CN113709353B

CN113709353B - Image acquisition method and device

Info

Publication number: CN113709353B
Application number: CN202010431688.4A
Authority: CN
Inventors: 潘之玮; 连颖
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2020-05-20
Filing date: 2020-05-20
Publication date: 2023-03-24
Anticipated expiration: 2040-05-20
Also published as: CN113709353A

Abstract

The disclosure provides an image acquisition method and equipment, and relates to the technical field of data acquisition. Acquiring the image quality of a target image, wherein the target image is an image obtained by image acquisition of a current scene through image acquisition equipment; if the image quality of the target image does not meet the quality requirement, focusing the image acquisition equipment according to the image quality of the target image; and acquiring a first iris image of the target object through the focused image acquisition equipment. By the method, the focusing adjustment information can be determined according to the collected target image, focusing is performed according to the focusing adjustment information, the first iris image is obtained through the adjusted focusing information, the definition of the obtained first iris image is improved, and the accuracy of first iris image identification is improved.

Description

Image acquisition method and device

Technical Field

The present disclosure relates to the field of data acquisition technologies, and in particular, to an image acquisition method and device.

Background

The iris identification technology is a technology for carrying out identity authentication by utilizing intrinsic texture information in an iris area of a human eye, is a biological characteristic identification technology with higher accuracy and anti-counterfeiting capability, and is applied to the fields of access control and attendance checking, security inspection and clearance, mobile payment and the like. With the development of data acquisition technology, the constraint conditions for data acquisition are gradually relaxed, and the constraint conditions for iris image acquisition are also gradually relaxed. Iris image acquisition gradually develops from short-distance acquisition to long-distance acquisition, and from common posture fixed acquisition to posture non-fixed acquisition and the like. However, the accuracy of extracting the iris information from the iris image acquired by a long distance or non-fixed posture acquisition is low, which results in inaccurate iris recognition.

Disclosure of Invention

The present disclosure provides an image acquisition method and apparatus that improve the sharpness of an acquired iris image, thereby improving the accuracy of first iris image recognition.

In one aspect, an image acquisition method is provided, and the method includes:

acquiring the image quality of a target image, wherein the target image is obtained by image acquisition of a current scene through image acquisition equipment;

if the image quality of the target image does not meet the quality requirement, focusing the image acquisition equipment according to the image quality of the target image;

and acquiring a first iris image of the target object through the focused image acquisition equipment.

In a possible implementation manner, the performing a focusing process on the image capturing device according to the image quality of the target image includes:

determining focusing adjustment information of the image acquisition equipment according to the image quality of the target image;

and focusing the image acquisition equipment according to the focusing adjustment information.

In another possible implementation manner, the image quality of the target image includes position information of a target object in the target image and the definition of the target image;

the determining the focusing adjustment information of the image acquisition equipment according to the image quality of the target image comprises the following steps:

inputting the position information of a target object in the target image and the definition of the target image into a first image quality determination model to obtain the focusing direction and degree of the image acquisition equipment;

and taking the focusing direction and degree of the image acquisition equipment as focusing adjustment information of the image acquisition equipment.

In another possible implementation manner, before the inputting the position information of the target object in the target image and the definition of the target image into the first image quality determination model and obtaining the direction and the degree of focusing of the image capturing device, the method further includes:

acquiring the image quality of at least one frame of first sample image acquired by the image acquisition equipment;

determining a first preset focusing adjustment information according to the image quality of the at least one frame of the first sample image and the second image quality determination model;

focusing the image acquisition equipment according to the first preset focusing adjustment information;

collecting at least one frame of second sample image according to the focused image collecting equipment;

determining a return value of the first preset focusing adjustment information according to the image quality of the second sample image and the preset image quality;

and adjusting the model parameters of the second image quality determination model according to the return value to obtain the first image quality determination model.

In another possible implementation manner, the adjusting, according to the return value, a model parameter of the second image quality determination model to obtain the first image quality determination model includes:

determining a return value of a second image quality determination model after each model parameter adjustment; summing each return value, and if the sum of the return values is larger than a preset threshold value, determining that a second image quality determination model is trained to finish one-time reinforcement learning until the first image quality determination model is obtained; alternatively, the first and second electrodes may be,

determining second preset focusing adjustment information according to the second image quality determination model after the parameters are adjusted; focusing the image acquisition equipment according to the second preset focusing adjustment information; and acquiring the image quality of at least one frame of second sample image according to the focused image acquisition equipment, and determining a second image quality determination model to finish one-time reinforcement learning if the image quality of the at least one frame of second sample image meets the quality requirement until the first image quality determination model is obtained.

In another possible implementation manner, before the obtaining of the image quality of the target image, the method further includes:

acquiring images of the faces of the target objects in the current scene through the image acquisition equipment to obtain a first face image;

taking the first face image as the target image; or, a second iris image corresponding to the iris image of the target object is cut from the first face image, and the second iris image is taken as the target image.

In another possible implementation manner, the acquiring, by the image acquisition device after focusing, a first iris image of a target object includes:

acquiring an image of the face of the target object in the current scene by the focused image acquisition equipment to obtain a second face image; intercepting a first iris image corresponding to the iris of the target object from the second face image; alternatively, the first and second liquid crystal display panels may be,

and acquiring an image of the iris of the target object by the focused image acquisition equipment to obtain the first iris image.

In another possible implementation manner, before the acquiring the target image, the method further includes:

acquiring a current scene image;

determining a current imaging distance according to the current scene image;

according to the imaging distance, determining a variable magnification value corresponding to the imaging distance from a mapping relation between the imaging distance and a variable magnification value of the image acquisition equipment;

determining a second focal length corresponding to the imaging distance according to a first focal length and the zoom value, wherein the first focal length is the current focal length of the image acquisition equipment;

and zooming the image acquisition equipment according to the second focal length.

In another possible implementation manner, before determining, according to the first focal length and the zoom value, a second focal length corresponding to the imaging distance, the method further includes:

initializing the image acquisition equipment, and determining the picture proportion of a target object in an imaging picture of the image acquisition equipment;

and determining the mapping relation between the imaging distance and the zoom value of the camera according to the camera parameter initialized by the image acquisition equipment and the picture proportion.

In another possible implementation manner, the acquiring image quality of the target image includes:

and inputting the target image into a first image quality determination model to obtain the image quality of the target image.

In another possible implementation manner, before the target image is input into the first image quality determination model and the image quality of the target image is obtained, the method further includes:

acquiring a plurality of sample images and determining a plurality of image quality classes;

for any sample image, performing feature extraction on the sample image to obtain image features corresponding to the sample image;

determining the probability of any image quality category of the sample image according to a second image quality determination model and the image characteristics;

determining a cross entropy error of a second image quality determination model according to the probability that the sample image is of any image quality category and the probability of the sample image;

and adjusting the model parameters of the second image quality determination model according to the cross entropy error until the cross entropy error is smaller than a preset threshold value, so as to obtain the image quality determination model.

In another possible implementation manner, after the acquiring, by the focused image acquisition device, the first iris image of the target object, the method further includes:

performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the first iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; determining the identity information of the target object according to the iris recognition result; alternatively, the first and second electrodes may be,

determining an image quality of the first iris image; if the image quality of the first iris image is larger than a preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the second iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

In another aspect, an image capture apparatus is provided, the apparatus comprising: the device comprises a camera, a focusing driving module and a calculation processing module;

the camera is respectively connected with the focusing driving module and the computing processing module, and the focusing driving module is connected with the computing processing module;

the camera is used for collecting images of a current scene to obtain a target image and sending the collected target image to the calculation processing module;

the calculation processing module is used for receiving the target image, determining the image quality of the target image, determining the focusing adjustment information of the camera according to the image quality of the target image if the image quality of the target image does not meet the quality requirement, and sending the focusing adjustment information to the focusing driving module;

the focusing driving module is used for receiving focusing adjustment information sent by the calculation processing module and carrying out focusing processing on the camera according to the focusing adjustment information;

the camera is further used for acquiring a first iris image of the target object after focusing is completed.

