Face recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a face recognition method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: firstly, in response to a face image acquisition request, determining the type, current illumination intensity and position information of a requester of the face image acquisition request, then determining a target structured light pattern to be used currently and image acquisition parameters according to the type, current illumination intensity and position information of the requester, and acquiring a target structured light pattern to be used currently on the basis of the image acquisition parameters; the method comprises the following steps: acquiring a target structured light pattern, acquiring a first face image under the target structured light pattern, then identifying the first face image based on the target structured light pattern, determining face features corresponding to the first face image, and finally matching the face features with target face features to determine a face identification result. Therefore, fraud attacks can be effectively resisted, and the reliability and safety of face recognition are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a face recognition method and device, electronic equipment and storage medium. BACKGROUND

[0002] Due to the convenience of face recognition technology, it is more and more widely used in people's life, especially in mobile device unlocking, payment and other scenarios, but the current face recognition technology still has some security risks, how to improve the reliability and security of face recognition is a problem to be solved at present. SUMMARY

[0003] The present disclosure provides a face recognition method and device, electronic equipment and storage medium to solve the problem of how to improve the reliability and security of face recognition.

[0004] According to an aspect of the present disclosure, a face recognition method is provided, comprising:

[0005] In response to a face image collection request, determining the type of the requestor of the face image collection request, the current light intensity and the location information;

[0006] According to the type of the requestor, the current light intensity and the location information, determining the target structured light pattern to be used currently and the image collection parameter;

[0007] Based on the image collection parameter, collecting the first face image under the target structured light pattern;

[0008] Based on the target structured light pattern, identifying the first face image to determine the face feature corresponding to the first face image;

[0009] Matching the face feature with a target face feature to determine a face recognition result.

[0010] According to another aspect of the present disclosure, a face recognition device is provided, comprising:

[0011] A first determining module is configured to, in response to a face image collection request, determine the type of the requestor of the face image collection request, the current light intensity and the location information;

[0012] A second determining module is configured to, according to the type of the requestor, the current light intensity and the location information, determine the target structured light pattern to be used currently and the image collection parameter;

[0013] A collecting module is configured to, based on the image collection parameter, collect the first face image under the target structured light pattern;

[0014] a third determining module, configured to identify the first face image based on the target structured light pattern, and determine a face feature corresponding to the first face image;

[0015] a matching module, configured to match the face feature with a target face feature, to determine a face recognition result.

[0016] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0017] at least one processor;

[0018] and a memory connected to the at least one processor in communication;

[0019] wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the above-mentioned embodiments.

[0020] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform the method according to the above-mentioned embodiments.

[0021] The present disclosure provides a face recognition method, device, electronic device and storage medium. First, in response to a face image collection request, the type of the requester of the face image collection request, the current light intensity and the location information are determined, then the target structured light pattern and the image collection parameters currently to be used are determined according to the type of the requester, the current light intensity and the location information, and the first face image under the target structured light pattern is collected based on the image collection parameters, then the first face image is identified based on the target structured light pattern, and the face feature corresponding to the first face image is determined, finally the face feature is matched with the target face feature to determine the face recognition result. Thus, by determining the structured light pattern and the image collection parameters based on the requester type, the current light intensity and the location information of the requester of the face image collection request, collecting the face image under the structured light pattern based on the image collection parameters, and matching the face feature corresponding to the face image with the pre-stored face feature to determine the face recognition result, the reliability and security of face recognition can be effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure together with the specification.

[0023] Figure 1 A flowchart of a face recognition method provided by the embodiments of the present disclosure is shown in the figure;

[0024] Figure 2 An example diagram in which a target structured light pattern is projected to a face in a face recognition method provided by an embodiment of the present disclosure;

[0025] Figure 3 A flowchart of a face recognition method provided by an embodiment of the present disclosure;

[0026] Figure 4 A flowchart of a face recognition method provided by an embodiment of the present disclosure;

[0027] Figure 5 A flowchart of a face recognition method provided by an embodiment of the present disclosure;

[0028] Figure 6 A flowchart of a face recognition method provided by an embodiment of the present disclosure;

[0029] Figure 7 A flowchart of a face recognition method provided by an embodiment of the present disclosure;

[0030] Figure 8 A structural diagram of a face recognition device provided by an embodiment of the present disclosure;

[0031] Figure 9 A structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0032] The specific embodiments of the present disclosure have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and descriptions are not intended to limit the scope of the present disclosure concept in any way, but to illustrate the present disclosure concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0033] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same or similar components are denoted by the same reference numerals throughout the drawings and the following description, unless otherwise specified. The embodiments described in the following exemplary embodiments are not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure, as detailed in the appended claims.

[0034] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the present disclosure are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data need to comply with relevant laws, regulations, and standards in relevant countries and regions.

[0035] It should be noted that the acquisition, transmission, storage, use, processing and the like of data in the technical solutions of the present disclosure comply with relevant provisions of national laws and regulations.

[0036] It should be noted that in the embodiments of the present disclosure, some existing industry solutions may be mentioned, such as certain software, components, models, etc., which should be considered as exemplary, and the purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present disclosure, but it does not mean that the applicant has or will necessarily use the solution.

[0037] The face recognition method of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0038] Figure 1 A flowchart of a face recognition method provided by the embodiments of the present disclosure is shown.

[0039] As shown in Figure 1 , the method comprises:

[0040] Step 101, in response to a face image acquisition request, determining the type of the requestor of the face image acquisition request, the current light intensity and the position information.

[0041] The type of the requestor can be determined according to actual needs, or can also be determined according to the application scenario of face recognition. For example, when the application scenario of face recognition is a payment application scenario, the requestor of the face image acquisition request can be a payment service, when the application scenario of face recognition is an education application scenario, the type of the requestor of the face image acquisition request can be an education service, etc., which is not limited by the present disclosure.

