CN101814129B - Automatically focused remote iris image acquisition device, method and recognition system - Google Patents

Abstract

The present invention relates to a long-distance iris image acquisition device, method and recognition system for automatic focusing. The device is composed of an iris camera, a long focal length lens, a focus transmission unit, a lens converter, a focus rotation motor, a motor drive unit and a calculation processing unit. . The autofocus method based on this device has the following steps: initializing the focusing device; the camera continuously collects iris images; the computing unit calculates the sharpness and sharpness changes of the collected images; and then determines the focusing speed and Direction; detect clear human eye images from image sequences for iris recognition. Based on the above focusing device and focusing method, the depth of field range and speed of long-distance iris image acquisition can be greatly increased. The long-distance iris recognition system applying the above-mentioned device and method is more convenient and easy to use.

Description

Autofocus remote iris image acquisition device, method and recognition system

technical field

The invention belongs to the technical fields of image processing, electromechanical control, computer vision and pattern recognition, and relates to an iris recognition and automatic focusing remote iris image acquisition device and method applied in the field of biological feature recognition.

Background technique

Among the current biometric identification technologies, iris recognition technology has the advantages of high accuracy, good uniqueness, strong anti-counterfeiting, and easy image processing, and has broad market application prospects. The steps of iris recognition generally include steps such as iris image acquisition, image preprocessing, iris location, liveness detection, feature extraction and feature matching. Among them, iris image acquisition is a very important link. If the iris acquisition is not done well, the image acquisition speed will be slowed down and the recognition rate will be greatly reduced.

It is very difficult to obtain iris images. The main reason is that the diameter of the iris is very small, and the resolution required for iris recognition is high, which makes the object-to-image ratio of the optical system very large, so the optical depth of field is very small, often only about a few centimeters. In this depth of field range, it is difficult for the user to align conveniently, which seriously affects the ease of use and recognition speed of iris recognition.

Fixed-focus lenses were used in the original iris image acquisition patented products. (Chinese patents CN1282048, CN1584917 etc.) the depth of field of the fixed-focus lens is very small, and can only be satisfied with some occasions where ease-of-use requirements are not high. In order to allow people to quickly align, some patented products use acousto-optic signals to give feedback to people, so that people can align according to the instructions of the machine, but this method still cannot fundamentally improve the ease of use of the iris collection device.

Some newer patented products use auto-zoom or auto-focus lenses to expand the depth of field. (Chinese patents: CN1892401, CN2672768, CN1894719, etc.) These are all very beneficial methods, but there are still several problems in the current focusing products: first, they all adopt short-distance focusing equipment, at a fixed distance and limited Second, in the focus system, when the focus position changes, it cannot quickly track the new focus position, and the adaptability is poor. The reason is that most of them do not design focusing devices specifically for iris images, but use devices and methods on digital cameras or surveillance cameras; and iris shooting is similar to microscopic imaging, which requires a large focus range and high precision, so these devices Not applicable is natural. An autofocus device suitable for long-distance iris recognition must be made.

Contents of the invention

(1) Technical problems to be solved

The purpose of the present invention is to design a long-distance iris image acquisition device, method and recognition system with automatic focus, so as to increase the depth of field range of long-distance iris image acquisition and improve the ease of use of iris recognition.

(2) Technical solutions

In order to achieve the above object, the present invention provides an automatic focusing remote iris image acquisition device. The device includes the following structure: an iris camera, a long focal length lens, a focus transmission unit, a lens converter, a focus rotating motor, a motor drive unit, and a calculation processing unit, wherein: the iris camera, the long focal length lens and the lens converter are located on the same axis, The focus transmission unit is connected coaxially with the focus rotation motor; the iris camera is connected with the long focal length lens through a lens converter; the focus transmission unit is connected with the focus ring on the long focal length lens; the focus rotation motor is electrically connected with the motor drive unit; the calculation processing unit and The signal connection of the motor drive unit controls the rotation of the focus rotation motor through the motor drive unit; the calculation processing unit is connected with the iris camera to process images from the iris camera.

