the camera shoots the first face image as the first angle;

processing the first face image to obtain the first eye position of the first face image;

calculating a first deflection angle according to the first angle, the first human eye position and the first preset position;

controlling the carrier to drive the camera to rotate the first deflection angle;

Control the camera to shoot to obtain an iris image.

Further, the carrier is also relatively provided with a backplane, and the backplane is provided with a positioning frame for identifying the position of the human face. Before acquiring the first human face image collected by the camera, the method further includes:

controlling the motor to drive the carrier to move toward the backplane;

Control the camera to face the direction of the backplane.

Specifically, the step of processing the first face image to obtain the first eye position of the first face image includes:

reduce the first face image;

performing target detection on the first face image to obtain the first eye region in the first face image;

The first center coordinates of the first human eye region are obtained, and the first center coordinates are used as the first human eye position.

Specifically, the step of obtaining the first center coordinates of the first human eye region includes:

Acquire all the first human eye coordinates corresponding to the first human eye region, wherein the first human eye coordinates are the coordinates of the first human eye region in the first human face image; for all the first human eye coordinates The first human eye coordinates are averaged to obtain the first center coordinates.

Specifically, the first deflection angle is calculated by the following expression:

θ=(y ₁ -y ₀ )α, where θ is the first deflection angle, y ₁ is the ordinate of the first human eye position in the first face image, and y ₀ is the first preset position at The ordinate in the first face image, α is the first angle.

An auto-focusing iris image acquisition device is applied to a controller, the controller is electrically connected with a motor and a camera, the camera is arranged on a carrier, and the motor is used to drive the carrier to move, and the device includes :

an acquisition module, configured to acquire the first face image collected by the camera, and take the angle between the main optical axis of the camera and the horizontal plane when the camera shoots the first face image as the first angle;

a processing module, configured to process the first human face image to obtain the first human eye position of the first human face image; according to the first angle, the first human eye position and the first preset position, calculating the first deflection angle; controlling the carrier to drive the camera to rotate the first deflection angle;

The shooting module is used to control the camera to shoot to obtain an iris image.

Further, the carrier is also relatively provided with a backplane, and the backplane is provided with a positioning frame for identifying the position of the human face. Before acquiring the first human face image collected by the camera, the processing module is further used for:

controlling the motor to drive the carrier to move toward the backplane;

Control the camera to face the direction of the backplane.

Specifically, the processing module is also specifically used for:

reduce the first face image;

performing target detection on the first face image to obtain the first eye region in the first face image;

The first center coordinates of the first human eye region are obtained, and the first center coordinates are used as the first human eye position.

Specifically, the processing module is also specifically used for:

Acquire all the first human eye coordinates corresponding to the first human eye region, wherein the first human eye coordinates are the coordinates of the first human eye region in the first human face image; for all the first human eye coordinates The first human eye coordinates are averaged to obtain the first center coordinates.

Specifically, the processing module is also specifically used for:

The first deflection angle is calculated by the following expression:

θ=(y ₁ -y ₀ )α, where θ is the first deflection angle, y ₁ is the ordinate of the first human eye position in the first face image, and y ₀ is the first preset position at The ordinate in the first face image, α is the first angle.

The beneficial effects of the present invention are as follows: the present invention discloses an auto-focusing iris image acquisition method and device, which is applied to a controller, wherein the controller is electrically connected to a motor and a camera, the camera is arranged on a carrier, and the motor For driving the carrier to move, by acquiring the first face image collected by the camera, the angle between the main optical axis of the camera and the horizontal plane when the camera shoots the first face image is taken as the first angle; processing a face image to obtain a first eye position of the first face image; calculating a first deflection angle according to the first angle, the first eye position and the first preset position; controlling the The carrier drives the camera to rotate the first deflection angle; controls the camera to shoot to obtain the iris image, the invention can accurately shoot the iris at the shooting position by using one camera, which improves the convenience and cost performance of iris image collection.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings required in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some of the present invention. In the embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative labor.

1 is a schematic diagram of a connection relationship of a controller according to an embodiment of the present invention;

2 is a schematic structural diagram of a camera, a carrier, and a backplane provided by an embodiment of the present invention;

3 is a schematic flowchart of an auto-focusing iris image acquisition method according to an embodiment of the present invention;

Fig. 4 is a flow chart of steps before step S100 shown in Fig. 3;

Fig. 5 is the sub-step flow chart of step S200 shown in Fig. 3;

FIG. 6 is a schematic structural diagram of an auto-focusing iris image acquisition device according to an embodiment of the present invention.