In one possible implementation, the focus driving module includes: a focusing rotation unit, a focusing rotation motor and a motor driving unit;

the focusing rotating unit is respectively connected with the camera and the focusing rotating motor, and the motor driving unit is respectively connected with the focusing rotating motor and the calculation processing module;

the motor driving unit is used for receiving focusing adjustment information sent by the computer processing module and driving the focusing rotating motor according to the focusing adjustment information;

the focusing rotating motor is used for rotating the focusing rotating unit under the driving of the motor driving unit;

the focusing rotation unit is used for carrying out rotation focusing.

In another possible implementation manner, the image acquisition device further comprises a distance sensor, and the camera is a zoom camera;

the distance sensor is connected with the zoom camera;

the distance sensor is used for detecting the imaging distance between a target object in the current scene and the zoom camera, and sending an image acquisition instruction to the zoom camera if the imaging distance between the target object in the current scene and the zoom camera is detected to be within a preset distance;

the zoom camera is used for receiving an image acquisition instruction sent by the distance sensor, the image acquisition instruction carries the imaging distance, the focal length of the zoom camera is adjusted to a second focal length from a first focal length according to the imaging distance, the first focal length is the current focal length of the zoom camera, the second focal length is the focal length of the zoom camera after the adjustment of the imaging distance, image acquisition is carried out according to the second focal length, a current scene image is obtained, and the acquired current scene image is sent to the calculation processing module.

In another aspect, an image capturing apparatus is provided, the apparatus comprising:

the first acquisition module is used for acquiring the image quality of a target image, wherein the target image is obtained by acquiring an image of a current scene through image acquisition equipment;

the first focusing module is used for focusing the image acquisition equipment according to the image quality of the target image if the image quality of the target image does not meet the quality requirement;

and the second acquisition module is used for acquiring a first iris image of the target object through the focused image acquisition equipment.

In a possible implementation manner, the first focus module is further configured to determine focus adjustment information of the image acquisition device according to the image quality of the target image; and focusing the image acquisition equipment according to the focusing adjustment information.

the first focusing module is further used for inputting the position information of the target object in the target image and the definition of the target image into a first image quality determination model to obtain the focusing direction and degree of the image acquisition equipment; and taking the focusing direction and degree of the image acquisition equipment as focusing adjustment information of the image acquisition equipment.

In another possible implementation manner, the apparatus further includes:

the third acquisition module is used for acquiring the image quality of at least one frame of first sample image acquired by the image acquisition equipment;

the first determining module is used for determining a model according to the image quality of the at least one frame of the first sample image and the second image quality and determining first preset focusing adjustment information;

the second focusing module is used for focusing the image acquisition equipment according to the first preset focusing adjustment information;

the first acquisition module is used for acquiring at least one frame of second sample image according to the focused image acquisition equipment;

a second determining module, configured to determine a reported value of the first preset focusing adjustment information according to an image quality of the second sample image and a preset image quality;

and the first adjusting module is used for adjusting the model parameters of the second image quality determination model according to the return value to obtain the first image quality determination model.

In another possible implementation manner, the first adjusting module is further configured to determine a return value of the second image quality determination model after each adjustment of the model parameter; summing each return value, and if the sum of the return values is larger than a preset threshold value, determining that a second image quality determination model is trained to finish one-time reinforcement learning until the first image quality determination model is obtained; alternatively, the first and second electrodes may be,

the first adjusting module is further used for determining second preset focusing adjusting information according to the second image quality determining model after the parameters are adjusted; focusing the image acquisition equipment according to the second preset focusing adjustment information; and acquiring the image quality of at least one frame of second sample image according to the focused image acquisition equipment, and determining a second image quality determination model to finish one-time reinforcement learning if the image quality of the at least one frame of second sample image meets the quality requirement until the first image quality determination model is obtained.

In another possible implementation manner, the apparatus further includes:

the second acquisition module is used for acquiring the face of the target object in the current scene through the image acquisition equipment to obtain a first face image;

the first acquisition module is further used for taking the first face image as the target image; or, a second iris image corresponding to the iris image of the target object is cut out from the first face image, and the second iris image is taken as the target image.

In another possible implementation manner, the second obtaining module is further configured to perform image acquisition on a face of a target object in a current scene through the focused image acquisition device to obtain a second face image; intercepting a first iris image corresponding to the iris of the target object from the second face image; alternatively, the first and second electrodes may be,

the second acquisition module is further configured to perform image acquisition on the iris of the target object through the focused image acquisition device to obtain the first iris image.

In another possible implementation manner, the apparatus further includes:

the third acquisition module is used for acquiring a current scene image;

a third determining module, configured to determine a current imaging distance according to the current scene image;

the fourth determining module determines a zoom value corresponding to the imaging distance from a mapping relation between the imaging distance and the zoom value of the image acquisition equipment according to the imaging distance;

a fifth determining module, configured to determine, according to a first focal length and the zoom value, a second focal length corresponding to the imaging distance, where the first focal length is a current focal length of the image acquisition device;

and the zooming module is used for zooming the image acquisition equipment according to the second focal length.

In another possible implementation manner, the apparatus further includes:

the sixth determining module is used for initializing the image acquisition equipment and determining the picture proportion of a target object in an imaging picture of the image acquisition equipment;

and the seventh determining module is used for determining the mapping relation between the imaging distance and the zoom value of the camera according to the camera parameter initialized by the image acquisition equipment and the picture proportion.

In another possible implementation manner, the first obtaining module is further configured to input the target image into an image quality determination model, so as to obtain the image quality of the target image.

In another possible implementation manner, the apparatus further includes:

the fourth acquisition module is used for acquiring a plurality of sample images and determining a plurality of image quality categories;

the first extraction module is used for extracting the characteristics of any sample image to obtain the image characteristics corresponding to the sample image;

the eighth determining module is used for determining the probability of any image quality category of the sample image according to the second image quality determining model and the image characteristics;

a ninth determining module, configured to determine a cross entropy error of the second image quality determination model according to the probability that the sample image is of any image quality category and the probability of the sample image;

and the second adjusting module is used for adjusting the model parameters of the second image quality determination model according to the cross entropy error until the cross entropy error is smaller than a preset threshold value, so that the image quality determination model is obtained.

In another possible implementation manner, the apparatus further includes:

the second extraction module is used for extracting iris characteristics of the first iris image to obtain the iris characteristics of the target object in the first iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; determining the identity information of the target object according to the iris recognition result; alternatively, the first and second electrodes may be,

the second extraction module is further used for determining the image quality of the first iris image; if the image quality of the first iris image is larger than a preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the second iris image; performing feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

In another aspect, an image capturing apparatus is provided, which includes a processor and a memory, where at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the image capturing method according to the embodiment of the present disclosure.

In another aspect, a computer-readable storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the image capturing method according to the embodiment of the present disclosure.

