A control method and device for intelligent face recognition door lock

Abstract

This application discloses a control method and device for an intelligent facial recognition door lock. The control method includes: upon detecting a target user approaching the intelligent facial recognition door lock through the detection unit, controlling the facial image acquisition unit to acquire a facial image to be verified; comparing the facial image to be verified with a first facial image in a first database to obtain a first comparison result; comparing the facial image to be verified with a second facial image in a second database to obtain a second comparison result; determining a verification result based on the first and second comparison results, and controlling the intelligent lock cylinder based on the verification result. This control method can improve the accuracy and flexibility of intelligent facial recognition door locks.

Description

Technical Field

[0001] The present application relates to the field of smart device technology, and more particularly to a control method and device for a smart face recognition door lock. Background Art

[0002] With the development of intelligent technology, the application of intelligent devices is becoming more and more widespread. For smart door locks, door lock control can usually be achieved through intelligent recognition methods such as face recognition, fingerprint recognition, and password recognition.

[0003] At present, in the field of facial recognition in smart door locks, there is a problem of a relatively scarce facial recognition database, which leads to poor accuracy and flexibility of facial recognition. Summary of the Invention

[0004] The purpose of this application is to provide a control method and device for an intelligent face recognition door lock, which can improve the accuracy and flexibility of the intelligent face recognition door lock.

[0005] To achieve the above-mentioned objectives, an embodiment of the present application provides a control method for an intelligent face recognition door lock, wherein the intelligent face recognition door lock includes: an intelligent lock core, a detection unit and a face image acquisition unit, and the control method includes: when the detection unit detects that the target user is approaching the intelligent face recognition door lock, controlling the face image acquisition unit to acquire a face image to be verified; comparing the face image to be verified with a first face image in a first database to obtain a first comparison result; the first face image is a preset trusted face image, and the first comparison result is used to indicate whether there is a matching first face image; comparing the face image to be verified with a second face image in a second database to obtain a second comparison result; the second face image is a face image obtained in real time from a target database, and the target database is used to update untrustworthy face images in real time, and the second comparison result is used to indicate the similarity between the face image to be verified and the second face image; determining a verification result based on the first comparison result and the second comparison result, and controlling the intelligent lock core based on the verification result.

[0006] In a possible implementation, before controlling the facial image acquisition unit to acquire the facial image to be verified, the control method further includes: determining that the distance between the target user and the intelligent facial recognition door lock is less than a preset distance, and outputting a voice prompt message; the voice prompt message is used to indicate whether to use facial unlocking; correspondingly, controlling the facial image acquisition unit to acquire the facial image to be verified includes: upon receiving the indication information for determining to use facial unlocking, controlling the facial image acquisition unit to acquire the facial image to be verified.

[0007] In a possible embodiment, controlling the facial image acquisition unit to acquire the facial image to be verified includes: controlling the facial image acquisition unit to acquire a first facial image to be verified under a first acquisition environment; the first acquisition environment includes a brightness parameter and a distance parameter; judging whether the image quality of the first facial image to be verified meets a preset quality standard; if so, controlling the facial image acquisition unit to acquire multiple facial images to be verified again based on the first acquisition environment, and determining a final facial image to be verified based on the multiple facial images to be verified; if not, determining a second acquisition environment based on the gap between the image quality and the preset quality standard, controlling the facial image acquisition unit to acquire multiple second facial images to be verified under the second acquisition environment, and determining the final facial image to be verified based on the multiple second facial images to be verified.

[0008] In one possible embodiment, the facial image to be verified includes multiple facial images, and the comparing the facial image to be verified with the first facial image in the first database to obtain a first comparison result includes: determining a target first facial image from the first facial image; the average similarity between the target first facial image and the multiple facial images is greater than the first similarity; determining the maximum similarity and the minimum similarity between the target first facial image and the multiple facial images; determining a first integrated similarity based on a preset first similarity integration rule, the average similarity, the maximum similarity and the minimum similarity; if the first integrated similarity is greater than the second similarity, determining that a matching first facial image exists; wherein the second similarity is greater than the first similarity; if the first integrated similarity is less than the second similarity, determining that a matching first facial image does not exist.