[0042] In the present disclosure, in response to a face image acquisition request, in order to improve the reliability and security of face recognition, the type of the requestor, the current light intensity and the position information can be determined from the face image acquisition request first.

[0043] Step 102, determining the target structured light pattern and the image acquisition parameters to be used currently according to the type of the requestor, the current light intensity and the position information.

[0044] The target structured light pattern can be an infrared grating pattern, which can be pre-set or can also be determined according to actual needs. For example, the target structured light pattern can be an infrared grating fringe pattern, etc., which is not limited by the present disclosure.

[0045] The image acquisition parameters can be parameters when acquiring a face image. For example, the image acquisition parameters can include the acquisition angle of the image, whether to use auxiliary light and the intensity of the auxiliary light used, etc., which is not limited by the present disclosure.

[0046] The specific type and intensity of the auxiliary light can be determined according to actual needs, and this disclosure does not limit them.

[0047] It should be noted that in order to improve the effect of face recognition, the acquisition angle needs to be controlled at a suitable angle. For example, when the acquisition angle is greater than 45 degrees, some feature areas of the face may be obscured during acquisition, thus affecting the acquisition effect. Therefore, when the acquisition angle is less than 45 degrees, face image acquisition can be carried out better and face recognition effect can be achieved. This disclosure does not limit this.

[0048] In this disclosure, after determining the type of the requester of the face image acquisition request, the current illumination intensity, and the location information, in order to improve the accuracy of face image acquisition, the target structured light pattern to be used and the image acquisition parameters can be determined first based on the type of the requester, the current illumination intensity, and the location information.

[0049] Optionally, if the requester is a payment service, the target structured light pattern can be determined as the first pattern.

[0050] The first pattern can be any pre-set pattern. For example, the first pattern can be a pattern containing a certain number (e.g., about 30) of vertically arranged infrared grating stripes, etc., and this disclosure does not limit it.

[0051] Optionally, if the requester is a non-payment service, the target structured light pattern can be determined as the second pattern.

[0052] It should be noted that, since non-payment services may have a lower impact on users compared to payment services, in order to save resources and improve the efficiency of facial recognition, the complexity of the second pattern can be less than that of the first pattern. For example, the second pattern can be a pattern containing a smaller number (compared to the first pattern) of vertically arranged infrared grating stripes, etc., and this disclosure does not limit this.

[0053] In this disclosure, the target structured light pattern to be used is determined by the type of the requester, thereby improving the flexibility and reliability of face recognition.

[0054] Optionally, when determining the image acquisition parameters, it is possible to first determine whether to use auxiliary light and the intensity of the auxiliary light used based on the illumination intensity and position information. Then, based on at least one of the illumination intensity, position information, and target structured light pattern, the image acquisition angle is determined, thereby improving the reliability of the determined image acquisition parameters and providing conditions for improving the face recognition effect. This disclosure does not limit this aspect.

[0055] In step 103, a first face image under the target structured light pattern is collected based on the image collection parameter.

[0056] The first face image can be a face image of a current user to be identified corresponding to a face image collection request, and the first face image contains a structured light pattern reflected by the face.

[0057] In the present disclosure, after the target structured light pattern and the image collection parameter currently to be used are determined, the target structured light pattern can be projected to the face of the user based on the determined image collection angle, and the first face image under the target structured light pattern is collected. For example, in the case where the target structured light pattern is an infrared grating fringe pattern, the infrared grating fringe pattern can be projected to the face of the user by using a pre-set infrared grating device (such as a set of infrared LED emitters), and the present disclosure does not limit this.

[0058] The LED is an abbreviation of Light Emitting Diode (LED).

[0059] It should be noted that, in the case where the target structured light pattern is an infrared grating fringe pattern, when the infrared LED emitters are selected to project the grating fringe pattern, infrared LED emitters with appropriate device size and battery life for face recognition need to be selected, and the infrared light wavelength used by the present disclosure can be determined as needed, such as 940 nanometer wavelength, to ensure that the infrared light is invisible to the human eye, and the present disclosure does not limit this.

[0060] It should be noted that, when the target structured light pattern is projected to the face of the user, in order to ensure the integrity and accuracy of the collected first face image, it is necessary to ensure that part of the target structured light pattern is projected to the face of the user, such as Figure 2 , Figure 2 An example of projecting the target structured light pattern to the face in the face recognition method proposed by the embodiments of the present disclosure is shown in Figure 2 , the target structured light pattern is taken as an example of an infrared grating fringe pattern, in order to improve the effect and accuracy of face recognition, it is necessary to ensure that the target structured light pattern covers the entire face, when the infrared grating fringe pattern is projected to the face, a bright line will be formed on the surface of the face Figure 2 , as shown in FIG. 1, wherein Figure 2 This is only an example, and the present disclosure does not limit this.

[0061] In step 104, the first face image is identified based on the target structured light pattern, and a face feature corresponding to the first face image is determined.

[0062] The face feature can include a position, size, shape and the like of a facial organ in the first face image.

[0063] In the present disclosure, after the first face image under the target structured light pattern is collected, the first face image can be identified based on the target structured light pattern to determine the face feature corresponding to the first face image, thereby providing conditions for improving the reliability and security of face recognition.

[0064] Step 105, matching the face feature with the target face feature to determine the face recognition result.

[0065] The target face feature can be a face feature of a user corresponding to a pre-stored face image collection request.

[0066] The face recognition result can be that the face recognition is passed or that the face recognition is not passed, which is not limited in the present disclosure.

[0067] In the present disclosure, after the face feature corresponding to the first face image is determined, the face feature can be matched with the target face feature to determine the face recognition result, thereby improving the accuracy and security of face recognition.