In order to achieve the above object, the invention provides a method for acquiring an autofocus remote iris image, comprising the steps of:

Step P1: Initialize the device, rotate the focus ring, and make the focusing position of the focus ring reach the zero point, that is, limit switch 11;

Step P2: The iris camera continuously collects images to form an image sequence;

Step P3: the calculation processing unit calculates the sharpness and the change value of the sharpness of each frame image in the image sequence, and executes step P4 and step P5 respectively in two threads;

Step P4: According to the sharpness of the image and the sharpness change value, change the direction and speed of the focus ring rotation, and return to step P2; the transformation is based on the sharpness and the sharpness change value, and the remote iris image acquisition device for automatic focusing The current system state of the system is determined by the system state transition conditions of the remote iris image acquisition device for automatic focusing;

Step P5: Turn to the image selection thread, calculate the sharpness and sharpness change value of the image in the image sequence, and judge whether to select an image whose sharpness meets the requirements through the sharpness and sharpness change value of the image, if the selected image is clear , execute step P6, if the selected image is not clear, return to step P2;

Step P6: Carry out human eye detection and extract eye images from the selected clear images;

Step P7: Judge the quality of the eye image to determine whether it can be used for iris recognition. If it is judged that the eye image can be used for iris recognition, the iris recognition ends. If it is judged that the eye image cannot be used for iris recognition, continue to collect images and continue to execute Step P5.

In order to achieve the above object, the present invention provides a fully automatic long-distance iris recognition system based on the above device and method, including the following structures: a long-distance autofocus device, a long-distance infrared light source, a drive controller, a light source controller, an image An acquisition card, a computer, a panel and a cabinet, wherein: the focus rotation motor of the long-distance auto-focus device is electrically connected to the computer through a drive controller; the iris camera on the long-distance auto-focus device is connected to the computer through an image acquisition card; the iris camera The collected high-resolution images are transmitted to the Internet; the computer calculates the sharpness of the real-time images collected by the camera, and automatically rotates the long-distance auto-focus device according to the change of sharpness to search and track the focus position of the object; the long-distance infrared light source It is connected to the computer through the controller; the above equipment is installed in the cabinet, the long-distance auto-focus device and the long-distance infrared light source are installed facing the front, and the panel is placed in front of the cabinet.

(3) Beneficial effects

The invention integrates technologies such as image processing, electromechanical control, computer vision and pattern recognition, and is applied to the iris recognition direction in the field of biological feature recognition. The invention collects the iris image at a long distance through an automatic focusing method, improves the iris image collection range and collection speed, and improves the usability of iris recognition.

The solution adopted by the present invention is firstly to redesign the focusing device so that it can take iris images by focusing in a larger range and a farther distance. Second, design a better focus strategy, which can satisfy both wide-range focus search and high-precision focus, and can quickly track when the focus changes.

The focusing device adopts a delicate mechanical device, which can be applied to a variety of long focal length lenses; the focusing ring is driven by a stepping motor, the focusing range is large, and the rotation is stable and fast; the focusing strategy based on state transition is adopted, and the focusing device can be controlled Quickly search and track the focus position; use image processing technology to judge the clarity of the image and detect the human eye to obtain the iris image.

Description of drawings

Fig. 1 is a structural diagram of an autofocus device;

Fig. 2 is a schematic diagram of a focusing transmission device;

Fig. 3 is the flow chart of the method of automatic focusing;

FIG. 4 is a schematic diagram of a focus strategy using the focus ring 21;

Figure 5 is a schematic diagram of the change of definition with distance;

Fig. 6 is a schematic diagram of the change of the focus position when the object moves;

Figure 7 is the definition calculation process;

Fig. 8 is the schematic diagram of example device;

Fig. 9 is the flow chart of the running steps of the example system;

Description of main parts marking

Iris camera 1 Telephoto lens 2

Focus ring 21 Focus transmission unit 3

Lens converter 4 Focus rotation motor 5

Motor drive unit 6 Computing processing unit 7

Hollow ring 31 Fixture 32

Belt 33 Limit switch 34

Long distance auto focus device D1 Long distance infrared light source D2

Stepping motor drive controller D3 Light source controller D4

Image acquisition card D5 Host D6

Panel D7 Cabinet D8

Detailed ways

Various details involved in the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be pointed out that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.