[0009] In a possible implementation, the preset first similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the maximum similarity and a preset adjustment value; wherein the preset adjustment value is determined based on the difference between the second similarity and the first similarity; if the difference between the average similarity and the maximum similarity is less than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the average similarity and the preset adjustment value; if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the first integrated similarity based on the maximum similarity and the minimum similarity.

[0010] In one possible embodiment, the facial image to be verified includes multiple facial images, and the comparing the facial image to be verified with the second facial image in the second database to obtain a second comparison result includes: determining a target second facial image from the second facial image based on the number of verifications of the second facial image and a preset number of verifications; the number of verifications is used to represent the number of times the second facial image is compared with other facial images to be verified; determining the maximum similarity, minimum similarity and average similarity between the target second facial image and the multiple facial images; determining a second integrated similarity based on a preset second similarity integration rule, the average similarity, the maximum similarity and the minimum similarity; the second integrated similarity is the second comparison result.

[0011] In a possible implementation, the preset second similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the maximum similarity and the minimum similarity; if the difference between the average similarity and the maximum similarity is less than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the average similarity; if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the second integrated similarity based on the maximum similarity and a preset adjustment value.

[0012] In one possible embodiment, determining the verification result based on the first comparison result and the second comparison result includes: if the first comparison result indicates that there is a matching first facial image, judging whether the similarity indicated by the second comparison result is greater than a first preset similarity; if so, determining that the verification result is verification passed and the door cannot be unlocked directly; if not, determining that the verification result is verification passed and the door can be unlocked directly; if the first comparison result indicates that there is no matching first facial image, judging whether the similarity indicated by the second comparison result is less than a second preset similarity; if so, determining that the verification result is verification failed and re-verification is required; if not, determining that the verification result is verification failed and an alarm prompt message needs to be output.

[0013] In a possible embodiment, the smart face recognition door lock also includes: a fingerprint verification unit and an alarm unit, and the controlling of the smart lock core according to the verification result includes: if the verification result is that the verification is passed and the lock cannot be unlocked directly, controlling the fingerprint verification unit to determine the fingerprint verification result; controlling the smart lock core according to the fingerprint verification result; if the verification result is that the verification fails and re-verification is required, controlling the fingerprint verification unit to determine the fingerprint verification result; controlling the smart lock core according to the fingerprint verification result and the verification result; if the verification result is that the verification fails and an alarm prompt message needs to be output, controlling the smart lock core to remain closed, and controlling the alarm unit to output an alarm prompt message.

[0014] An embodiment of the present application also provides a control device for an intelligent face recognition door lock, which includes: an intelligent lock core, a detection unit and a face image acquisition unit, and the control device includes: a control unit, which is used to control the face image acquisition unit to acquire a face image to be verified when the detection unit detects that the target user is approaching the intelligent face recognition door lock; a comparison unit, which is used to compare the face image to be verified with a first face image in a first database to obtain a first comparison result; the first face image is a preset trusted face image, and the first comparison result is used to indicate whether there is a matching first face image; the comparison unit is also used to compare the face image to be verified with a second face image in a second database to obtain a second comparison result; the second face image is a face image obtained in real time from a target database, and the target database is used to update untrustworthy face images in real time, and the second comparison result is used to indicate the similarity between the face image to be verified and the second face image; the control unit is also used to determine a verification result based on the first comparison result and the second comparison result, and control the intelligent lock core based on the verification result.