In another aspect, a computer program product is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the image capturing method in the implementation of the present disclosure.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

in the embodiment of the disclosure, by obtaining the image quality of a target image, the target image is an image obtained by image acquisition of a current scene by an image acquisition device; if the image quality of the target image does not meet the quality requirement, focusing the image acquisition equipment according to the image quality of the target image; and acquiring a first iris image of the target object through the focused image acquisition equipment. By the method, the focusing adjustment information can be determined according to the acquired target image, focusing is performed according to the focusing adjustment information, and the first iris image is acquired through the adjusted focusing information, so that the definition of the acquired first iris image is improved, and the accuracy of first iris image identification is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a block diagram of an image acquisition device according to an exemplary embodiment;

FIG. 2 is a flow diagram illustrating an image acquisition method according to an exemplary embodiment;

FIG. 3 is a flow diagram illustrating an image acquisition method according to an exemplary embodiment;

FIG. 4 is a flow diagram illustrating an image acquisition method according to an exemplary embodiment;

FIG. 5 is a flow diagram illustrating an image acquisition method according to an exemplary embodiment;

FIG. 6 is a block diagram illustrating an image acquisition device according to an exemplary embodiment;

fig. 7 is a schematic structural diagram of an image capturing device according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Fig. 1 is an image pickup apparatus shown according to an exemplary embodiment, as shown in fig. 1, the image pickup apparatus including: the device comprises a camera, a focusing driving module and a calculation processing module; the camera is respectively connected with the focusing driving module and the computing processing module, and the focusing driving module is connected with the computing processing module. The camera is used for collecting images of the current scene to obtain a target image, and sending the collected target image to the calculation processing module. The calculation processing module is used for receiving the target image, determining the image quality of the target image, determining the focusing adjustment information of the camera according to the image quality of the target image if the image quality of the target image does not meet the quality requirement, and sending the focusing adjustment information to the focusing driving module. The focusing driving module is used for receiving the focusing adjustment information sent by the calculation processing module and carrying out focusing processing on the camera according to the focusing adjustment information. The camera is also used for acquiring a first iris image after focusing is finished.

The camera may be any one, for example, the camera may be an iris camera or a zoom camera, and the camera may also be a camera module composed of an iris camera and a zoom camera, or the like. The focusing driving module is respectively connected with the camera and the calculation processing module, and focuses on the camera according to the focusing adjustment information if the focusing driving module receives the focusing adjustment information.

In the implementation mode, the target image of the current scene is acquired through the camera, the image quality of the target image is determined according to the calculation processing module, the focusing adjustment information is determined according to the image quality of the target image, the focusing driving module performs focusing according to the focusing adjustment information, the camera acquires the image again after the focusing is completed, and the first iris image is acquired according to the acquired image, so that the camera can acquire the image of the current scene after the focusing is automatically performed, the image quality of the first iris image acquired by the camera is improved, and the accuracy of the first iris image identification is improved.

In one possible implementation, the focus driving module includes: the focusing device comprises a focusing rotating unit, a focusing rotating motor and a motor driving unit. The focusing rotation unit is respectively connected with the camera and the focusing rotation motor, and the motor driving unit is respectively connected with the focusing rotation motor and the calculation processing module. And the motor driving unit is used for receiving the focusing adjustment information sent by the computer processing module and driving the focusing rotating motor according to the focusing adjustment information. The focusing rotating motor is used for rotating the focusing rotating unit under the driving of the motor driving unit. The focusing rotating unit is used for carrying out rotary focusing.

In the implementation mode, the focusing driving unit is adjusted through the focusing adjustment information, so that the image acquisition equipment can automatically focus, and the definition of the first iris image acquired by the image acquisition equipment is improved.

It should be noted that the image capturing device may capture a video stream of a current scene through the camera, and acquire a multi-frame image of the current scene from the captured video stream, and the image capturing device may also periodically capture an image of the current scene, where an image capturing period may be set and changed as needed, and in the embodiment of the present disclosure, the image capturing period is not specifically limited.

In addition, the image acquisition equipment can sense the target object in the current scene, and image acquisition is carried out when the target object is sensed to exist in the current scene, wherein the image acquisition equipment can sense the target object in the current scene according to the distance sensor. Correspondingly, in another possible implementation manner, the image acquisition device further comprises a distance sensor; the distance sensor is connected with the camera; the distance sensor is used for detecting the imaging distance between a target object and the camera in the current scene, and sending an image acquisition instruction to the camera if the imaging distance between the target object and the camera in the current scene is detected to be within a preset distance; the camera is further used for receiving an image acquisition instruction sent by the distance sensor, acquiring an image according to the image acquisition instruction to obtain a target image, and sending the acquired target image to the calculation processing module.

The distance sensor may be an infrared distance sensor, an acoustic wave distance sensor, or the like. It should be noted that the distance sensor may send an image capturing instruction to the camera when detecting the target object, and the distance sensor may also detect an imaging distance between the target object and the camera, and send the image capturing instruction to the camera when the imaging distance between the target object and the camera is within a preset distance.

In the implementation mode, whether a target object exists in the current scene is determined through the distance sensor, if the target object exists in the current scene, an image acquisition instruction is sent to the camera, and the camera performs image acquisition according to the received image acquisition instruction, so that the camera can perform image acquisition only when receiving the image acquisition instruction, and further the camera is prevented from performing image acquisition all the time and acquiring invalid images.

In another possible implementation, the camera is a zoom camera;

the zoom camera is further used for receiving an image acquisition instruction sent by the distance sensor, the image acquisition instruction carries the imaging distance and acquires the imaging distance according to the image acquisition instruction, the focal length of the zoom camera is adjusted from a first focal length to a second focal length according to the imaging distance, the first focal length is the current focal length of the zoom camera, and the second focal length is the focal length of the zoom camera adjusted according to the imaging distance.

In this implementation, through setting up the camera into the camera that can zoom to the focus of camera can be adjusted according to current image forming distance, makes image acquisition equipment can use in wider image forming distance scope, has richened image acquisition equipment's application scene, and further, through auto zoom and auto focus, makes image acquisition equipment also can gather the image that satisfies the image quality condition after the zoom, and then has improved first iris image recognition's rate of accuracy.

Fig. 2 is a flow chart illustrating an image acquisition method according to an exemplary embodiment, as shown in fig. 2, the method including the following steps.

Step 201: and acquiring the image quality of a target image, wherein the target image is obtained by carrying out image acquisition on the current scene through image acquisition equipment.

Step 202: and if the image quality of the target image does not meet the quality requirement, carrying out focusing processing on the image acquisition equipment according to the image quality of the target image.

Step 203: and acquiring a first iris image of the target object through the focused image acquisition equipment.

In another possible implementation, the image quality of the target image includes position information of a target object in the target image and a sharpness of the target image;

In another possible implementation manner, the adjusting the model parameter of the second image quality determination model according to the return value to obtain the first image quality determination model includes:

determining a return value of a second image quality determination model after each model parameter adjustment; summing each return value, and if the sum of the return values is larger than a preset threshold value, determining that the second image quality determination model completes one-time reinforcement learning until the first image quality determination model is obtained; alternatively, the first and second electrodes may be,

determining second preset focusing adjustment information according to the second image quality determination model after the parameters are adjusted; focusing the image acquisition equipment according to the second preset focusing adjustment information; and acquiring the image quality of at least one frame of second sample image according to the focused image acquisition equipment, and determining that the second image quality determination model is trained to finish one reinforcement learning if the image quality of the at least one frame of second sample image meets the quality requirement until the first image quality determination model is obtained.

In another possible implementation manner, before obtaining the image quality of the target image, the method further includes:

taking the first face image as the target image; or, a second iris image corresponding to the iris image of the target object is cut out from the first face image, and the second iris image is taken as the target image.