Detailed ways

The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

Iris recognition mainly includes five key steps: image acquisition, image preprocessing, iris segmentation, iris feature extraction, and feature classification. The clarity of the iris image collected in the first step will directly affect the accuracy and speed of iris recognition. Therefore, it is very important to quickly acquire iris images with sufficient sharpness within a certain period of time.

When the user is too close or too far from the lens, the iris image captured by the iris camera will become blurred, which cannot meet the subsequent iris image coding requirements. For this reason, the user needs to move forward or backward to adjust the distance so that the captured iris image Meet system coding requirements. In order to make the iris recognition system more convenient, user-friendly and intelligent, the existing iris recognition system will be equipped with a distance sensor to prompt the user to move forward, backward, or in the Within a certain distance range, the lens of the iris camera has the function of automatic zoom. When the user is closer to the lens, the zoom makes the focal length of the lens shorter and the magnification smaller, and when the user is farther away from the lens, the focal length of the lens becomes longer and the magnification becomes larger, so as to keep the collected iris image to a certain level The image clarity meets the coding requirements of the iris recognition system.

However, the existing technologies above all require the user's eyes and the iris camera on the identification device to be kept at substantially the same height. However, when the user is in a higher position or a lower position, the user needs to adjust his own position according to the height of the recognition device, such as stepping on feet or squatting, etc., which is inconvenient in practical applications and has certain limitations.

In view of the above problems, an auto-focusing iris image acquisition method and device are provided, which can not only accurately locate the iris position by adjusting the moving position of the camera 3, but also improve the convenience of iris image acquisition; Shooting to improve the cost-effectiveness of iris image acquisition.

Referring to FIG. 1 and FIG. 2 in combination, an auto-focusing iris image acquisition method provided in this embodiment is applied to a controller 1, and the controller 1 is electrically connected to the motor 2 and the camera 3, and the camera 3 is arranged on the On the carrier 4 , the motor 2 is used to drive the carrier 4 to move.

The controller 1 can be an integrated circuit chip with signal processing capability, the controller 1 can be a general-purpose processor, including a central processing unit, a network processor, etc., or a digital signal processor, an application-specific integrated circuit, a field programmable Gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

The camera 3 is electrically connected to the controller 1, and is used for photographing the user's face under the control of the controller 1, collecting a face image and transmitting the face image to the controller 1, and under the control of the controller 1 , the user's eye is photographed, an iris image is collected, and the iris image is transmitted to the controller 1 . The camera 3 can be, but is not limited to, an iris camera.

The motor 2 is electrically connected to the controller 1 and is used to move under the control of the controller 1, thereby driving the carrier 4 to move, and the camera 3 provided on the carrier 4 also moves accordingly. The carrier 4 may be, but is not limited to, a rotatable structure such as a pan/tilt, a pod, etc., which is not limited here.

The motor 2 in this embodiment can drive the carrier 4 to move in three directions, up and down, left and right, and front and rear. The motor 2 used can also control the rotation of the carrier 4 to drive the camera 3 to rotate. The motor 2 may be, but is not limited to, a geared motor.

Based on the above-mentioned controller 1, a possible implementation manner of an auto-focusing iris image acquisition method is given below. The execution subject of the method may be the above-mentioned controller 1. Please refer to FIG. 3, which shows an embodiment of the present invention. Provided is a flow chart of an auto-focusing iris image acquisition method.

The method includes the following steps:

Step S100: Obtain the first face image collected by the camera 3, and take the angle between the main optical axis of the camera 3 and the horizontal plane when the camera 3 shoots the first face image as the first angle.

In this embodiment, the first human face image may be an image including a human face captured by the camera 3 . The step of acquiring the first face image collected by the camera 3 can be understood as: the controller 1 sends a control instruction to the camera 3 to control the camera 3 to capture the face, obtain the first face avatar, and then send the first face image. to controller 1.

In one embodiment, the angle at which the camera 3 shoots the first face image may be based on the horizontal plane, and the angle between the main optical axis of the camera 3 and the horizontal plane when the camera 3 shoots the first face image is taken as the first an angle.

As a further improvement of this embodiment, the carrier 4 is also provided with a back plate 5 oppositely, and the back plate 5 is provided with a positioning frame for identifying the position of the face. Referring to FIG. 4 , before step S100, the method further includes: :

Step S110 , controlling the motor 2 to drive the carrier 4 to move toward the backplane 5 .

Step S120 , controlling the camera 3 to face the direction of the backplane 5 .

In this embodiment, by controlling the motor 2 to drive the carrier 4 to rotate, the camera 3 is controlled to face the direction of the backplane 5 .