[0068] In the embodiment of the present disclosure, first, in response to the face image collection request, the type of the requester of the face image collection request, the current light intensity and the position information are determined, then the target structured light pattern and the image collection parameter currently to be used are determined according to the type of the requester, the current light intensity and the position information, and the first face image under the target structured light pattern is collected based on the image collection parameter, after that, the first face image is identified based on the target structured light pattern to determine the face feature corresponding to the first face image, finally, the face feature is matched with the target face feature to determine the face recognition result. Therefore, by determining the structured light pattern and the image collection parameter based on the requester type, the current light intensity and the position information of the requester of the face image collection request, collecting the face image under the structured light pattern based on the image collection parameter, and matching the face feature corresponding to the face image with the pre-stored face feature to determine the face recognition result, the fraud attack can be effectively resisted, and the reliability and security of face recognition are improved.

[0069] Figure 3 A flowchart of a face recognition method provided by the embodiment of the present disclosure is shown.

[0070] As shown in Figure 3 , the method comprises:

[0071] Step 301, in response to the face image collection request, the type of the requester of the face image collection request, the current light intensity and the position information are determined.

[0072] In step 302, a target structured light pattern to be used currently and image acquisition parameters are determined according to the type of the requester, the current illumination intensity and the position information.

[0073] In step 303, a first face image under the target structured light pattern is acquired based on the image acquisition parameters.

[0074] In step 304, the first face image is recognized based on the target structured light pattern to determine a face feature corresponding to the first face image.

[0075] In step 305, the face feature is matched with a target face feature to determine a face recognition result.

[0076] The specific implementation forms of steps 301 to 305 can refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0077] In step 306, the image acquisition parameters are updated when the matching degree of the face feature and the target face feature is less than a first threshold and greater than a second threshold.

[0078] The first threshold can be a minimum critical value of the matching degree of the face feature for determining whether the face recognition passes, which can be pre-set or determined according to actual needs, and the present disclosure does not limit this.

[0079] The second threshold can be a matching degree critical value for determining whether to update the image acquisition parameters, which can be pre-set or determined according to actual needs, and is less than the first threshold, and the present disclosure does not limit this.

[0080] In the present disclosure, after the face feature is matched with the target face feature to determine the face recognition result, when the matching degree of the face feature and the target face feature is less than the first threshold and greater than the second threshold, it can be determined that the matching degree of the currently determined face feature and the target face feature is low, and the face recognition does not pass. When the matching degree of the face feature and the target face feature is greater than the second threshold, it can be determined that the accuracy of the recognized face feature is low or the integrity is low, which can be caused by the angle or illumination of the acquired image. At this time, the image acquisition parameters can be updated to further improve the accuracy and integrity of the face image acquisition.

[0081] In step 307, a second face image under the target structured light pattern is acquired based on the updated image acquisition parameters.

[0082] In the present disclosure, after the image acquisition parameters are updated, the second facial image under the target structured light pattern can be re-acquired based on the updated image acquisition parameters, and the target structured light pattern is projected to the face of the user, thereby providing conditions for high facial recognition effect.

[0083] In step 308, the first facial image and the second facial image are fused to obtain a fused facial image.

[0084] In the present disclosure, after the second facial image under the target structured light pattern is acquired, in order to improve the effect and efficiency of facial recognition, the first facial image and the second facial image can be fused to obtain a fused facial image before facial recognition.

[0085] In step 309, based on the fused facial image, the operation of determining facial features is returned to be executed to determine the facial recognition result.

[0086] In the present disclosure, after the fused facial image is obtained, the operation of determining facial features can be returned to be executed based on the fused facial image to determine the facial recognition result. In the case where the matching degree between the facial features corresponding to the fused facial image and the target facial features is greater than or equal to the first threshold, it is determined that the facial recognition passes, or in the case where the matching degree between the facial features corresponding to the fused facial image and the target facial features is still less than the first threshold, it is output that the facial recognition fails, thereby improving the accuracy and reliability of facial recognition and improving the user experience.

[0087] In the embodiments of the present disclosure, first, in response to a face image collection request, the type of the requester of the face image collection request, the current illumination intensity and the position information are determined, and according to the type of the requester, the current illumination intensity and the position information, the target structured light pattern to be currently used and the image collection parameter are determined, then based on the image collection parameter, the first face image under the target structured light pattern is collected, and based on the target structured light pattern, the first face image is identified to determine the face feature corresponding to the first face image, then the face feature is matched with the target face feature to determine the face recognition result, in the case that the matching degree of the face feature and the target face feature is less than a first threshold and greater than a second threshold, the image collection parameter is updated, and based on the updated image collection parameter, the second face image under the target structured light pattern is collected, finally, the first face image and the second face image are fused to obtain the fused face image, and based on the fused face image, the operation of determining the face feature is performed to determine the face recognition result. Therefore, after collecting the face image based on the structured light pattern, in the case that the matching degree between the face feature corresponding to the collected face image and the pre-stored face feature is less than the first threshold and greater than the second threshold, the image collection parameter is updated, and based on the updated image collection parameter, the face image under the structured light pattern is collected, and the previously collected face image is fused, and the fused face image is re-identified to improve the accuracy and reliability of face recognition.

[0088] Figure 4 A flowchart of a face recognition method provided by the embodiments of the present disclosure is shown.

[0089] As shown in Figure 4 , the method comprises:

[0090] Step 401, in response to a face image collection request, the type of the requester of the face image collection request, the current illumination intensity and the position information are determined.

[0091] Step 402, according to the type of the requester, the current illumination intensity and the position information, the target structured light pattern to be currently used and the image collection parameter are determined.

[0092] Step 403, based on the image collection parameter, the first face image under the target structured light pattern is collected.

[0093] The specific implementation forms of steps 401 to 403 can be referred to the detailed description in other embodiments of the present disclosure, which will not be repeated here.

[0094] Step 404, the structured light pattern reflected by the face contained in the first face image is obtained.

[0095] The structure light pattern reflected by the face can be a structure light pattern reflected after the target structure light pattern is projected to the face.