(1) Long-distance iris image acquisition device with automatic focus

The structural design of the present invention is as shown in Figure 1, and is made up of following and part: iris camera 1, telephoto lens 2, focusing transmission unit 3, lens converter 4, focusing rotating motor 5, motor drive unit 6, computing processing unit 7.

Iris camera 1 and lens 2 are connected by lens converter 4; Focus transmission unit 3 and focus ring 21 on lens 2 and focus rotation motor 5 are connected; Focus rotation motor 5 is electrically connected with motor drive unit 6; Calculation processing unit 7 and The motor drive unit 6 is connected to the signal, and the rotation of the focus rotation motor 5 can be controlled by the motor drive unit 6; the calculation processing unit 7 is connected to the iris camera 1 to process images from the camera 1.

The focal length of the telephoto lens 2 is any value between 100mm and 500mm. The telephoto lens 2 can be connected with the iris camera 1 through a lens converter 4 .

Wherein, the structure diagram of the focusing transmission unit 3 is shown in FIG. 2 . A hollow ring 31 and a clamp 32 are arranged on the focusing transmission unit 3, and a clamp 32 is installed between the hollow ring 31 and the focus ring 21, and a clamp 32 has elastic three claws for clamping the Lens 2 and focus ring 21 of different sizes in a hollow ring 31; the focus transmission unit 3 also has a belt 33 and a limit switch 34, and the belt 33 is fastened to the hollow ring 31 and the focus rotating motor 5, so that when the focus rotation motor 5 rotates, it will also drive the hollow ring 31 to rotate, thereby driving the focus ring 21 to focus the lens 2; the limit switch 34 will be turned when the focus ring 21 rotates to a position Run into, limit switch 34 sends a signal and can make stepper motor 5 stop rotating, and so just makes focusing transmission unit 3 have an initial position.

(2) Auto-focus remote iris image acquisition method

Based on the above autofocus remote iris image acquisition device, the flow chart of the autofocus method we adopt is shown in Figure 3: the method has two threads, the first thread is used for focusing, and the second thread is used for image selection. The focusing of the first thread consists of the following steps:

Step P1: Initialize the device, rotate the focus ring so that the focus position of the focus ring 21 is zero, that is, the limit switch 11;

Step P2: The iris camera 1 continuously collects images to form an image sequence;

Step P3: The calculation processing unit 7 calculates the sharpness and the change value of the sharpness of each frame image in the image sequence collected by the iris camera 1, and performs step P4 and step P5 respectively;

Step P4: Transform the direction and speed of the focus ring rotation according to the sharpness and the sharpness change value of the image, and return to step P2; State transition conditions are determined. The state of the long-distance iris image acquisition device for automatic focusing is divided into four types, static state, wide range search state, small range search state and focus state.

Step P5: Turn to the image selection thread, select images with sharpness and sharpness change value, and continuously judge whether to select an image whose sharpness meets the requirements from the image sequence, if the selected image is clear, execute step P6, if The selected image is not clear, return to step P2;

Step P6: Carry out human eye detection and extract eye images from the selected clear images;

Step P7: Judge the quality of the eye image to determine whether it can be used for iris recognition. If it is judged that the eye image can be used for iris recognition, the iris recognition ends. If it is judged that the eye image cannot be used for iris recognition, continue to collect images and continue to execute Step P5.

(1) Calculate image sharpness

In the above method flow, the method for calculating the image sharpness is as follows:

Step P31: Randomly extract 100 small image blocks of 20*20 from the collected image;

Step P32: Calculate the edge energy of the image for each image small block. The method of calculating the edge energy is: find the square sum of the gradient values in the two directions of the image small block X and Y, and take the edge of all points of the image small block The energy is added to get the edge energy;

Step P33: adding up the edge energy values of 100 small image blocks, and normalizing to a value between 0 and 1, the value being the change value of image clarity.

FIG. 5 is a schematic diagram of sharpness changing with focusing distance. When the object is fixed, the sharpest point is at the focal point. With the distance away from the focal point, the sharpness gradually decreases, and the sharpness peak is very sharp, which can be used to judge whether there is a focal point in the sequence. Among them, the X-axis is the distance, the Y-axis is the sharpness, Q is the change curve, P is the focus position, and D is the identifiable depth of field range.