The position of the camera 3 is preliminarily adjusted before shooting, which ensures that the human eye is within the preferred shooting range of the camera 3 and a high-definition iris image can be obtained.

Step S200: Process the first human face image to obtain a first eye position of the first human face image.

In this embodiment of the present invention, the first human eye position may be the position coordinates representing the human eyes in the first face image, specifically, the average coordinates of all coordinates corresponding to the human eye region, or the positions of two eyes The mean coordinate of the coordinates. The step of processing the first face image to obtain the position of the first human eye of the first face image can be understood as inputting the first face image into a preset model to perform face detection and feature point matching, and obtain two The position coordinates of the eyes, add the position coordinates of the two eyes, and then divide by 2 to get the first human eye position. The preset model includes a face detection model and a feature point matching model, where the face detection model can be a model obtained by training a non-deep learning algorithm (for example, a sliding window, artificial features and a classifier), or it can be obtained based on deep learning training. The model (several convolutional neural network cascade regression), the feature point matching model can be a model (average face model and feature point description vector) trained based on the point distribution model algorithm, or a model based on deep learning training (Several convolutional neural networks cascade from coarse to fine).

In this embodiment of the present invention, the location coordinates may be determined in the following manner:

Taking the lower left corner of the image as the origin, the width direction of the image as the abscissa, and the length direction of the image as the ordinate, establish a plane coordinate system on the image; set the value range of the abscissa and ordinate of any point on the image to be [0 ,1], the abscissa value of any point on the image is the ratio of the vertical distance from the point to the ordinate to the width of the image, and the ordinate value of any point on the image is the ratio of the vertical distance from the point to the abscissa to the length of the image.

Referring to FIG. 5, step S200 may further include the following sub-steps:

Step S210, reducing the first face image.

In the embodiment of the present invention, the step of reducing the first face image can be understood as using the proximity interpolation method or bilinear interpolation to reduce the first face image, so as to reduce the amount of subsequent image data processing .

As an implementation manner, when the proportion of the human face in the first human face image is relatively large, the first human face image is subjected to reduction processing. The first face image can be detected by setting two fixed position coordinates, if the corresponding pixel values of the first face image in the first face image of the two fixed position coordinates are within a preset pixel value range within, it is considered that the proportion of the face in the first face image is larger. The preset pixel value range may be a user-defined pixel value for determining the face area. Specifically, the two fixed position coordinates can be respectively close to the opposite corners in the first face image (for example, upper left and lower right, or lower left and upper right).

Step S220: Perform target detection on the first human face image to obtain a first human eye region in the first human face image.

In this embodiment of the present invention, the first human eye region may be a region corresponding to the human eye in the first human eye image. The step of performing target detection on the first face image to obtain the first eye region in the first face image may be a target detection algorithm based on SSD (Single-Shot-Multi-Box-Detector). Region detection is performed on the first face image to obtain a first human eye region, and the first human eye region is a rectangle.

In other embodiments of the present invention, a first face image based on a target detection algorithm based on YOLO (You-Only-Look-Once) may also be collected for region detection to obtain a first eye region.

Step S230: Obtain the first center coordinates of the first human eye region, and use the first center coordinates as the first human eye position.

In this embodiment of the present invention, the first center coordinate may be an average coordinate of all the coordinates corresponding to the first human eye region in the first human face image. The step of obtaining the first center coordinates of the first human eye region and using the first center coordinates as the first human eye position can be understood as: first, acquiring all the first human eyes corresponding to the first human eye region Eye coordinates, where the first human eye coordinates are the coordinates of the first human eye region in the first human face image; then, average all the first human eye coordinates to obtain the first center coordinates, that is, the first human eye Location. For example, if all the obtained coordinates of the first eye region in the first face image are (0.54, 0.65), (0.55, 0.63) and (0.5, 0.68) respectively, then the first center coordinate is taken as the first Human eye position, then the first human eye position is (0.53, 0.65).

Step S300: Calculate a first deflection angle according to the first angle, the first human eye position and the first preset position.

In this embodiment of the present invention, the first preset position is a preset position in all images captured by the first camera 3. For example, the first preset position is a position where the width of the image is 1/3 and the height of the image is 2/3. Then, the abscissa of the first preset position in the first face image is 1/3, and the ordinate of the first preset position in the first face image is 2/3. When the position of the first human eye is equal to the first preset position, it can be considered that the position of the first human eye is at the first preset position, and the iris of the human eye can be directly photographed without adjusting the camera 3 to obtain an iris image; When the ordinate of the position of the human eye in the first face image is greater than the ordinate of the first preset position in the first face image, it can be considered that the position of the first human eye is higher than the first preset position , adjust the camera 3 to deflect upward; when the ordinate of the first human eye position in the first face image is smaller than the ordinate of the first preset position in the first face image, it can be considered that the first When the position of the human eye is lower than the first preset position, the camera 3 is adjusted to deflect downward. The first deflection angle may be the angle at which the carrier 4 needs to be rotated, so that the camera 3 can capture the iris of the human eye.