In another possible implementation manner, the acquiring, by the image acquisition device after focusing, a first iris image of the target object includes:

acquiring an image of the face of the target object in the current scene by the focused image acquisition equipment to obtain a second face image; intercepting a first iris image corresponding to the iris of the target object from the second face image; alternatively, the first and second electrodes may be,

In another possible implementation, before the acquiring the target image, the method further includes:

acquiring a current scene image;

determining a current imaging distance according to the current scene image;

according to the imaging distance, determining a variable magnification value corresponding to the imaging distance from a mapping relation between the imaging distance and the variable magnification value of the image acquisition equipment;

determining a second focal length corresponding to the imaging distance according to the first focal length and the zoom value, wherein the first focal length is the current focal length of the image acquisition equipment;

In another possible implementation manner, before determining the second focal length corresponding to the imaging distance according to the first focal length and the zoom value, the method further includes:

In another possible implementation manner, the acquiring the image quality of the target image includes:

and inputting the target image into an image quality determination model to obtain the image quality of the target image.

In another possible implementation manner, before the target image is input into the image quality determination model and the image quality of the target image is obtained, the method further includes:

determining the probability of any image quality category of the sample image according to the second image quality determination model and the image characteristics;

determining the cross entropy error of a second image quality determination model according to the probability that the sample image is of any image quality category and the probability of the sample image;

and adjusting the model parameters of the second image quality determination model according to the cross entropy error until the cross entropy error is smaller than a preset threshold value, and obtaining the image quality determination model.

extracting iris features of the first iris image to obtain iris features of a target object in the first iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; determining the identity information of the target object according to the iris recognition result; alternatively, the first and second electrodes may be,

determining the image quality of the first iris image; if the image quality of the first iris image is larger than a preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the second iris image; performing feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

Fig. 3 is a flowchart of a proposed image acquisition method according to an exemplary embodiment, which includes the following steps, as shown in fig. 3.

Step 301: the image acquisition equipment acquires a current scene image.

The image acquisition equipment can directly acquire images according to the current focal length, and can focus firstly and then acquire images according to the focused focal length. The image acquisition equipment can acquire video streams, and determine a current scene image from the acquired video streams, wherein the current scene image can be a face image or an iris image.

Step 302: and the image acquisition equipment determines the current imaging distance according to the current scene image.

The imaging distance is the distance between a target object in the current scene and the image acquisition equipment. The image capturing device may further determine an imaging distance between the target object and the image capturing device according to the distance sensor, which is not particularly limited in the embodiments of the present disclosure.

In a possible implementation manner, the image capturing device may determine the second focal length corresponding to the current scene image according to the current scene image, the imaging parameter of the image capturing device, the picture proportion of the target object in the current scene image in the image picture, and the like. In the implementation manner, the image acquisition device calculates the second focal length corresponding to the current scene image according to the current scene image, so that the second focal length can be more matched with the imaging distance, and the accuracy of the determined second focal length is improved. In another possible implementation manner, the image acquisition device may further determine an imaging distance corresponding to the current scene image according to the current scene image, read a zoom value of the focal length corresponding to the imaging distance from a mapping relation between the imaging distance and the zoom value of the image acquisition device, and adjust the current first focal length of the image acquisition device according to the zoom value to obtain an adjusted second focal length.

Step 303: and the image acquisition equipment determines a variable magnification value corresponding to the imaging distance from the mapping relation between the imaging distance and the variable magnification value of the image acquisition equipment according to the imaging distance.

The image acquisition equipment determines the mapping relation between the imaging distance and the zoom value of the image acquisition equipment by calibrating. The process of determining the mapping relation between the imaging distance and the zoom value of the image acquisition device by the image acquisition device can be realized by the following steps (1) to (3), and comprises the following steps:

(1) The image acquisition device initializes the image acquisition device.

In this step, the image capturing device initializes device parameters of the image capturing device, where the device parameters of the image capturing device may include internal parameters of the image capturing device, a wide angle of a lens, an imaging resolution, and the like.

(2) The image acquisition equipment determines the picture proportion of the target object in the imaging picture of the image acquisition equipment.

The frame ratio may be the number of pixels occupied by the target object in the imaging frame, or the area ratio occupied by the target object in the imaging frame, and the like, which is not specifically limited in the embodiment of the present disclosure. In addition, the picture ratio may be a default picture ratio of the system, or may also be a picture ratio input by a user, and the picture ratio may be set and changed as needed.

(3) And the image acquisition equipment determines the mapping relation between the imaging distance and the zoom value of the camera according to the camera parameter initialized by the image acquisition equipment and the picture proportion.

In this step, the image acquisition device shoots according to the picture proportion of the target object in the imaging picture and different imaging distances, so that the picture proportions of the target objects corresponding to the different imaging distances are the same, records the corresponding relations between the different imaging distances and the focal lengths, and performs numerical fitting on the corresponding relations between the imaging distances and the focal lengths to obtain the mapping relation between the shooting distances and the zoom values.

It should be noted that, the steps (1) - (2) may be performed in any step before the step 303, and this is not particularly limited in the embodiment of the present disclosure. In addition, the steps (1) - (2) may be executed by the image capturing device, or may be performed by another device to determine the mapping relationship through simulation, and then send the mapping relationship to the image capturing device.

In the implementation manner, the mapping relationship between the target object and the zoom value is determined by determining the corresponding relationship between the imaging distance and the zoom value, so that the image acquisition device can determine the zoom value corresponding to the current focal length directly according to the imaging distance between the target object and the image acquisition device when determining the imaging distance between the target object and the image acquisition device, calculation is not needed, the zooming speed is increased, and the image acquisition speed is increased.

Step 304: and the image acquisition equipment determines a second focal length corresponding to the imaging distance according to the first focal length and the zoom value, wherein the first focal length is the current focal length of the image acquisition equipment.

In this step, the current first focal length is adjusted through the zoom value to obtain an adjusted second focal length.

In the implementation mode, the image acquisition equipment carries out coarse adjustment according to the first focal length, so that the image acquisition equipment can carry out coarse adjustment before image acquisition, the focusing time after the image acquisition equipment is shortened, the focusing efficiency of the image acquisition equipment is improved, and the image acquisition speed of the image acquisition equipment is further improved.

Step 305: and the image acquisition equipment acquires an image according to the second focal length to obtain the target image.

The target image may be a face image or an iris image, which is not specifically limited in the embodiment of the present disclosure. Accordingly, in a possible implementation manner, if the target image is a face image, the step can be implemented by the following steps (A1) - (A2), including:

(A1) The image acquisition equipment is used for carrying out image acquisition on the face of the target object in the current scene to obtain a first face image.

The image acquisition equipment can directly acquire images according to the current focal length to obtain a first face image. The image acquisition equipment can also focus firstly and then acquire the image according to the focused focal length to obtain the first face image. The image capture device may capture a video stream and determine a first facial image from the captured video stream.

(A2) The image acquisition device takes the first face image as the target image.

In another possible implementation manner, the target image is an iris image, and the image capturing device may directly capture the iris image of the target object, and accordingly, the process may be: the image acquisition equipment acquires an iris image of a target object to obtain a target image. The image acquisition device can also intercept an iris image of a target object from the acquired face image as a target image. Accordingly, the process can be realized by the following steps (B1) to (B2), including:

(B1) The image acquisition equipment acquires the image of the face of the target object in the current scene through the image acquisition equipment to obtain a first face image.

This step is similar to step (A1) and will not be described herein again.