[0096] In the present disclosure, after the first face image under the target structure light pattern is collected, in order to improve the accuracy of face recognition, the structure light pattern reflected by the face contained in the first face image can be obtained first.

[0097] It should be noted that, in the case that the target structure light pattern is an infrared grating fringe pattern, when capturing the structure light pattern reflected by the face, the infrared camera can be made to work in the infrared spectrum range, so that the structure light pattern reflected by the face can be accurately captured. In addition, an infrared filter can be installed in front of the lens of the infrared camera to reduce visible light interference and only capture infrared light. At the same time, a suitable filter can also be selected to ensure the best infrared light transmittance, and the infrared camera and the LED emitter are calibrated to ensure the accuracy and consistency of the pattern, which is not limited in the present disclosure.

[0098] Step 405, determining the deformation data and energy difference data between the target structure light pattern and the structure light pattern reflected by the face.

[0099] In the present disclosure, after the structure light pattern reflected by the face contained in the first face image is obtained, since the face structure of each person is unique, that is, the structure light pattern reflected by the face will also be different under different collection angles or light intensities, the deformation data and energy difference data between the target structure light pattern and the structure light pattern reflected by the face can be determined to provide conditions for improving the security of face recognition.

[0100] Step 406, determining the three-dimensional face data corresponding to the first face image based on the deformation data and the energy difference data.

[0101] In the present disclosure, after the deformation data and the energy difference data between the target structure light pattern and the structure light pattern reflected by the face are determined, the three-dimensional face data corresponding to the first face image can be determined based on the deformation data and the energy difference data, thereby providing a data basis for obtaining more abundant face features.

[0102] It should be noted that, when determining the three-dimensional face data corresponding to the first face image, the three-dimensional face data can be determined by the principle of triangular positioning, using the geometric information in the structure light illumination, according to the geometric relationship between the camera projecting the structure light, the structure light and the object, which is not limited in the present disclosure.

[0103] Step 407, determining the face feature corresponding to the first face image based on the three-dimensional face data.

[0104] In the present disclosure, after determining the three-dimensional face data corresponding to the first face image, the face feature corresponding to the first face image can be determined based on the three-dimensional face data, so as to obtain richer face features, thereby providing conditions for improving the face recognition effect and security.

[0105] Step 408, matching the face feature with the target face feature to determine the face recognition result.

[0106] The specific implementation form of step 408 can refer to the detailed description in other embodiments of the present disclosure, which will not be repeated here.

[0107] In the embodiments of the present disclosure, first, in response to the face image acquisition request, the type of the requester of the face image acquisition request, the current illumination intensity and the position information are determined, and then the target structured light pattern to be used currently and the image acquisition parameters are determined according to the type of the requester, the current illumination intensity and the position information. Then, based on the image acquisition parameters, the first face image under the target structured light pattern is acquired, and the structured light pattern reflected by the face contained in the first face image is obtained. Then, the deformation data and the energy difference data between the target structured light pattern and the structured light pattern reflected by the face are determined, and based on the deformation data and the energy difference data, the three-dimensional face data corresponding to the first face image is determined. Finally, based on the three-dimensional face data, the face feature corresponding to the first face image is determined, and the face feature is matched with the target face feature to determine the face recognition result. Therefore, after the structured light pattern is projected onto the face to obtain the acquired face image, the deformation data and the energy difference data between the structured light pattern and the structured light pattern reflected by the face contained in the face image are determined, and based on the deformation data and the energy difference data, the three-dimensional face data corresponding to the face image is determined, and based on the three-dimensional face data, the face feature corresponding to the face image is determined, and the face feature is matched with the pre-stored face feature to determine the face recognition result, thereby effectively reducing the influence of environmental illumination on the face recognition result, and improving the security and effect of face recognition.

[0108] Figure 5 A flowchart of a face recognition method provided by the embodiments of the present disclosure is shown.

[0109] As shown in Figure 5 , the method comprises:

[0110] Step 501, in response to a face image acquisition request, determining the type of the requester of the face image acquisition request, the current illumination intensity and the position information.

[0111] Step 502, determining the target structured light pattern to be used currently and the image acquisition parameters according to the type of the requester, the current illumination intensity and the position information.

[0112] Step 503, based on the image acquisition parameters, acquiring a first facial image under the target structured light pattern.

[0113] Step 504, obtaining the structured light pattern reflected by the face in the first facial image.

[0114] Step 505, determining the deformation data and the energy difference data between the target structured light pattern and the structured light pattern reflected by the face.

[0115] The specific implementation forms of steps 501 to 505 can refer to the detailed descriptions in other embodiments of the present disclosure, which will not be repeated here.

[0116] Step 506, based on the deformation data, determining the depth data of the facial feature points of the first facial image.

[0117] The facial feature points can be the feature points of the facial organs, such as the feature points of the eyebrows, eyes, nose, and mouth, which are not limited in the present disclosure.

[0118] In the present disclosure, after the deformation data is determined, the depth of the facial feature points is different, which can cause different deformations of the patterns at different positions in the reflected structured light pattern. Therefore, based on the deformation data, the depth data of the facial feature points of the first facial image can be determined to provide a data basis for determining the three-dimensional facial data corresponding to the first facial image. Figure 2 For example, the twisted deformation of the infrared grating fringe pattern in the infrared grating fringe pattern can be observed to determine the deformation data and further determine the depth data of the face, thereby providing a data basis for determining the three-dimensional facial data corresponding to the first facial image. Figure 2

[0119] Step 507, based on the energy difference data, determining the facial skin texture data of the first facial image.

[0120] The facial skin texture data can include data such as wrinkles, protrusions, and smoothness of the face, which are not limited in the present disclosure.

[0121] In the present disclosure, after the energy difference data is determined, the skin texture of the face will affect the energy distribution of the structured light. The smooth skin surface can reduce the reflection of the structured light, so that more structured light energy is absorbed by the skin, and the wrinkles and protrusions of the skin surface will also affect the absorption of the structured light. Therefore, based on the energy difference data, the facial texture data of the first facial image can be determined.