The step of calculating the first deflection angle according to the first angle, the first human eye position and the first preset position can be understood as: the controller 1 pre-acquires and stores the first angle, and then according to the first angle, the first person The eye position and the first preset position calculate the first deflection angle. Specifically, assuming that the first human eye position is φ ₁ (x ₁ , y ₁ ), and the first preset position is φ ₀ (x ₀ , y ₀ ), the first deflection angle calculation formula is as follows:

θ=(y ₁ -y ₀ )α, where θ is the first deflection angle, and α is the first angle. When θ<0, the carrier 4 is deflected upward by |θ|, and when θ>0, the carrier 4 is deflected downward by |θ|. For example, when the position of the first human eye is (0.53, 0.65), the ordinate of the first preset position in the first face image is 0.67, and the first angle is 10 degrees, the first deflection angle=(0.65 -0.67)*10 degrees=-0.2 degrees, then the carrier 4 is deflected upward by 0.2 degrees.

Step S400, controlling the carrier 4 to drive the camera 3 to rotate by a first deflection angle.

The carrier 4 is rotated by a first deflection angle to drive the camera 3 to rotate to a shooting position corresponding to the position of the first human eye.

In the embodiment of the present invention, the controller 1 controls the carrier 4 to rotate by the first deflection angle, and the camera 3 is arranged on the carrier 4. According to the above reasoning, the camera 3 can be rotated to the shooting position corresponding to the first human eye position.

Step S500 , controlling the camera 3 to shoot to obtain an iris image.

In the embodiment of the present invention, after fine-tuning the first deflection angle of the carrier 4 to drive the camera 3 to rotate to the shooting position corresponding to the first human eye position, the camera 3 is controlled to shoot at the shooting position. Specifically, the controller 1 sends a The control command is sent to the camera 3, and the camera 3 is controlled to shoot the human eye at the shooting position to obtain the iris image.

Compared with the prior art, the embodiment of the present invention has the following advantages:

The iris can be accurately photographed at the photographing position by using one camera 3, which improves the convenience and cost-effectiveness of iris image acquisition.

A possible implementation manner of an auto-focusing iris image acquisition device is given below. The auto-focusing iris image acquisition device can be implemented by using the controller 1 in the above embodiment and the structures or components electrically connected to it. Referring to FIG. 6 , FIG. 6 shows a schematic block diagram of an auto-focusing iris image acquisition device provided by an embodiment of the present invention. The iris image acquisition device includes an acquisition module 100 , a processing module 200 and a photographing module 300 .

The acquisition module 100 is configured to acquire the first face image collected by the camera 3, and the angle between the main optical axis of the camera 3 and the horizontal plane when the camera 3 shoots the first face image is taken as the first angle;

The processing module 200 is configured to process the first human face image to obtain the first human eye position of the first human face image; according to the first angle, the first human eye position and the first preset position , calculate the first deflection angle; control the carrier 4 to drive the camera 3 to rotate the first deflection angle;

The photographing module 300 is configured to control the camera 3 to photograph to obtain an iris image.

In the embodiment of the present invention, the carrier 4 is further provided with a backplane 5 oppositely, and the backplane 5 is provided with a positioning frame for identifying the position of the face. Before acquiring the first face image collected by the camera 3, The processing module 200 is also used for:

Controlling the motor 2 to drive the carrier 4 to move toward the backplane 5;

Control the camera 3 to face the direction of the backplane 5 .

Specifically, the processing module 200 is also specifically used for:

reduce the first face image;

performing target detection on the first face image to obtain the first eye region in the first face image;

The first center coordinates of the first human eye region are obtained, and the first center coordinates are used as the first human eye position.

Specifically, the processing module 200 is also specifically used for:

Acquire all the first human eye coordinates corresponding to the first human eye region, wherein the first human eye coordinates are the coordinates of the first human eye region in the first human face image; for all the first human eye coordinates The first human eye coordinates are averaged to obtain the first center coordinates.