(B2) And the image acquisition equipment intercepts a second iris image corresponding to the iris image of the target object from the first face image, and takes the second iris image as the target image.

In the step, the image acquisition device determines the position of the iris image of the target object in the first face image, intercepts the first face image according to the position of the iris of the target object to obtain a second iris image, and takes the second iris image as the target image.

Step 306: the image quality of a target image is obtained by the image acquisition equipment, and the target image is obtained by image acquisition of a current scene through the image acquisition equipment.

The current scene is the scene where the image acquisition equipment is located. Referring to fig. 4, the image capturing device captures an image in a current scene and determines the image quality of the captured target image. Wherein the image quality may include: the definition of the image, the position of the target object in the image, the focusing position corresponding to the target image, and the like. Accordingly, the image acquisition device can determine the image quality of the target image according to the image definition of the acquired target image, the position of the target object in the image, the focusing position corresponding to the target image and the like. For example, the image quality of the target image may be proportional to the sharpness of the image, and the image quality of the target image may also be determined according to the position of the target object in the target image and the target position, and the like.

The process of determining the image quality by the image acquisition device may be: and the image acquisition equipment inputs the target image into a target image quality determination model to obtain the image quality of the target image.

Correspondingly, before this step, the image acquisition device needs to perform model training on the second image quality determination model to obtain the target image quality determination model. The process of training the second image quality determination model to obtain the target image quality determination model may be implemented by the following steps (A1) to (A5), including:

(A1) An image acquisition device acquires a plurality of sample images and determines a plurality of image quality classes.

In this step, the image capturing apparatus may receive a plurality of sample images input by a user, where each sample image has an image quality class corresponding to the sample image. The multiple image quality classes may be manually classified according to image quality of different sample images. For example, the image qualities of the plurality of sample images may be manually classified into N classes, and the value of N may be set as needed, for example, N may be 100. Different image quality classes may correspond to different image quality scores, e.g., 0 for the image quality class with the lowest image quality and N-1 for the image quality class with the highest image quality.

(A2) For any sample image, the image acquisition equipment performs feature extraction on the sample image to obtain the image features corresponding to the sample image.

In this step, the image acquisition device performs feature extraction on the sample image, where the image features may be texture features, edge features, and the like of the image. For example, the image feature may be a texture of the iris, an edge contour of the iris, or the like. In addition, the image acquisition device may further perform feature extraction on the sample image through a deep convolutional neural network, and in the embodiment of the present disclosure, a method for extracting the image feature by the image acquisition device is not specifically limited.

In addition, before this step, the image capturing device needs to capture the target image in the current scene. In one possible implementation, the image capturing device may capture a video stream in a current scene, and extract a target image from the video stream. In another possible implementation, the image capturing device may also periodically capture the target image in the current scene. The acquisition period may be set and changed as needed, and in the embodiment of the present disclosure, the acquisition period is not specifically limited. For example, the acquisition period may be 10s,15s, 20s, or the like. In another possible implementation manner, the image capturing device detects whether a target object exists in the current scene, and captures the target image only when the target object exists.

(A3) And the image acquisition equipment determines the probability of any image quality class of the sample image according to the second image quality determination model and the image characteristics.

The image acquisition equipment inputs the image characteristics into a second image quality determination model, and the probability of each image quality category corresponding to the sample image is determined through the second image quality determination model.

The second image quality determination model is a deep neural convolution network, the last layer of the second image quality determination model is a full-connected layer, when the number of image quality categories is N, N probabilities can be output through the last layer of the second image quality determination model, and the N probabilities are the probabilities that the sample image is of each image quality category respectively. The last layer of the second image quality determination model may further include a softmax function, and the softmax function may normalize the value output by the full connection layer to obtain a probability of each image quality category corresponding to the sample image after normalization.

(A4) And the image acquisition equipment determines the cross entropy error of the second image quality determination model according to the probability that the sample image is of any image quality class and the probability of the sample image.

In this step, the image pickup device may determine the cross entropy error of the second image quality determination model by the softmax loss function. And the image acquisition equipment performs weighted summation on the logarithm of the probability of the sample image being in any image quality category according to the softmax loss function, and determines the opposite number of the summation as the cross entropy error of the second sample image quality determination model. The weight of the probability of each image quality category may be set as needed, for example, the weight of the probability of the image quality category corresponding to the sample image may be set to 1, and the other weights may be set to 0. In the embodiment of the present disclosure, the weight of the probability for each image quality category is not particularly limited.

(A5) And the image acquisition equipment adjusts the model parameters of the second image quality determination model according to the cross entropy error until the cross entropy error is smaller than a preset threshold value, so as to obtain the target image quality determination model.

In this step, the image acquisition device determines the cross entropy error of the model according to the second image quality, adjusts the model parameters of the second image quality determination model, determines the sample type of the sample image continuously through the second image quality determination model after the parameters are adjusted, determines the cross entropy error again until the cross entropy error is smaller than a preset threshold value, and determines that the model training is completed to obtain the first image quality determination model.

It should be noted that the process of training the second image quality determination model may be performed by the image capturing device, or may be performed by another device, and the first image quality determination model obtained by training is sent to the image capturing device. For example, the image quality determination model may be model-trained by a device such as a computer or a server, resulting in a first image quality determination model.

The image acquisition device determines whether the image quality of the target image meets the quality requirement according to the image quality of the target image, and if the image quality of the target image meets the quality requirement, the image acquisition device directly executes step 309 to obtain the first iris image in the red region. If the quality requirement is not satisfied, the image capturing device performs step 307 to perform focusing on the image capturing device.

Step 307: and if the image quality of the target image does not meet the quality requirement, the image acquisition equipment determines the focusing adjustment information of the image acquisition equipment according to the image quality of the target image.

With continued reference to fig. 4, the image capture device determines whether the image quality of the captured target image meets the quality requirements. The definition may be a definition of a target image or a definition of a target object in the target image, for example, the target object is an iris, and correspondingly, the definition is a definition of the iris, and the definition of the iris is determined by combining a visibility of an iris region, a visibility and definition of an iris texture, a visibility and definition of an iris edge contour.

Wherein the image capturing device may determine the focus adjustment information of the image capturing device through the first image quality determination model, and the process may be implemented through the following steps (1) - (2), including:

(1) And the image acquisition equipment inputs the position information of the target object in the target image and the definition of the target image into a first image quality determination model to obtain the focusing direction and degree of the image acquisition equipment.

The image quality of the target image includes position information of a target object in the target image and a sharpness of the target image. Before this step, model training needs to be performed on the second image quality determination model to obtain the first image quality determination model. The model training process can be realized by the following steps (1-1) - (1-6), including:

(1-1) the image capturing device acquires the image quality of at least one frame of the first sample image captured by the image capturing device.

The image capturing device captures a first video stream based on the current focus adjustment information, extracts at least one frame of first sample image from the captured first video stream, and determines the image quality of the at least one frame of first sample image, where the image quality of the first sample image may be achieved through (A1) - (A5) in step 306, and is not repeated again.

(1-2) the image capturing device determines a first preset focus adjustment information according to the image quality of the at least one frame of the first sample image and the second image quality determination model.

The first preset focusing adjustment information comprises a focusing direction and a focusing degree. In this step, the second image quality determination model generates first preset focusing adjustment information according to the image quality of the at least one frame of the first sample image.

And (1-3) the image acquisition equipment carries out focusing processing on the image acquisition equipment according to the first preset focusing adjustment information.

In this step, the image capturing device performs focusing processing on the image capturing device according to the first preset focusing adjustment information, and changes a focusing position, a focusing direction, a focusing degree, and the like of the image capturing device.