[0015] Compared to existing technologies, the control method and device for the intelligent facial recognition door lock provided in the embodiments of this application verify the facial image to be verified based on two databases. The first database stores trusted facial images, while the second database stores untrusted facial images, which are updated in real time. Consequently, a match comparison result can be obtained based on the first database, while a similarity comparison result can be obtained based on the second database. Based on these two comparison results, the final verification result is determined, ensuring the accuracy of the facial verification result. Furthermore, the integration of the two databases enhances the flexibility of facial recognition. Furthermore, the intelligent lock cylinder is controlled based on the verification results. Consequently, this control method and device can improve the accuracy and flexibility of intelligent facial recognition door locks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic structural diagram of an intelligent face recognition door lock according to an embodiment of the present application;

[0017] Figure 2 This is a flow chart of a control method for an intelligent face recognition door lock according to an embodiment of the present application;

[0018] Figure 3 2 is a schematic structural diagram of an intelligent face recognition door lock according to another embodiment of the present application;

[0019] Figure 4 1 is a schematic structural diagram of a control device for an intelligent face recognition door lock according to an embodiment of the present application;

[0020] Figure 5 It is a structural diagram of a controller according to one embodiment of the present application. DETAILED DESCRIPTION

[0021] The specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present application is not limited by the specific implementation methods.

[0022] Unless expressly stated otherwise, throughout the specification and claims, the term "comprise" or variations such as "include" or "comprising", etc., will be understood to include the stated elements or components but not to exclude other elements or other components.

[0023] The technical solution provided in the embodiments of the present application can be applied to smart face recognition door locks, which can be used in various application scenarios, such as: home door locks, corporate door locks, special place door locks, etc.

[0024] In these application scenarios, if facial recognition function is required, on the one hand, the smart door lock needs to have an image acquisition module, and on the other hand, the smart door lock needs to have a corresponding database for facial verification; then, facial verification can be achieved based on the collected facial images and the existing database.

[0025] In related technologies, the face verification database is usually set up in the following way: through user preset, the user can only preset the face data with unlocking authority, which makes the database relatively scarce, and thus cannot guarantee the accuracy, flexibility, and security of the smart face recognition door lock.

[0026] Based on this, the embodiments of the present application provide an intelligent facial recognition door lock. This intelligent facial recognition door lock, based on facial recognition, increases the richness of the facial recognition database, thereby improving the accuracy, flexibility, and security of the facial recognition door lock. It should be noted that when the camera for collecting facial data is installed, a prominent facial recognition prompt is set.

[0027] Please refer to Figure 1 , is a schematic diagram of the structure of the smart face recognition door lock 10 provided in an embodiment of the present application. The smart face recognition door lock 10 includes: a smart lock cylinder 101, a detection unit 102, a face image acquisition unit 103, and a controller 104. The smart lock cylinder 101, the detection unit 102, and the face image acquisition unit 103 are respectively connected to the controller 104.

[0028] In some embodiments, the connection between the smart lock core 101 and the controller 104, as well as the control method, can refer to mature technologies in the field.

[0029] In some embodiments, the detection unit 102 may be a sensor, including a distance sensor or other sensor capable of object detection, for detecting the distance between a person and a door lock.

[0030] In some embodiments, the facial image acquisition unit 103 can be an ordinary camera, an infrared camera, or other device capable of image acquisition.

[0031] In some embodiments, the smart lock core 101 and the controller 104 are set inside the smart face recognition door lock 10, the detection unit 102 can be set inside or outside the smart face recognition door lock 10; the face image acquisition unit 103 is set outside the smart face recognition door lock 10.

[0032] In some embodiments, the smart face recognition door lock 10 may also be provided with a display unit, and the face image acquisition unit 103 may be provided together with the display unit.

[0033] It can be understood that the configuration of each unit of the intelligent face recognition door lock 10 can refer to the mature technology in this field and will not be introduced in detail here.

[0034] In some embodiments, the smart face recognition door lock 10 may have a background control system that can establish a communication connection with the controller 104, for example, via Bluetooth, wireless network, etc. Therefore, the smart face recognition door lock 10 may also include Bluetooth communication, wireless communication, etc. modules.