[0122] Step 508, based on the depth data of the facial feature points and the facial skin texture data, determining the three-dimensional facial data corresponding to the first facial image.

[0123] ​In the present disclosure, after the facial skin texture data is determined, the three-dimensional face data corresponding to the first face image can be determined based on the depth data of the facial feature points and the facial skin texture data, thereby improving the accuracy and reliability of the determined three-dimensional face data.

[0124] In step 509, the face feature corresponding to the first face image is determined based on the three-dimensional face data.

[0125] In step 510, the face feature is matched with a target face feature to determine a face recognition result.

[0126] The specific implementation forms of steps 509 to 510 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0127] In the embodiments of the present disclosure, first, in response to a face image collection request, the type of the requester of the face image collection request, the current light intensity and the position information are determined, and the target structured light pattern to be used currently and the image collection parameters are determined according to the type of the requester, the current light intensity and the position information. The first face image under the target structured light pattern is collected based on the image collection parameters, and the structured light pattern reflected by the face contained in the first face image is obtained. Then, the deformation data between the target structured light pattern and the structured light pattern reflected by the face, and the energy difference data are determined, and the depth data of the facial feature points of the first face image is determined based on the deformation data. The facial skin texture data of the first face image is determined based on the energy difference data. After that, the three-dimensional face data corresponding to the first face image is determined based on the depth data of the facial feature points and the facial skin texture data, and the face feature corresponding to the first face image is determined based on the three-dimensional face data. Finally, the face feature is matched with a target face feature to determine a face recognition result. Thus, after the structured light pattern is projected to the face and the face image is collected, the deformation data between the structured light pattern reflected by the face and the projected structured light pattern, and the energy difference data are determined, and the depth data of the facial feature points of the face image and the facial skin texture data of the face image are determined based on the deformation data and the energy difference data respectively. The three-dimensional face data corresponding to the face image is determined based on the depth data and the facial skin texture data, and the face feature corresponding to the face image is determined based on the three-dimensional face data, and then the face recognition is performed, thereby improving the reliability and effect of the face recognition.

[0128] Figure 6 A flowchart of a face recognition method provided by the embodiments of the present disclosure is shown.

[0129] As shown in Figure 6 , the method comprises:

[0130] In step 601, in response to the face image collection request, the type of the requester of the face image collection request, the current light intensity, and the location information are determined.

[0131] In step 602, according to the type of the requester, the current light intensity, and the location information, the target structured light pattern to be currently used and the image collection parameter are determined.

[0132] In step 603, the first face image under the target structured light pattern is collected based on the image collection parameter.

[0133] In step 604, the structured light pattern reflected by the face in the first face image is obtained.

[0134] In step 605, the deformation data and the energy difference data between the target structured light pattern and the structured light pattern reflected by the face are determined.

[0135] In step 606, the three-dimensional face data corresponding to the first face image is determined based on the deformation data and the energy difference data.

[0136] The specific implementation forms of steps 601 to 606 can be referred to the detailed description in other embodiments of the present disclosure, which will not be repeated here.

[0137] In step 607, the three-dimensional face model corresponding to the first face image is generated based on the three-dimensional face data.

[0138] In the present disclosure, after the first face image is determined, in order to improve the efficiency and effect of face recognition, the three-dimensional face model corresponding to the first face image can be generated based on the three-dimensional face data.

[0139] In step 608, the three-dimensional face feature corresponding to the first face image is determined based on the three-dimensional face model.

[0140] In the present disclosure, after the three-dimensional face model corresponding to the first face image is generated, the three-dimensional face feature corresponding to the first face image can be determined based on the three-dimensional face model, thereby providing conditions for obtaining more abundant and accurate face features.

[0141] Optionally, when the three-dimensional face feature corresponding to the first face image is determined based on the three-dimensional face model, in order to improve the accuracy and reliability of the three-dimensional face model, the positions of the reference feature points in the preset three-dimensional reference face model can be obtained first, and then the positions of the three-dimensional feature points in the three-dimensional face model are calibrated based on the positions of the reference feature points to determine the three-dimensional face feature corresponding to the first face image, thereby improving the reliability and accuracy of the determined three-dimensional face feature.

[0142] In step 609, the three-dimensional face feature is converted into a two-dimensional face feature, and the two-dimensional face feature is determined as the face feature corresponding to the first face image.

[0143] In the present disclosure, after determining the three-dimensional face feature corresponding to the first face image, the three-dimensional face feature is converted into a two-dimensional face feature, and the two-dimensional face feature is determined as the face feature corresponding to the first face image, thereby improving the accuracy and reliability of the determined face feature, and providing conditions for improving the face recognition effect and accuracy.

[0144] In step 610, the face feature is matched with a target face feature to determine a face recognition result.

[0145] The specific implementation form of step 610 can refer to the detailed description in other embodiments of the present disclosure, and will not be repeated here.

[0146] In the embodiments of the present disclosure, first, in response to a face image collection request, the type of the requester of the face image collection request, the current light intensity and the position information are determined, and according to the type of the requester, the current light intensity and the position information, the target structured light pattern to be currently used and the image collection parameters are determined, then based on the image collection parameters, the first face image under the target structured light pattern is collected, the structured light pattern reflected by the face contained in the first face image is obtained, and the deformation data and the energy difference data between the target structured light pattern and the structured light pattern reflected by the face are determined, based on the deformation data and the energy difference data, the three-dimensional face data corresponding to the first face image is determined, then based on the three-dimensional face data, the three-dimensional face model corresponding to the first face image is generated, and based on the three-dimensional face model, the three-dimensional face feature corresponding to the first face image is determined, finally, the three-dimensional face feature is converted into a two-dimensional face feature, the two-dimensional face feature is determined as the face feature corresponding to the first face image, and the face feature is matched with a target face feature to determine a face recognition result. Therefore, after determining the three-dimensional face data corresponding to the collected face image based on the deformation data and the energy difference data between the structured light pattern projected to the face and the structured light pattern emitted by the face, the corresponding three-dimensional face model is generated based on the three-dimensional face data, and the three-dimensional face feature corresponding to the face image is determined based on the three-dimensional face model, the three-dimensional face feature is converted into a two-dimensional face feature, and is determined as the face feature corresponding to the face image, and the face recognition is performed based on the face feature, thereby improving the effect and reliability of face recognition.