And (1-4) the image acquisition equipment acquires at least one frame of second sample image according to the focused image acquisition equipment.

This step is similar to step (1-1) and will not be described again.

(1-5) the image capturing device determining a reported value of the first preset focus adjustment information according to the image quality of the second sample image and a preset image quality.

In this step, the image quality of the second sample image is determined by the image capturing device, and this step is similar to the steps (A1) - (A5) in step 306, and will not be described herein again. The image acquisition equipment compares the image quality of the second sample image with the preset image quality, when the image quality of the second sample image is higher than the preset image quality, the current focusing processing is determined to meet the focusing condition, the return value of the first preset focusing adjustment information is determined to be a positive value, and when the image quality of the second sample image is not higher than the preset image quality, the current focusing processing is determined not to meet the focusing condition, the return value of the first preset focusing adjustment information is determined to be a negative value. The image capturing device may receive a preset image quality input by a user, and the image capturing device may further use the image quality of the first sample image as the preset image quality, which is not specifically limited in the embodiment of the present disclosure.

In addition, the magnitude of the absolute value of the reward value may also be determined according to the magnitude of the difference between the image qualities of the first sample image and the second sample image, and when the difference between the image qualities of the first sample image and the second sample image is larger, the absolute value of the reward value is larger.

And (1-6) adjusting the model parameters of the second image quality determination model by the image acquisition equipment according to the return value to obtain the first image quality determination model.

Referring to fig. 5, the image acquisition device may perform reinforcement learning on the trained first image quality determination model according to the image acquired by the image acquisition device, so that the first image quality determination model may be updated, perform reinforcement training on the first image quality determination model through the image acquired by the image acquisition device under the current focusing adjustment information, and determine new focusing adjustment information through the first image quality determination model after the reinforcement training, the image acquisition device may complete the training through multiple reinforcement learning, and the image acquisition device may complete the training through multiple reinforcement learning by performing steps (1-1) - (1-6) multiple times.

The image acquired by the image acquisition equipment carries out strengthening training on the first image quality determination model, so that the training sample images are enriched, and the accuracy of the first image quality determination model in determining the focusing adjustment information is improved.

After the image acquisition equipment performs multiple times of reinforcement learning, the image quality determination model is trained according to the determined second image quality determination model to obtain a first image quality determination model. The image acquisition equipment can directly determine the second information after the model parameters are adjusted as a first image quality determination model, and confirm that one-time reinforcement learning is completed; the image acquisition equipment can also sum the return values corresponding to the second image quality determination model after the parameters are adjusted each time, and when the sum of the return values is greater than a preset threshold value, the image acquisition equipment determines that one reinforcement learning is finished; or the image acquisition equipment determines the model according to the quality of the second image after the parameters are adjusted, continues to determine the primary focusing adjustment information, performs focusing according to the focusing adjustment information, acquires the second sample image again after the focusing is finished, and determines to finish the primary reinforcement learning when the image quality of the second sample image which is acquired again meets the image quality requirement; or the image acquisition equipment records the focusing times of the image acquisition equipment, and when the focusing times reach the preset times, the reinforcement learning is determined to be completed.

Correspondingly, in a possible implementation manner, the image acquisition equipment determines the return value of the second image quality determination model after adjusting the model parameters each time; and summing each return value, and determining that the reinforcement learning is finished if the sum of the return values is greater than a preset threshold value.

In another possible implementation manner, determining second preset focusing adjustment information according to the second image quality determination model after the parameter adjustment; focusing the image acquisition equipment according to the second preset focusing adjustment information; and acquiring the image quality of at least one frame of second sample image according to the focused image acquisition equipment, and determining that the reinforcement learning is finished if the image quality of the at least one frame of second sample image meets the quality requirement.

And after the image acquisition equipment finishes one-time reinforcement learning training, calculating a loss value of the second image quality determination model, and when the loss value of the second image quality determination model is smaller than a preset loss value, determining that the second image quality determination model is finished to obtain the first image quality determination model.

It should be noted that, because the camera of the image capturing device may be a continuous focusing camera or a discrete focusing camera, in the embodiment of the present disclosure, the focusing adjustment information of the image capturing device may be determined according to different functions. In a possible implementation manner, when the camera of the image acquisition device is a discrete focusing camera, the second image quality determination model may be a cost function, the value scoring is performed on multiple focusing adjustment information through the cost function, the focusing adjustment information with the highest value is determined as the current focusing adjustment information, the focusing adjustment information is used as the focusing adjustment information output by the second image quality determination model, and then the return value of the focusing adjustment information is determined.

In another possible implementation manner, when the camera of the image capturing device is a continuous focusing camera, the second image quality determining model may be a continuous function, and the output value of the continuous function is used as the focusing adjustment information output by the second image quality determining model, and then the reported value of the focusing adjustment information is determined.

It should be noted that, the training process may be performed by the image capturing device, or may be performed by other devices, and the other devices send the trained first image quality determination model to the image capturing device. For example, the device may be a terminal such as a computer or a mobile phone, or may be a server, where the server may be a single server, or may be a server cluster composed of a plurality of servers, and this is not particularly limited in the embodiment of the present disclosure. When the first image quality determination model is obtained by training other equipment, the training process is similar to the steps (1-1) - (1-6), and is not repeated again.

(2) The image acquisition device takes the direction and degree of focusing of the image acquisition device as the focusing adjustment information of the image acquisition device.

In this step, the image capturing device generates focusing adjustment information according to the focusing direction and degree, wherein the focusing direction includes: positive direction, negative direction, no movement, and the degree of focus may include small amplitude and hair amplitude. Therefore, the focusing adjustment information may include discrete focusing actions such as focusing in a positive direction with a large amplitude, focusing in a positive direction with a small amplitude, keeping still, focusing in a negative direction with a small amplitude, focusing in a negative direction with a large amplitude, and continuous focusing actions such as directly driving a motor to a focusing position of a camera.

Step 308: and the image acquisition equipment carries out focusing processing on the image acquisition equipment according to the focusing adjustment information.

In this step, the image acquisition device adjusts the focal length adjustment direction and the focal length adjustment size of the image acquisition device according to the focusing adjustment information, and the focusing is completed through the driving motor.

Step 309: the image acquisition device acquires a first iris image of the target object through the focused image acquisition device.

The first iris image may be an iris image of a target object directly acquired or a face image captured from an acquired face image, which is not specifically limited in the embodiment of the present disclosure. Correspondingly, in a possible implementation manner, the focused image acquisition equipment is used for acquiring the image of the face of the target object in the current scene to obtain a second face image; and intercepting a first iris image corresponding to the iris of the target object from the second face image. In another possible implementation manner, the focused image acquisition device acquires an image of the iris of the target object to obtain the first iris image.

In addition, after the image acquisition device acquires the first iris image, the iris in the first iris image can be identified, and the process of identifying the first iris image can be realized through the following steps (1) - (3), including:

(1) And the image acquisition equipment performs iris feature extraction on the first iris image to obtain the iris feature of the target object in the first iris image.

(2) And the image acquisition equipment performs characteristic identification on the iris characteristics of the target object to obtain an iris identification result.

(3) And the image acquisition equipment determines the identity information of the target object according to the iris recognition result.