FIG. 6 is a schematic diagram of changes in the focus position of the telephoto lens 2 of the iris camera 1 when the object changes (ie, when a person moves). When the person moves from position A to B, the sharpness value of different focus distances of iris camera 1 also changes from curve QA to curve QB, and the focus position changes from PA to PB. This device can realize that when a person moves, the device can quickly track from the original focus position PA to the new focus position PB.

(2) Focusing strategy based on state transition

In the above-mentioned method flow, according to the sharpness of the image and the sharpness change value, the current system state of the long-distance iris image acquisition device that changes the rotation direction and speed of the focus ring 21 and autofocus is determined by the defined system state transition conditions Decide. The system states are defined as static state S1, wide range search state S2, small range search state S3 and focus state S4. The conversion conditions between them are: C11, C12, C23, C34, C44, C43, C32, C21. The system state and state transition conditions are shown in the focus strategy schematic diagram in Figure 4, where:

Static state S1: the focus ring 21 is at the leading position, and is still. If the state transition condition C11 is satisfied (i.e., the sharpness is lower than a threshold T1), then it is considered that no object enters the field of view of the iris camera, and the focus ring 21 is not rotated. At this time, the focus ring 21 is still in a static state; if the state transition condition C12 is satisfied ( That is, if the definition is higher than the threshold T1), it is considered that there is an object entering the field of view, and the system enters a large-scale search state.

The wide-range search state S2 is: rotate the focus ring 21 to rotate quickly within the search range from 0 to the maximum number of steps: every time a certain number of steps is rotated, one frame of image is collected, and the value of sharpness is calculated, and the current position is recorded. If the state transition condition C23 is met (that is, when the sharpness value is greater than a threshold T2, or when the sharpness value has an obvious peak value), it is considered to be close to the focus position, and enters the small-scale search S3; if the state transition condition C21 is satisfied (that is, if no focus position), then return to zero position S1.

The small-range search state S3 is: near the focus position, the focus ring 21 rotates in small steps within the range near the focus: every time a certain angle is rotated, a frame of image is collected, and the value of the sharpness is calculated, and the current step is recorded Location. If the state transition condition C34 is satisfied (that is, when the sharpness value is greater than a threshold T3, or when the sharpness value has an obvious peak value), it is considered that the focus position has been reached, the peak value is recorded, and the focus mode is entered; if the state transition condition C32 is satisfied (that is, if If the focus position is not found), then continue to search S2 in a large area.

Focus mode S4: the focus ring 21 stops at the focus position, and calculates successive sharpness change values at regular intervals. If the state transition condition C43 is satisfied (that is, when the sharpness changes greatly, or the sharpness is less than half of the initial focus peak value), it is considered that the focus has changed, and a new focus of S3 is searched in a small range; otherwise, if the state transition is satisfied Condition C44 (that is, when the sharpness change is not less than half of the initial focus peak value), pause for a period of time, continue to calculate the sharpness change value, and the state remains unchanged.

The thresholds T1, T2 and T3 are obtained through experiments. During the experiment, a number of images (over 500) were collected by the camera; the images were manually divided into four categories: no object, object but blurred image, clearer image, and extremely clear image; and then calculate the value of the sharpness of each image ; The sharpness values of the four types of images are normally distributed respectively, and the boundary values T1, T2 and T3 between the three types are determined by Bayesian method, which are the above-mentioned thresholds.

(3) Image selection method

In the above-mentioned method flow, a clear image is selected for iris recognition while focusing, and the specific method of step P5 is:

Step P51: every time 10 frames of images are collected, one frame of images with the highest definition is selected from the 10 frames of images;

Step P52: If the sharpness of the image is less than a threshold T3, no processing is performed;

Step P53: If the sharpness of the image is greater than or equal to the threshold T3, continue processing the image.

Wherein, the concrete method of step P6 eye detection is:

First, a machine learning algorithm (Adaboostting) is used to train and generate a cascaded classifier based on Haar wavelet (Haar) features. During the system operation of the auto-focused remote iris image acquisition device, the acquired high-resolution images are down-sampled and feature cascade classifiers are used for eye detection at different scales. If the eye is not detected, no processing is performed; if the eye is detected, the image of the eye part at the original resolution is sampled on the collected high-resolution image, and the processing continues.