[0147] Figure 7 A flowchart of a face recognition method provided by an embodiment of the present disclosure is shown in FIG. 6.

[0148] As shown in FIG. 6, the method includes the following steps. Figure 7 ​

[0149] Step 701, in response to the face image collection request, determining the type of the requestor of the face image collection request, the current light intensity and the location information.

[0150] Step 702, according to the type of the requestor, the current light intensity and the location information, determining the target structured light pattern to be used currently and the image collection parameter.

[0151] Step 703, collecting the first face image under the target structured light pattern based on the image collection parameter.

[0152] Step 704, identifying the first face image based on the target structured light pattern, and determining the face feature corresponding to the first face image.

[0153] The specific implementation forms of steps 701 to 704 can refer to the detailed description in other embodiments of the present disclosure, which will not be repeated here.

[0154] Step 705, determining the first description information corresponding to the face feature, wherein the first description information includes the size, proportion, shape and position of the facial organ.

[0155] In the present disclosure, after determining the face feature corresponding to the first face image, the first description information corresponding to the face feature can be determined based on the position of the facial feature point in the face feature, for example, the size, proportion, shape and position of the eyebrow, eye, nose and mouth in the face can be determined based on the position of the corresponding feature points of the eyebrow, eye, nose and mouth in the face feature, thereby providing a data basis for face recognition.

[0156] Step 706, obtaining the second description information corresponding to the target face feature.

[0157] In the present disclosure, after determining the first description information corresponding to the face feature, the second description information corresponding to the target face feature can also be obtained for accurate and efficient face recognition, thereby determining the size, proportion, shape and position of the facial organ corresponding to the target face feature.

[0158] Step 707, determining the matching degree between the first description information and the second description information.

[0159] In the present disclosure, after obtaining the second description information corresponding to the target face feature, the matching degree between the first description information and the second description information can be determined based on the first description information and the second description information, so as to determine the face recognition result.

[0160] It should be noted that in the disclosure, when the matching degree between the first description information and the second description information is calculated, the discrete variables of the first description information can also be analyzed by a classification method, and the relationship model between the first description information and the second description information can be calculated by a regression analysis method, and the like, which further provides conditions for improving the face recognition effect, and the disclosure does not limit this.

[0161] Step 708, in the case where the matching degree is greater than the first threshold, it is determined that the first face image face recognition passes.

[0162] In the disclosure, after the matching degree between the first description information and the second description information is calculated, in the case where the matching degree is greater than the first threshold, it can be determined that the matching degree between the first description information and the second description information is high, at this time, it can be determined that the first face image face recognition passes, thereby improving the effect and safety of face recognition.

[0163] In the embodiment of the disclosure, first, in response to the face image acquisition request, the type of the requester of the face image acquisition request, the current illumination intensity and the position information are determined, and according to the type of the requester, the current illumination intensity and the position information, the target structured light pattern to be currently used and the image acquisition parameter are determined, then based on the image acquisition parameter, the first face image under the target structured light pattern is acquired, and based on the target structured light pattern, the first face image is identified to determine the face feature corresponding to the first face image, then the first description information corresponding to the face feature is determined, and the second description information corresponding to the target face feature is obtained, finally, the matching degree between the first description information and the second description information is calculated, in the case where the matching degree is greater than the first threshold, it is determined that the first face image face recognition passes. Therefore, after the face image under the structured light pattern is acquired, and the face feature corresponding to the face image is determined, the description information corresponding to the face feature is determined, and the matching degree between the description information and the pre-stored description information corresponding to the face feature is calculated, in the case where the matching degree is greater than the threshold, it is determined that the face recognition passes, thereby improving the effect and reliability of face recognition.

[0164] In order to realize the above-mentioned embodiment, the embodiment of the disclosure also provides a face recognition device.

[0165] Figure 8 A structural schematic diagram of a face recognition device provided by the embodiment of the disclosure.

[0166] As shown in Figure 8 the face recognition device 800 can include:

[0167] The first determination module 801 is configured to, in response to a face image acquisition request, determine the type of the requester of the face image acquisition request, the current illumination intensity and the position information.

[0168] The second determining module 802 is configured to determine a target structured light pattern to be used currently and image acquisition parameters according to the type of the requester, the current illumination intensity, and the position information.

[0169] The acquisition module 803 is configured to acquire a first face image under the target structured light pattern based on the image acquisition parameters.

[0170] The third determining module 804 is configured to identify the first face image based on the target structured light pattern, and determine a face feature corresponding to the first face image.

[0171] The matching module 805 is configured to match the face feature with a target face feature, to determine a face recognition result.

[0172] Optionally, the second determining module 802 is specifically configured to perform any one of the following:

[0173] In a case where the type of the requester is a payment service, the target structured light pattern is determined as a first pattern.

[0174] In a case where the type of the requester is a non-payment service, the target structured light pattern is determined as a second pattern.

[0175] The complexity of the second pattern is less than that of the first pattern.

[0176] Optionally, the second determining module 802 is specifically configured to:

[0177] According to the illumination intensity and the position information, it is determined whether to use auxiliary light and the intensity of the auxiliary light used.

[0178] According to at least one of the illumination intensity, the position information, and the target structured light pattern, the acquisition angle of the image is determined.