It should be noted that, before performing iris recognition on the first iris image, the image capture device may first determine whether the image quality of the first iris image satisfies the image quality condition, and when the image quality condition is not satisfied, continue to perform focusing according to the image quality of the first iris image until the image quality of the first iris image satisfies the image quality, where the process may be: the image acquisition equipment determines the image quality of the first iris image; if the image quality of the first iris image is larger than the preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the first iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

It should be noted that the image acquisition device may readjust the focal length of the image, acquire the target image, and then reacquire the first iris image from the target image according to the requirement on quality. The image capturing device may also directly capture the first iris image of the target object after the focal length of the image is adjusted again, which is not particularly limited in the embodiment of the present disclosure.

In the implementation mode, the iris features of the first iris image collected after the automatic focusing are extracted for iris recognition, and the first iris image is high in image quality and clear, so that the iris recognition accuracy is improved.

FIG. 6 is a block diagram illustrating an image capture device according to an exemplary embodiment. The device includes:

a first obtaining module 601, configured to obtain image quality of a target image, where the target image is an image obtained by image-capturing a current scene through an image-capturing device;

a first focusing module 602, configured to perform focusing processing on the image acquisition device according to the image quality of the target image if the image quality of the target image does not meet the quality requirement;

a second obtaining module 603, configured to obtain a first iris image of the target object through the focused image capturing device.

In a possible implementation manner, the first focus module 602 is further configured to determine focus adjustment information of the image capturing device according to the image quality of the target image; and focusing the image acquisition equipment according to the focusing adjustment information.

the first focusing module 602 is further configured to input the position information of the target object in the target image and the sharpness of the target image into a first image quality determination model, so as to obtain a focusing direction and a focusing degree of the image capturing device; and taking the focusing direction and degree of the image acquisition equipment as focusing adjustment information of the image acquisition equipment.

In another possible implementation manner, the apparatus further includes:

a second determining module, configured to determine a reported value of the first preset focusing adjustment information according to the image quality of the second sample image and a preset image quality;

In another possible implementation manner, the first adjusting module is further configured to determine a return value of the second image quality determination model after each adjustment of the model parameter; summing each return value, and if the sum of the return values is larger than a preset threshold value, determining that the second image quality determination model completes one-time reinforcement learning until the first image quality determination model is obtained; alternatively, the first and second electrodes may be,

the first adjusting module is further used for determining second preset focusing adjusting information according to the second image quality determining model after the parameters are adjusted; focusing the image acquisition equipment according to the second preset focusing adjustment information; and according to the image quality of at least one frame of second sample image acquired by the focused image acquisition equipment, if the image quality of the at least one frame of second sample image meets the quality requirement, determining that the second image quality determination model completes one-time reinforcement learning until the first image quality determination model is obtained.

In another possible implementation manner, the apparatus further includes:

the second acquisition module is used for acquiring the image of the face of the target object in the current scene through the image acquisition equipment to obtain a first face image;

the first acquisition module is also used for taking the first face image as the target image; or, a second iris image corresponding to the iris image of the target object is cut out from the first face image, and the second iris image is taken as the target image.

In another possible implementation manner, the second obtaining module 603 is further configured to perform image acquisition on a face of a target object in a current scene through the focused image acquisition device to obtain a second face image; intercepting a first iris image corresponding to the iris of the target object from the second face image; alternatively, the first and second electrodes may be,

the second obtaining module 603 is further configured to perform image acquisition on the iris of the target object through the focused image acquisition device to obtain the first iris image.

In another possible implementation manner, the apparatus further includes:

the third acquisition module is used for acquiring a current scene image;

a fifth determining module, configured to determine, according to the first focal length and the zoom value, a second focal length corresponding to the imaging distance, where the first focal length is a current focal length of the image acquisition device;

In another possible implementation manner, the apparatus further includes:

the sixth determining module is used for initializing the image acquisition equipment and determining the picture proportion of the target object in the imaging picture of the image acquisition equipment;

In another possible implementation manner, the first obtaining module 601 is further configured to input the target image into an image quality determination model, so as to obtain the image quality of the target image.

In another possible implementation manner, the apparatus further includes:

and the second adjusting module is used for adjusting the model parameters of the second image quality determination model according to the cross entropy error until the cross entropy error is smaller than a preset threshold value, so as to obtain the image quality determination model.

In another possible implementation manner, the apparatus further includes:

the second extraction module is further used for determining the image quality of the first iris image; if the image quality of the first iris image is larger than a preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of the target object in the second iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

It should be noted that: in the image capturing device provided in the above embodiment, only the division of the above functional modules is used for illustration during image capturing, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the above described functions. In addition, the image acquisition device and the image acquisition method provided by the above embodiment belong to the same concept, and the specific implementation process thereof is described in the method embodiment, which is not described herein again.

Fig. 7 shows a block diagram of an image capturing apparatus 700 according to an exemplary embodiment of the present disclosure. The image acquisition apparatus 700 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Image capture device 700 may also be referred to by other names such as user equipment, portable terminals, laptop terminals, desktop terminals, and the like.

Generally, image acquisition device 700 includes: a processor 701 and a memory 702.

The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 701 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 701 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 702 may include one or more computer-readable storage media, which may be non-transitory. Memory 702 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 702 is used to store at least one instruction for execution by processor 701 to implement the image acquisition method provided by the method embodiments of the present disclosure.

In some embodiments, the image capturing apparatus 700 may further include: a peripheral interface 703 and at least one peripheral. The processor 701, the memory 702, and the peripheral interface 703 may be connected by buses or signal lines. Various peripheral devices may be connected to peripheral interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 704, a display screen 705, a camera assembly 706, an audio circuit 707, a positioning component 708, and a power source 709.

The peripheral interface 703 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 701 and the memory 702. In some embodiments, processor 701, memory 702, and peripheral interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral interface 703 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuitry 704 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 704 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 704 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 704 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 704 may also include NFC (Near Field Communication) related circuits, which are not limited by this disclosure.

The display screen 705 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to capture touch signals on or over the surface of the display screen 705. The touch signal may be input to the processor 701 as a control signal for processing. At this point, the display 705 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display screen 705 may be one, providing the front panel of the image capture device 700; in other embodiments, the display screens 705 may be at least two, respectively disposed on different surfaces of the image capturing apparatus 700 or in a folded design; in still other embodiments, display 705 may be a flexible display disposed on a curved surface or on a folded surface of image capture device 700. Even more, the display 705 may be arranged in a non-rectangular irregular pattern, i.e. a shaped screen. The Display 705 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or the like.

The camera assembly 706 is used to capture images or video. Optionally, camera assembly 706 includes a front camera and a rear camera. Generally, a front camera is disposed on a front panel of an electronic apparatus, and a rear camera is disposed on a rear surface of the electronic apparatus. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 706 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuitry 707 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 701 for processing or inputting the electric signals to the radio frequency circuit 704 to realize voice communication. For stereo capture or noise reduction purposes, the microphones may be multiple and disposed at different locations of the image capturing device 700. The microphone may also be an array microphone or an omni-directional acquisition microphone. The speaker is used to convert electrical signals from the processor 701 or the radio frequency circuit 704 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 707 may also include a headphone jack.

The positioning component 708 is used to position the current geographic Location of the image-capturing device 700 for navigation or LBS (Location Based Service). The Positioning component 708 can be a Positioning component based on the GPS (Global Positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

The power supply 709 is used to supply power to various components in the image capturing apparatus 700. The power source 709 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When power supply 709 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, image capture device 700 also includes one or more sensors 170. The one or more sensors 170 include, but are not limited to: acceleration sensor 711, gyro sensor 712, pressure sensor 713, fingerprint sensor 714, optical sensor 715, and proximity sensor 716.