(4) Iris image quality judgment

The above-mentioned clear image may not be capable of iris recognition, so the present invention needs to judge the image quality of the eye image again, as shown in Figure 7, the method of step P7 is:

Step P71: Calculate the high-frequency component E1 of the original human eye image; the high-frequency component E1 is obtained by the following method: generate an 8*8 operator, the 4*4 points in the center of the operator are -3, and the other values are +1; use this 8*8 operator to filter on the image; then the sum obtained by adding all the filtered image points is defined as E1;

Step P72: Downsampling the human eye image is to reduce the eye image by one time;

Step P73: Calculate the high-frequency component E2 of the down-sampled human eye image, and the calculation method for obtaining E2 is the same as step P71;

Step P74: Calculate the ratio R of the energy E1 of the high frequency band and the energy E2 of the lower frequency band;

Step P75: Combining the high-frequency band energy E1, the definition value C of the iris image quality is obtained as: C=αE1+βR, α, β are weighted operators, obtained from experience;

If the obtained sharpness value C is less than a threshold T4, the iris image is not processed; otherwise, preprocessing, iris location, feature extraction and feature comparison are performed on the iris image.

Application Example: Fully Automatic Remote Iris Recognition System

According to the above-mentioned focusing device and focusing method, a set of iris collection example system is formed, as shown in Figure 8, wherein, the fully automatic long-distance iris recognition system is composed of the following parts: long-distance auto-focusing device D1, long-distance infrared light source D2, drive controller D3, light source controller D4, image acquisition card D5, computer D6, panel D7 and cabinet D8, the connection method is: the stepper motor of the remote autofocus device D1 is electrically connected to the computer through the drive controller D3 On D6; the iris camera 1 on the long-distance auto-focus device D1 is connected to the computer D6 by the image acquisition card D5, and the wide-angle camera 7 of the distance auto-focus device D1 is connected to the computer D6 by a USB cable; the long-distance infrared light source D2 is passed The controller D4 is connected to the computer D6; the above devices are all installed in the cabinet D8, and the long-distance auto-focus device D1 and the long-distance infrared light source D2 are installed facing the front. For the sake of aesthetics, a panel D7 is placed in front of the cabinet D8, and the panel D7 can be an acrylic plate with a cavity, or glass that transmits infrared light and reflects visible light.

Fig. 9 shows the example of the fully automatic long-distance iris recognition system shown in Fig. 8, and this recognition system operation has the following steps:

Step F1: aim the iris camera 1 in the long-distance auto-focus device D1 at the face area of the person, and start the iris camera 1 to collect high-resolution images;

Step F2: The computer calculates the sharpness of the real-time image collected by the camera 1, and automatically rotates the long-distance auto-focus device D1 according to the change of the sharpness to search and track the focus position of the object;

Step F3: iris camera 1 selects the clearest image in the image sequence, detects the human eye image, and extracts the image of the human eye;

Step F4: human eye image quality judgment, selecting the clearest image in the human eye image sequence for iris recognition.

In this example, since the automatic long-distance iris recognition system of the present invention adopts a distance auto-focus device, the effective recognition range of the automatic long-distance iris recognition system is greatly improved. When a person walks to a range of about 2.5 to 3.2 meters in front of the cabinet and stands still, the recognition system will automatically adjust the position of the camera D1 according to the person's height, and at the same time automatically focus on the person's iris.

When using the fully automatic long-distance iris recognition system of the present invention, the user can feel comfortable and natural, and does not need to worry that the recognition cannot be completed due to a wrong position. On the other hand, for users who use the fully automatic long-distance iris recognition system for the first time, they will not be unable to complete it because they have no experience.