[0179] Optionally, the matching module 805 is further configured to:

[0180] In a case where the matching degree of the face feature and the target face feature is less than a first threshold value and greater than a second threshold value, the image acquisition parameters are updated.

[0181] Based on the updated image acquisition parameters, a second face image under the target structured light pattern is acquired.

[0182] The first face image and the second face image are fused to obtain a fused face image.

[0183] Based on the fused face image, the operation of determining the face feature is performed again to determine the face recognition result.

[0184] Optionally, the third determining module 804 is specifically configured to:

[0185] acquire a structured light pattern reflected by the face in the first face image;

[0186] determine deformation data and energy difference data between the target structured light pattern and the structured light pattern reflected by the face;

[0187] determine three-dimensional face data corresponding to the first face image based on the deformation data and the energy difference data;

[0188] determine face features corresponding to the first face image based on the three-dimensional face data.

[0189] Optionally, the third determining module 804 is further configured to:

[0190] determine depth data of facial feature points of the first face image based on the deformation data;

[0191] determine facial skin texture data of the first face image based on the energy difference data;

[0192] determine three-dimensional face data corresponding to the first face image based on the depth data of the facial feature points and the facial skin texture data.

[0193] Optionally, the third determining module 804 is further configured to:

[0194] generate a three-dimensional face model corresponding to the first face image based on the three-dimensional face data;

[0195] determine three-dimensional face features corresponding to the first face image based on the three-dimensional face model;

[0196] convert the three-dimensional face features into two-dimensional face features, and determine the two-dimensional face features as the face features corresponding to the first face image.

[0197] Optionally, the third determining module 804 is further configured to:

[0198] acquire positions of reference feature points in a preset three-dimensional reference face model;

[0199] calibrate positions of three-dimensional feature points in the three-dimensional face model based on the positions of the reference feature points, and determine the three-dimensional face features corresponding to the first face image.

[0200] Optionally, the matching module 805 is specifically configured to:

[0201] determine first description information corresponding to the face features, wherein the first description information includes sizes, proportions, shapes and positions of facial organs;

[0202] acquire second description information corresponding to the target face features;

[0203] determine the matching degree between the first description information and the second description information;

[0204] In a case where the matching degree is greater than a first threshold, it is determined that the first face image face recognition passes.

[0205] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can refer to the above method embodiments, which will not be described here.

[0206] In the present disclosure, first, in response to a face image collection request, the type of the requester of the face image collection request, the current light intensity and the location information are determined, then according to the type of the requester, the current light intensity and the location information, the target structured light pattern to be used currently and the image collection parameters are determined, and based on the image collection parameters, the first face image under the target structured light pattern is collected, then the first face image is identified based on the target structured light pattern, the face feature corresponding to the first face image is determined, and finally the face feature is matched with the target face feature to determine the face recognition result. Therefore, by determining the structured light pattern and the image collection parameters based on the requester type, the current light intensity and the location information of the requester of the face image collection request, collecting the face image under the structured light pattern based on the image collection parameters, matching the face feature corresponding to the face image with the pre-stored face feature to determine the face recognition result, the reliability and security of face recognition are improved.

[0207] Figure 9 A block diagram of an exemplary electronic device suitable for use in implementing the embodiments of the present disclosure is shown.

[0208] Figure 9 The electronic device 12 shown is merely an example and should not impose any limitations on the functions and use range of the embodiments of the present disclosure.

[0209] As Figure 9As shown, the electronic device 12 is in the form of a general-purpose computing device. The components of the electronic device 12 can include, but are not limited to, one or more processors or processing units 16, a memory 28, a bus 18 that connects the various system components, including the memory 28 and the processing unit 16. The bus 18 represents one or more of any of several bus structures, including a memory bus or memory controller, a peripheral bus, a graphics accelerator bus, and a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0210] The electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by the electronic device 12 and includes both volatile and non- volatile media, removable and non-removable media.

[0211] The memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 can be used for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 9 A removable / non-removable volatile, non-volatile computer system storage medium (e.g., a floppy disk, a magnetic tape, and / or an optical disk, etc.) is typically used for storing data that is either not needed immediately nor for a long period of time. For example, a storage system 34 can be used for storing such data as an operating system, application programs, and program data. Note that the storage system 34 can be

[0212] Although the Figure 9A disk drive, a floppy disk drive, a CD-ROM drive, a DVD-ROM drive, or other removable media drive, can be provided for reading from and writing to a removable n onvolatile magnetic disk (e.g., a "floppy disk"), and to a removable nonvolatile optical disk (e.g., a CD ROM, a DVD ROM, or another optical medium). In these instances, each drive can be connected to the bus 18 by one or more data media interfaces. The memory 28 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

[0213] Program / utility 40, having a set (at least one) of program modules 42, can be stored in memory 28 by way of example, and can include an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, which may

[0214] The electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or a pointing device, a display 24, etc.; other devices such as a device that enables a human user to interact with the electronic device 12; and / or one or more devices that enable the electronic device 12 to communicate with one or more other computing devices. Such communication can be via the input / output (I / O) interface 22. Furthermore, the electronic device 12 can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) through a network adapter 20. As shown, the network adapter 20 communicates with the other components of the electronic device 12 through the bus 18. It should be appreciated that, although not shown, other hardware and / or software modules could be used in connection with the electronic device 12. These include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0215] The processing unit 16 executes the various program applications and parameter information determinations by running the programs stored in the memory 28, such as to implement the face recognition methods mentioned in the foregoing embodiments.

[0216] To achieve the above-mentioned embodiments, the present disclosure further proposes a non-transitory computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the face recognition method as proposed in the foregoing embodiments of the present disclosure.

[0217] To achieve the above-mentioned embodiments, the present disclosure further proposes a computer program product, which, when instructions in the computer program product are executed by a processor, executes the face recognition method as proposed in the foregoing embodiments of the present disclosure.