The acceleration sensor 711 may detect the magnitude of acceleration in three coordinate axes of a coordinate system established with the image capturing apparatus 700. For example, the acceleration sensor 711 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 701 may control the display screen 705 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 711. The acceleration sensor 711 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 712 may detect a body direction and a rotation angle of the image capturing apparatus 700, and the gyro sensor 712 may cooperate with the acceleration sensor 711 to capture a 3D motion of the user with respect to the image capturing apparatus 700. From the data collected by the gyro sensor 712, the processor 701 may implement the following functions: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

Pressure sensors 713 may be disposed on a side frame of image capture device 700 and/or underneath display screen 705. When the pressure sensor 713 is disposed on a side frame of the image capturing apparatus 700, a user's holding signal of the image capturing apparatus 700 may be detected, and the processor 701 performs right-left hand recognition or shortcut operation according to the holding signal acquired by the pressure sensor 713. When the pressure sensor 713 is disposed at a lower layer of the display screen 705, the processor 701 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 705. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 714 is used for collecting a fingerprint of a user, and the processor 701 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 714, or the fingerprint sensor 714 identifies the identity of the user according to the collected fingerprint. Upon identifying that the user's identity is a trusted identity, the processor 701 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings, etc. Fingerprint sensor 714 may be disposed on the front, back, or side of image capture device 700. When a physical key or vendor Logo is provided on the image capturing device 700, the fingerprint sensor 714 may be integrated with the physical key or vendor Logo.

The optical sensor 715 is used to collect the ambient light intensity. In one embodiment, the processor 701 may control the display brightness of the display screen 705 based on the ambient light intensity collected by the optical sensor 715. Specifically, when the ambient light intensity is high, the display brightness of the display screen 705 is increased; when the ambient light intensity is low, the display brightness of the display screen 705 is adjusted down. In another embodiment, processor 701 may also dynamically adjust the shooting parameters of camera assembly 706 based on the ambient light intensity collected by optical sensor 715.

A proximity sensor 716, also referred to as a distance sensor, is typically disposed on the front panel of the image acquisition device 700. Proximity sensor 716 is used to capture the distance between the user and the front of image capture device 700. In one embodiment, when proximity sensor 716 detects that the distance between the user and the front of image capture device 700 is gradually decreased, processor 701 controls display screen 705 to switch from the bright screen state to the dark screen state; when the proximity sensor 716 detects that the distance between the user and the front of the image capturing device 700 is gradually increased, the processor 701 controls the display screen 705 to switch from the breath screen state to the bright screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 7 is not intended to be limiting of image acquisition device 700 and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components may be used.

In an exemplary embodiment, a computer-readable storage medium is further provided, in which at least one instruction is stored, and the at least one instruction is executable by a processor in a server to perform the voice signal processing method in the above-described embodiment. For example, the computer readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an embodiment of the present disclosure, a computer program product is further provided, where at least one instruction is stored in the computer program product, and the at least one instruction is loaded and executed by a processor, so as to implement the image acquisition method described in the implementation of the present disclosure.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be described in detail here.

It is to be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image acquisition method, characterized in that the method comprises:

acquiring the image quality of a target image, wherein the target image is obtained by image acquisition of a current scene through image acquisition equipment, and the image quality of the target image comprises position information of a target object in the target image and the definition of the target image;

if the image quality of the target image does not meet the quality requirement, inputting the position information of the target object in the target image and the definition of the target image into a first image quality determination model to obtain the focusing direction and degree of the image acquisition equipment;

taking the focusing direction and degree of the image acquisition equipment as focusing adjustment information of the image acquisition equipment;

focusing the image acquisition equipment according to the focusing adjustment information, wherein the image acquisition equipment is equipment for automatically focusing;

acquiring a first iris image of the target object through the focused image acquisition equipment;

wherein the process of determining the first image quality determination model comprises:

determining a return value of the first preset focusing adjustment information according to the image quality of the second sample image and the preset image quality; when the image quality of the second sample image is higher than the preset image quality, the return value of the first preset focusing adjustment information is a positive value; when the image quality of the second sample image is not higher than the preset image quality, the reported value of the first preset focusing adjustment information is a negative value;

2. The method of claim 1, wherein the adjusting the model parameters of the second image quality determination model according to the return value to obtain the first image quality determination model comprises:

determining second preset focusing adjustment information according to the second image quality determination model after the parameters are adjusted; focusing the image acquisition equipment according to the second preset focusing adjustment information; and acquiring the image quality of at least one frame of second sample image according to the focused image acquisition equipment, and determining that a second image quality determination model is trained to finish one reinforcement learning if the image quality of the at least one frame of second sample image meets the quality requirement until the first image quality determination model is obtained.

3. The method of claim 1, wherein prior to obtaining the image quality of the target image, the method further comprises:

4. The method of claim 1, wherein the acquiring, by the image acquisition device after focusing, a first iris image of the target object comprises:

5. The method of claim 3, wherein prior to acquiring the target image, the method further comprises:

acquiring a current scene image;

determining a current imaging distance according to the current scene image;

determining a second focal length corresponding to the imaging distance according to a first focal length and the zoom value, wherein the first focal length is a current focal length of the image acquisition equipment;

6. The method of claim 1, wherein after the acquiring, by the image acquisition device after focusing, a first iris image of the target object, the method further comprises:

extracting iris features of the first iris image to obtain the iris features of the target object in the first iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; determining the identity information of the target object according to the iris recognition result; alternatively, the first and second electrodes may be,

determining an image quality of the first iris image; if the image quality of the first iris image is larger than a preset threshold value, performing iris feature extraction on the first iris image to obtain the iris feature of a target object in a second iris image; carrying out feature recognition on the iris features of the target object to obtain an iris recognition result; and determining the identity information of the target object according to the iris recognition result.

7. An image acquisition apparatus, characterized in that the apparatus comprises: the device comprises a camera, a focusing driving module and a calculation processing module;

the camera is used for collecting images of a current scene to obtain a target image, and sending the collected target image to the calculation processing module, wherein the image quality of the target image comprises position information of a target object in the target image and the definition of the target image;

the calculation processing module is used for receiving the target image, determining the image quality of the target image, and if the image quality of the target image does not meet the quality requirement, inputting the position information of a target object in the target image and the definition of the target image into a first image quality determination model to obtain the focusing direction and degree of the image acquisition equipment, wherein the image acquisition equipment is equipment for automatically focusing;

taking the focusing direction and degree of the image acquisition equipment as focusing adjustment information of the image acquisition equipment, and sending the focusing adjustment information to the focusing driving module;

the camera is further used for acquiring a first iris image of the target object after focusing is finished;

the camera is further used for collecting at least one frame of first sample image and sending the at least one frame of first sample image to the calculation processing module;

the calculation processing module is further configured to obtain image quality of the at least one frame of the first sample image; determining a first preset focusing adjustment information according to the image quality of the at least one frame of the first sample image and the second image quality determination model; sending the first preset focusing adjustment information to the focusing driving module;

the focusing driving module is further used for carrying out focusing processing on the camera according to the first preset focusing adjustment information;

the camera is further used for collecting at least one frame of second sample image after focusing is finished; sending the at least one frame of second sample image to the calculation processing module;

the calculation processing module is further configured to determine a report value of the first preset focusing adjustment information according to the image quality of the second sample image and a preset image quality; when the image quality of the second sample image is higher than the preset image quality, the return value of the first preset focusing adjustment information is a positive value; when the image quality of the second sample image is not higher than the preset image quality, the return value of the first preset focusing adjustment information is a negative value; and adjusting the model parameters of the second image quality determination model according to the return value to obtain the first image quality determination model.