[0035] Thus, the background control system can upload data to the controller 104, so that the controller 104 can control the smart face recognition door lock 10 based on the uploaded data. In addition, the background control system can also configure the control method of the controller 104, that is, the background control system is equivalent to the control unit of the controller 104, which is used to maintain the operation of the smart face recognition door lock 10.

[0036] Please refer to Figure 2, is a flow chart of a control method of the smart face recognition door lock 10 provided in an embodiment of the present application, and the control method can be applied to the aforementioned controller 104. Figure 2 As shown, the control method includes:

[0037] Step 201 : When the detection unit 102 detects that the target user is approaching the intelligent face recognition door lock 10 , the face image acquisition unit 103 is controlled to acquire a face image to be verified.

[0038] In some embodiments, the target user is the user who currently wants to unlock the door. The target user may be a user with unlocking authority or a user without unlocking authority, so face verification is required for the target user.

[0039] In some embodiments, the detection unit 102 detects the distance between the target user and the smart face recognition door lock 10. When the detected distance is less than a certain distance value, it can be considered that the target user may have a need to unlock the door, and a facial image to be verified can be collected. However, for the smart face recognition door lock 10, in addition to the face unlocking function, other unlocking functions may be configured. Therefore, the target user may not necessarily use face unlocking. Therefore, the target user can be asked whether to use face unlocking.

[0040] Therefore, as an optional implementation, before step 201, the control method also includes: determining that the distance between the target user and the smart face recognition door lock 10 is less than a preset distance, and outputting a voice prompt message; the voice prompt message is used to indicate whether face unlocking is adopted; correspondingly, controlling the face image acquisition unit 103 to acquire the face image to be verified, including: when receiving the indication information for determining to adopt face unlocking, controlling the face image acquisition unit 103 to acquire the face image to be verified.

[0041] In some embodiments, the preset distance can be set in combination with the application scenario of the smart face recognition door lock 10, for example: 0.1m, etc.

[0042] In some embodiments, the voice prompt information can also be set in combination with the application scenario of the smart face recognition door lock 10, for example, whether to turn on face recognition. In addition, the voice prompt information can also be divided into languages, for example, Chinese prompt information, English prompt information, etc.

[0043] In some embodiments, the instruction information for using face unlocking can be realized through voice instruction information. In this case, the smart face recognition door lock 10 can also be equipped with a voice input module. It can also be realized through a confirmation module on the smart face recognition door lock 10. In this case, the smart face recognition door lock 10 can also be equipped with a confirmation button.

[0044] In some embodiments, the facial image acquisition unit 103 may include: multiple facial image acquisition units 103, each configured to acquire facial images to be verified at a different angle.

[0045] In some embodiments, the facial image acquisition unit 103 can realize omnidirectional image acquisition and obtain facial images to be verified at different angles.

[0046] In some embodiments, controlling the facial image acquisition unit 103 to acquire the facial image to be verified includes: controlling the facial image acquisition unit 103 to acquire the first facial image to be verified under a first acquisition environment; the first acquisition environment includes a brightness parameter and a distance parameter; judging whether the image quality of the first facial image to be verified meets a preset quality standard; if so, controlling the facial image acquisition unit 103 to acquire multiple facial images to be verified again based on the first acquisition environment, and determining the final facial image to be verified based on the multiple facial images to be verified; if not, determining the second acquisition environment based on the gap between the image quality and the preset quality standard, controlling the facial image acquisition unit 103 to acquire multiple second facial images to be verified under the second acquisition environment, and determining the final facial image to be verified based on the multiple second facial images to be verified.

[0047] In some embodiments, the brightness parameter can be understood as the brightness of the current environment; the distance parameter can be understood as the distance between the face and the face image acquisition unit 103.

[0048] The first acquisition environment may be a current real-time acquisition environment. In the first acquisition environment, better images may be acquired, or worse images may be acquired.