Specifically, the processing module 200 is also specifically used for:

The first deflection angle is calculated by the following expression:

θ=(y ₁ -y ₀ )α, where θ is the first deflection angle, y ₁ is the ordinate of the first human eye position in the first face image, and y ₀ is the first preset position at The ordinate in the first face image, α is the first angle.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only-Memory), random access memory (RAM, Random-Access-Memory), magnetic disk or optical disk and other various programs that can store programs medium of code. It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprises" does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The series of detailed descriptions listed above are only specific descriptions for the feasible embodiments of the present invention, and they are not used to limit the protection scope of the present invention. Changes should all be included within the protection scope of the present invention.

Claims (10)

1. a kind of automatic focusing iris image acquiring method, which is characterized in that be applied to controller, the controller and motor It is electrically connected with camera, the camera is set on carrier, and the motor is for driving the carrier mobile, the method Include:

The first facial image for obtaining camera acquisition, when camera is shot the first facial image camera primary optical axis with Angle between horizontal plane is as first angle；

First facial image is handled, the first position of human eye of first facial image is obtained；

According to the first angle, the first position of human eye and the first predeterminated position, the first deflection angle is calculated；

Controlling the carrier drives camera to rotate the first deflection angle；

The camera shooting is controlled, iris image is obtained.

2. a kind of automatic focusing iris image acquiring method according to claim 1, which is characterized in that the carrier is also It is relatively set with backboard, the backboard is equipped with the posting of mark face location, is obtaining the first of the camera acquisition Before facial image, the method also includes:

It is mobile towards the backboard direction to control carrier described in the motor driven；

The camera is controlled towards the backboard direction.

3. a kind of automatic focusing iris image acquiring method according to claim 1, which is characterized in that described to described The step of first facial image is handled, and the first position of human eye of first facial image is obtained, comprising:

First facial image is subjected to diminution processing；

Target detection is carried out to first facial image, obtains the first human eye area in first facial image；

The first centre coordinate of first human eye area is obtained, and using first centre coordinate as the first position of human eye.

4. a kind of automatic focusing iris image acquiring method according to claim 3, which is characterized in that the acquisition institute The step of stating the first centre coordinate of the first human eye area, comprising:

Obtain corresponding the first all human eye coordinates of first human eye area, wherein first human eye coordinates are described Coordinate of first human eye area in first facial image；It averages, is obtained in first to the first all human eye coordinates Heart coordinate.

5. a kind of automatic focusing iris image acquiring method according to claim 1, which is characterized in that described first partially Gyration is calculated by following expression:

θ=(y₁-y₀) α, wherein θ is the first deflection angle, y₁It is the first position of human eye vertical in first facial image Coordinate, y₀For ordinate of first predeterminated position in first facial image, α is first angle.

6. a kind of automatic focusing iris image acquiring device, which is characterized in that be applied to controller, the controller and motor It is electrically connected with camera, the camera is set on carrier, and the motor is for driving the carrier mobile, described device Include:

Module is obtained, for obtaining the first facial image of the camera acquisition, when camera is shot the first facial image Angle between camera primary optical axis and horizontal plane is as first angle；

Processing module obtains the first human eye position of first facial image for handling first facial image It sets；According to the first angle, the first position of human eye and the first predeterminated position, the first deflection angle is calculated；Control the load Body drives camera to rotate the first deflection angle；

Shooting module obtains iris image for controlling the camera shooting.

7. a kind of automatic focusing iris image acquiring device according to claim 6, which is characterized in that the carrier is also It is relatively set with backboard, the backboard is equipped with the posting of mark face location, is obtaining the first of the camera acquisition Before facial image, the processing module is also used to:

It is mobile towards the backboard direction to control carrier described in the motor driven；

The camera is controlled towards the backboard direction.

8. a kind of automatic focusing iris image acquiring device according to claim 6, which is characterized in that the processing mould Block also particularly useful for:

First facial image is subjected to diminution processing；

Target detection is carried out to first facial image, obtains the first human eye area in first facial image；

The first centre coordinate of first human eye area is obtained, and using first centre coordinate as the first position of human eye.

9. a kind of automatic focusing iris image acquiring device according to claim 8, which is characterized in that the processing mould Block also particularly useful for:

Obtain corresponding the first all human eye coordinates of first human eye area, wherein first human eye coordinates are described Coordinate of first human eye area in first facial image；It averages, is obtained in first to the first all human eye coordinates Heart coordinate.

10. a kind of automatic focusing iris image acquiring device according to claim 6, which is characterized in that the processing Module also particularly useful for:

First deflection angle is calculated by following expression:

θ=(y₁-y₀) α, wherein θ is the first deflection angle, y₁It is the first position of human eye vertical in first facial image Coordinate, y₀For ordinate of first predeterminated position in first facial image, α is first angle.