The above is only a specific implementation mode in the present invention, but the scope of protection of the present invention is not limited thereto. Anyone familiar with the technology can understand the conceivable transformation or replacement within the technical scope disclosed in the present invention. All should be covered within the scope of the present invention, therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (7)

1. a remote iris image acquisition device of automatically focusing, is characterized in that, comprising: iris camera, long focal length lens, focusing gear unit, lens converter, focusing electric rotating machine, electric-motor drive unit, calculation processing unit, wherein:

Iris camera, long focal length lens and lens converter are positioned on same axis, the focusing gear unit with focus that electric rotating machine is coaxial to be connected; The iris camera connects by lens converter with long focal length lens; The focusing ring that the focusing gear unit is connected with long focal length lens connects; Focusing electric rotating machine and electric-motor drive unit electrical connection; Calculation processing unit is connected with the electric-motor drive unit signal, controls the rotation of focusing electric rotating machine by electric-motor drive unit; Calculation processing unit is connected with the iris camera, processing is from the image of iris camera, described focusing gear unit contains cavity ring, jig, belt and limit switch, jig is being installed on cavity ring and between focusing ring, jig has the elasticity three-jaw, is used for blocking camera lens and the focusing ring of different sizes in described cavity ring; The be locked rotating shaft of cavity ring and the focusing electric rotating machine that is locked of described belt be used for to drive the cavity ring rotation, thereby drive focusing ring, camera lens is focused; Be connected with limit switch when focusing ring rotates to a position, limit switch sends a signal stops operating the focusing electric rotating machine, makes the focusing gear unit have an initial position.

2. the remote iris image acquisition device of automatically focusing as claimed in claim 1 is characterized in that the focal length value of long focal length lens is that 100mm is to the arbitrary value between 500mm.

3. a distant range iris image acquiring method of automatically focusing, is characterized in that, the step of obtaining the distant range iris image with the remote iris image acquisition device of automatically focusing is as follows:

Step P1: initialization apparatus, the rotation focusing ring makes the focusing ring focusing position to zero point, i.e. the limit switch place;

Step P2: the iris camera constantly gathers image, forms image sequence;

Step P3: the sharpness of every two field picture in the calculation processing unit sequence of computed images, then calculate the changing value of sharpness, execution in step P4 and step P5 respectively in two threads;

Step P4: according to sharpness and the sharpness changing value of image, direction and the speed of the rotation of conversion focusing ring are returned to step P2; Described conversion is according to sharpness and sharpness changing value, and the automatic current system state of the remote iris image acquisition device of focusing, is decided by the system state switch condition of the remote iris image acquisition device of automatic focusing;

Step P5: change image over to and select thread, the sharpness of image in sequence of computed images, calculate again the sharpness changing value, and judge whether to pick out by sharpness and the sharpness changing value of image the image that sharpness meets the demands, if the clear picture of selecting, execution in step P6, if select not fogging clear, get back to step P2;

Step P6: carry out human eye detection and extract eye image from the picture rich in detail of picking out;

Step P7: eye image is carried out the quality judgement, judge whether to be used for iris recognition, if the judgement eye image can be used in iris recognition, iris recognition finishes, if the judgement eye image can not be used for iris recognition, continue to gather image, continue execution in step P5;

The step that described image definition is calculated is as follows:

Step P31: the image fritter of randomly drawing 100 20*20 on the image that gathers;

Step P32: to the edge energy of each image fritter computed image, the edge calculation energy approach is: asks at image fritter X, and the quadratic sum of the Grad of Y both direction, and the edge energy addition of having a few of image fritter, obtain edge energy;

Step P33: the edge energy value addition of 100 image fritters, and normalize to a numerical value between 0～1, described numerical value is the changing value of image definition;

The described step that the eye image quality is judged is as follows:

Step P71: the high band component E1 that calculates original eye image; High fdrequency component E1 obtains by the following method: generate the operator of a 8*8,4*4 the point value at operator center is-3, and other value is+1; Operator with this 8*8 carries out filtering on image; Then that filtered all picture point additions are obtained and be defined as E1;

Step P72: down-sampled eye image is that eye image is dwindled one times;

Step P73: the high band component E2 that calculates down-sampled image; Obtain the method for high band component E2 with step P71;

Step P74: ask for the ENERGY E 1 of high band and than the ratio R of the ENERGY E 2 of low-frequency range,

Step P75: in conjunction with high band ENERGY E 1, the definition values C that obtains iris image quality is: C=α E1+ β R, and α, β are that weighted operator is drawn by experience;

If the definition values C that obtains does not process iris image less than a threshold value T4; Otherwise iris image is carried out pre-service, Iris Location, feature extraction and aspect ratio pair.