[0049] Therefore, it is determined whether the image quality of the first face image to be verified collected under the first collection environment meets the preset quality standard.

[0050] The preset quality standards may include image resolution, image clarity, and face integrity, etc. Specific standards may be configured according to different application scenarios.

[0051] Thus, the image quality of the first face image to be verified is compared with a preset quality standard. If the standard is met, multiple face images to be verified can be collected again, and the collection can be performed at different angles.

[0052] If the standards are not met, the collection environment needs to be adjusted.

[0053] In some embodiments, adjustment values ​​of the brightness parameter and the distance parameter are determined according to the difference between the image quality and a preset quality standard, and then corresponding adjustments are made to determine the second adjustment environment.

[0054] In some embodiments, when adjusting the brightness parameters, it can be achieved by lighting, using infrared acquisition, etc.

[0055] In some embodiments, when the distance parameter is adjusted, a prompt message may be output to prompt the user to adjust the distance.

[0056] In some embodiments, the second acquisition environment may involve not only brightness parameters and distance parameters but also position parameters of the face relative to the face image acquisition parameters, and it is necessary to ensure that the face can be fully presented in the face image to be verified.

[0057] In some embodiments, the greater the difference between the current image quality and the preset quality standard, the larger the aforementioned adjustment value is.

[0058] In some embodiments, when determining the final facial image to be verified, multiple selectable images may be deduplicated. For example, for images with a similarity greater than 95%, only one image may be retained.

[0059] Therefore, there may be multiple facial images to be verified, and these multiple images correspond to different acquisition angles.

[0060] Step 202: Compare the facial image to be verified with a first facial image in a first database to obtain a first comparison result, wherein the first facial image is a preset trusted image, and the first comparison result is used to indicate whether there is a matching first facial image.

[0061] In some embodiments, the preset trusted images may be images configured by authorized users (eg, owners of door locks), and these trusted images respectively include facial information of people with unlocking authority.

[0062] As an optional implementation, step 202 includes: determining a target first facial image from the first facial image; the average similarity between the target first facial image and multiple facial images is greater than the first similarity; determining the maximum similarity and the minimum similarity between the target first facial image and the multiple facial images; determining a first integrated similarity based on a preset first similarity integration rule, the average similarity, the maximum similarity, and the minimum similarity; if the first integrated similarity is greater than the second similarity, determining that a matching first facial image exists; wherein the second similarity is greater than the first similarity; if the first integrated similarity is less than the second similarity, determining that a matching second facial image does not exist.

[0063] In some embodiments, the average similarity between each first facial image and multiple facial images is determined; specifically, for a first facial image, the similarities between the first facial image and multiple facial images are determined, and then the similarities are averaged to determine the average similarity.

[0064] Thus, each first facial image corresponds to an average similarity. These average similarities are then compared with the first similarity, and the first facial image with a higher similarity than the first similarity is determined as the target first facial image. The first similarity is a preset similarity value, such as a 50% or 75% similarity value.

[0065] Furthermore, a maximum similarity and a minimum similarity between the target first facial image and the multiple facial images are determined, wherein the maximum similarity is the maximum value of the similarities between the target first facial image and the multiple facial images, and the minimum similarity is the minimum value of the similarities between the target first facial image and the multiple facial images.

[0066] In some embodiments, the first similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the maximum similarity and a preset adjustment value; wherein the preset adjustment value is determined based on the difference between the second similarity and the first similarity; if the difference between the average similarity and the maximum similarity is less than the preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the average similarity and the preset adjustment value; if the difference between the average similarity and the maximum similarity is greater than the preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the first integrated similarity based on the maximum similarity and the minimum similarity.

[0067] In some embodiments, the preset difference value may be, for example, a similarity value such as 10%, 25%, etc.

[0068] In some embodiments, the preset adjustment value may be a value smaller than the difference between the second similarity and the first similarity.