[0218] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the present disclosure cover any and all variations of the present disclosure including combinations or permutations of individual features disclosed. The true scope of the present disclosure is indicated by the appended claims, along with the full scope of equivalents to which such claims are entitled. The specification and examples given herein are to be considered illustrative rather than restrictive.

[0219] It should be understood that the present disclosure is not limited to the precise construction that has been described above and shown in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present disclosure. The scope of the present disclosure is limited only by the appended claims.

[0220] It should be noted that, in the description of the present disclosure, the terms "first", "second", and the like are used only for descriptive purposes, and cannot be construed as indicating or implying relative importance. In addition, in the description of the present disclosure, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0221] Any process or method descriptions or any other descriptions herein can be understood as representing embodiments of implementations encompassing one or more steps, operations or functions, and the scope of methods of the preferred embodiments of the present disclosure include additional implementations that can be performed in an order different from the order shown or discussed, including substantially concurrently or in reverse order, and the like, depending on the functionality involved.

[0222] It should be understood that various parts of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: discrete logic circuit with logic gates for implementing logical functions on data signals, application specific integrated circuit (ASIC) with suitable combination logic gates, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0223] Those skilled in the art can understand that all or part of the steps of the method carried out by the above-mentioned embodiments can be completed by programs instructing the relevant hardware, and the programs can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0224] In addition, each functional unit in each embodiment of the present disclosure can be integrated into one processing module, or each unit can exist physically independently, or two or more units can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0225] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0226] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0227] Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present disclosure.

Claims

1. A face recognition method, characterized by, The method comprises the following steps: In response to a face image collection request, determining the type of the requester of the face image collection request, the current light intensity and the location information; According to the type of the requester, the current light intensity and the location information, determining the target structured light pattern to be used currently and the image collection parameters; Based on the image collection parameters, collecting the first face image under the target structured light pattern; Based on the target structured light pattern, identifying the first face image to determine the face feature corresponding to the first face image; Matching the face feature with a target face feature to determine a face recognition result.

2. The method of claim 1, wherein, The determination of the target structured light pattern to be used currently according to the type of the requester, the current light intensity and the location information comprises any of the following: In the case that the type of the requester is a payment service, the target structured light pattern is determined as a first pattern; In the case that the type of the requester is a non-payment service, the target structured light pattern is determined as a second pattern; The complexity of the second pattern is less than that of the first pattern.

3. The method of claim 1, wherein, The determination process of the image collection parameters comprises: According to the light intensity and the location information, determining whether to use auxiliary light and the intensity of the auxiliary light used; According to at least one of the light intensity, the location information and the target structured light pattern, determining the collection angle of the image.

4. The method according to any one of claims 1 to 3, characterized in that, After the matching of the face feature with the target face feature to determine the face recognition result, the method further comprises the following steps: In the case that the matching degree of the face feature and the target face feature is less than a first threshold value and greater than a second threshold value, updating the image collection parameters; Based on the updated image collection parameters, collecting a second face image under the target structured light pattern; Fusing the first face image and the second face image to obtain a fused face image; Based on the fused face image, returning to perform the operation of determining the face feature to determine the face recognition result.

5. The method of claim 1, wherein, The identification of the first face image based on the target structured light pattern to determine the face feature corresponding to the first face image comprises the following steps: Obtaining the structured light pattern reflected by the face contained in the first face image; Determining the deformation data and the energy difference data between the target structured light pattern and the structured light pattern reflected by the face; Based on the deformation data and the energy difference data, determining the three-dimensional face data corresponding to the first face image; Based on the three-dimensional face data, determining the face feature corresponding to the first face image.

6. The method of claim 5, wherein, The determination of the three-dimensional face data corresponding to the first face image based on the deformation data and the energy difference data comprises the following steps: Based on the deformation data, determining the depth data of the facial feature points of the first face image; Based on the energy difference data, determining the facial skin texture data of the first face image; Based on the depth data of the facial feature points and the facial skin texture data, determining the three-dimensional face data corresponding to the first face image.

7. The method of claim 5, wherein, The determining the face feature corresponding to the first face image based on the three-dimensional face data comprises: generating a three-dimensional face model corresponding to the first face image based on the three-dimensional face data; determining a three-dimensional face feature corresponding to the first face image based on the three-dimensional face model; converting the three-dimensional face feature into a two-dimensional face feature, and determining the two-dimensional face feature as the face feature corresponding to the first face image.

8. The method of claim 7, wherein, The determining the three-dimensional face feature corresponding to the first face image based on the three-dimensional face model comprises: obtaining positions of reference feature points in a preset three-dimensional reference face model; calibrating positions of three-dimensional feature points in the three-dimensional face model based on the positions of the reference feature points, and determining the three-dimensional face feature corresponding to the first face image.

9. The method of claim 1, wherein, The matching the face feature with a target face feature to determine a face recognition result comprises: determining first description information corresponding to the face feature, wherein the first description information comprises sizes, proportions, shapes and positions of facial organs; obtaining second description information corresponding to the target face feature; determining a matching degree between the first description information and the second description information; determining that the face recognition of the first face image is passed when the matching degree is greater than a first threshold.

10. A face recognition apparatus, characterized by comprising: The method comprises: a first determining module configured to determine a type of a requester of a face image collection request, a current light intensity and position information of the requester in response to the face image collection request; a second determining module configured to determine a target structured light pattern and image collection parameters to be used currently according to the type of the requester, the current light intensity and the position information of the requester; a collection module configured to collect a first face image under the target structured light pattern based on the image collection parameters; a third determining module configured to determine a face feature corresponding to the first face image by identifying the first face image based on the target structured light pattern; a matching module configured to match the face feature with a target face feature to determine a face recognition result.

11. An electronic device, comprising: The method comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions likely to be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method in any one of claims 1-9.

12. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to execute the method in any one of claims 1-9.

13. A computer program product comprising a computer program which, when executed by a processor, implements the method in any one of claims 1-9.

Images