4. the distant range iris image acquiring method of automatically focusing as claimed in claim 3 is characterized in that, the switch condition of the system state of the remote iris image acquisition device of described automatic focusing and focusing strategy are as described below:

Sharpness and sharpness changing value according to image, the current system state of the remote iris image acquisition device of the direction of conversion focusing ring rotation and speed and automatic focusing, decided by the system state switch condition, system state is defined by system software, the system state of remote iris image acquisition device of focusing automatically is divided into stationary state, extensive search state, search condition and focus condition among a small circle, the switch condition between them is:

C11，C12，C23，C34，C44，C43，C32，C21；

The switch condition of described system state and focusing strategy are as described below:

Stationary state: focusing ring is in null position, and transfixion is if satisfy state transition condition C11, described state transition condition C11 is that sharpness is lower than a threshold value T1, thinking does not have object to enter the visual field of iris camera, does not rotate focusing ring, and this moment, focusing ring still remained static; If satisfy state transition condition C12, described state transition condition C12 be sharpness higher than threshold value T1, thinking has object to come into view, system enters the extensive search state;

The extensive search state is: the rotation focusing ring from 0 in the hunting zone of maximum step number quick rotation: the certain step number of every rotation gathers a two field picture, and calculates the value of sharpness, and records current location; If satisfy state transition condition C23, described state transition condition C23 be when definition values greater than a threshold value T2, or definition values is when obvious peak value occurring, thinks to enter search among a small circle near the focal position; If satisfy state transition condition C21 for not finding the focal position, get back to null position;

Search condition is among a small circle: near the focal position, rotate so that small step is long near the scope of focusing ring focus: often rotate to an angle, gather a two field picture, and calculate the value of sharpness, and record current step-length position; If satisfy state transition condition C34, greater than a threshold value T3, or definition values thinks to arrive the focal position when obvious peak value occurring, records this peak value, enters focus mode when described state transition condition C34 definition values; If satisfy state transition condition C32 for not finding the focal position, proceed extensive search;

Focus mode: focusing ring stops at the focal position, calculate at set intervals sharpness changing value successively, if satisfy state transition condition C43, described state transition condition C43 is when the half of sharpness less than initial focus peak value, think that variation has occured focus, the new focus of search among a small circle; Otherwise if satisfy state transition condition C44, described state transition condition C44 is that sharpness changes a half that is not less than initial focus peak value, suspends a period of time, continues to calculate the sharpness changing value, and state is constant.

5. the distant range iris image acquiring method of automatically focusing as claimed in claim 3 is characterized in that, the concrete steps that described image is selected are as follows:

Step P51: every collection 10 two field pictures, choose 1 two field picture of sharpness maximum from 10 two field pictures;

Step P52: if the sharpness of image is not processed less than a threshold value T3;

Step P53: if the sharpness of image more than or equal to threshold value T3, continues to process to this image.

6. the distant range iris image acquiring method of automatically focusing as claimed in claim 5 is characterized in that, the step of described extraction eye image is as follows:

Utilization is generated based on Ha Er wavelet character cascade sorter by the machine learning algorithm training; Down-sampled high-resolution image, and utilize above-mentioned sorter to carry out eye detection; If eyes do not detected, do not process; If eyes detected, go out the image of the eyes part under original resolution at the high-definition picture up-sampling that collects, proceed to process.

7. a right to use requires the full automatic distant range iris recognition system of the distant range iris image acquiring method of 3 or 4 described automatic focusings, comprise far distance automatic focusing mechanism, remote infrared light supply, driving governor, light source controller, image pick-up card, computing machine, panel and rack, wherein:

The focusing electric rotating machine of far distance automatic focusing mechanism is electrically connected on computing machine by driving governor; Iris camera on far distance automatic focusing mechanism is connected on computing machine by image pick-up card; The high-definition picture of iris camera collection passes on computing machine by image pick-up card; By computing machine calculate camera collection to the sharpness of realtime graphic, and according to switch condition and the focusing strategy of the system state of the remote iris image acquisition device of automatic focusing, the far distance automatic focusing mechanism of automatic rotating, the focal position of realizing search and tracking object; Remote infrared light supply is connected on computing machine by light source controller; Above equipment all is installed in rack, and far distance automatic focusing mechanism and remote infrared light supply are all installed towards the front, rack front plate placement.

Images