[0069] In some embodiments, a preset adjustment value is subtracted from the maximum similarity to determine the first integrated similarity.

[0070] In some embodiments, a preset adjustment value is added to the minimum similarity to determine a second integrated similarity.

[0071] In some embodiments, a weighted average of the maximum similarity and the minimum similarity is taken to determine a first integrated similarity. The weight corresponding to the maximum similarity and the weight corresponding to the minimum similarity can be determined based on the difference between the maximum similarity and the average similarity, with the larger the difference, the larger the weight; and the weight corresponding to the minimum similarity can be determined based on the difference between the minimum similarity and the average similarity, with the larger the difference, the larger the weight.

[0072] In some embodiments, the second similarity is greater than the first similarity. If the first integrated similarity is greater than the first similarity, it is determined that a matching first facial image exists; otherwise, it is determined that no matching first facial image exists.

[0073] Step 203 compares the facial image to be verified with a second facial image in a second database to obtain a second comparison result. The second facial image is a facial image obtained in real time from a target database, which is used to update untrusted facial images in real time. The second comparison result indicates the similarity between the facial image to be verified and the second facial image.

[0074] In some embodiments, the target database may be a database provided by a relevant organization, which can be updated with untrusted facial images in real time. The background control system of the smart facial recognition door lock 10 can then obtain these facial images and update them into the second database for use in facial verification.

[0075] In some embodiments, step 203 includes: determining a target second facial image from the second facial image based on the number of verifications of the second facial image and a preset number of verifications; the number of verifications is used to characterize the number of times the second facial image is compared with other facial images to be verified; determining the maximum similarity, minimum similarity and average similarity between the target second facial image and multiple facial images; determining a second integrated similarity based on a preset second similarity integration rule, average similarity, maximum similarity and minimum similarity; the second integrated similarity is a second comparison result.

[0076] In some embodiments, other facial images to be verified can be understood as facial images that have been verified historically. These facial images do not need to be stored in the database, and only the number of verifications needs to be recorded.

[0077] In some embodiments, the preset number of verifications may be 1, or a value greater than 1.

[0078] In some embodiments, a second facial image with a verification number greater than a preset number is determined as a target second facial image.

[0079] Furthermore, based on the target second facial image, the maximum similarity, minimum similarity and average similarity between the target second facial image and the plurality of facial images are determined.

[0080] In some embodiments, the preset second similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than the preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the maximum similarity and the minimum similarity; if the difference between the average similarity and the maximum similarity is less than the preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the average similarity; if the difference between the average similarity and the maximum similarity is greater than the preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the second integrated similarity based on the maximum similarity and a preset adjustment value.

[0081] In some embodiments, the preset difference here may be the same as the aforementioned preset difference.

[0082] In some embodiments, based on the maximum similarity and the minimum similarity, the second integrated similarity may be determined by referring to the aforementioned weighted average method.

[0083] In some embodiments, the average similarity may be determined as the second integrated similarity.

[0084] In some embodiments, a preset adjustment value may be subtracted from the maximum similarity to determine the second integrated similarity. The implementation of the preset adjustment value may refer to the aforementioned embodiments.

[0085] In the embodiment of the present application, the method for determining the similarity between images can refer to the mature technology in the field.

[0086] Step 204, determine the verification result based on the first comparison result and the second comparison result, and control the smart lock core 101 based on the verification result.

[0087] As an optional implementation, step 204 includes: if the first comparison result indicates that there is a matching first facial image, determining whether the similarity indicated by the second comparison result is greater than a first preset similarity; if so, determining that the verification result is verified to be passed, and the door cannot be unlocked directly; if not, determining that the verification result is verified to be passed, and the door can be unlocked directly; if the first comparison result indicates that there is no matching first facial image, determining whether the similarity indicated by the second comparison result is less than a second preset similarity; if so, determining that the verification result is verified to be failed, and re-verification is required; if not, determining that the verification result is verified to be failed, and an alarm prompt message needs to be output.

[0088] In some embodiments, the first preset similarity may be 80%, or a higher similarity value.

[0089] In some embodiments, the second preset similarity may be 50%, or a relatively medium similarity value.

[0090] In some embodiments, please refer to Figure 3 The smart face recognition door lock 10 also includes: a fingerprint verification unit 105 and an alarm unit 106.

[0091] Correspondingly, step 204 includes: if the verification result is verification passed and the lock cannot be unlocked directly, controlling the fingerprint verification unit 105 to determine the fingerprint verification result; controlling the smart lock core 101 according to the fingerprint verification result; if the verification result is verification failed and re-verification is required, controlling the fingerprint verification unit 105 to determine the fingerprint verification result; controlling the smart lock core 101 according to the fingerprint verification result and the verification result; if the verification result is verification failed and an alarm prompt message needs to be output, controlling the smart lock core 101 to remain closed, and controlling the alarm unit 106 to output an alarm prompt message.

[0092] In some embodiments, the implementation method of the fingerprint verification unit 105 obtaining the fingerprint verification result can refer to mature technologies in the art.

[0093] In some embodiments, if the fingerprint verification result is passed, the smart lock cylinder 101 is controlled to be opened; if not, the smart lock cylinder 101 is controlled to be closed.

[0094] In some embodiments, if both the fingerprint verification result and the verification result indicate that the verification is passed, the smart lock cylinder 101 is controlled to open; as long as one of the verification results indicates that the verification is failed, the smart lock cylinder 101 is controlled to remain closed.

[0095] In some embodiments, the alarm unit 106 may be a voice alarm unit 106 , and the alarm prompt information is voice prompt information.

[0096] In some embodiments, the alarm prompt information can also be information sent to the administrator of the smart face recognition door lock 10, etc.

[0097] In some embodiments, the controller 104 controls the specific control method of opening and closing the smart lock core 101. In combination with different application scenarios, different smart lock cores 101 can be flexibly changed and will not be introduced in detail here.

[0098] As can be seen from the description of the embodiments of this application, facial images to be verified are verified based on two databases; the first database stores trusted facial images, while the second database stores untrusted facial images, which are updated in real time. Thus, a comparison result indicating a match can be obtained based on the first database; a similarity comparison result can be obtained based on the second database. Based on these two comparison results, the final verification result is determined, ensuring the accuracy of the facial verification result. Furthermore, due to the integration of the two databases, the flexibility of facial recognition is also correspondingly enhanced. Furthermore, the smart lock cylinder 101 is controlled based on the verification results. Consequently, this control method and device can improve the accuracy and flexibility of the smart facial recognition door lock 10.

[0099] Please refer to Figure 4 , as Figure 1 To implement the control method shown in FIG, an embodiment of the present application provides a control device for an intelligent face recognition door lock, the control device comprising:

[0100] The control unit 401 is used to control the facial image acquisition unit to acquire the facial image to be verified when the detection unit detects that the target user is approaching the intelligent facial recognition door lock; the comparison unit 402 is used to compare the facial image to be verified with the first facial image in the first database to obtain a first comparison result; the first facial image is a preset trusted facial image, and the first comparison result is used to indicate whether there is a matching first facial image; the comparison unit 402 is also used to compare the facial image to be verified with the second facial image in the second database to obtain a second comparison result; the second facial image is a facial image obtained in real time from the target database, and the target database is used to update untrustworthy facial images in real time, and the second comparison result is used to indicate the similarity between the facial image to be verified and the second facial image; the control unit 401 is also used to determine the verification result based on the first comparison result and the second comparison result, and control the intelligent lock core based on the verification result.

[0101] In some embodiments, the control unit 401 is also used to: determine that the distance between the target user and the smart face recognition door lock is less than a preset distance, and output a voice prompt message; the voice prompt message is used to indicate whether to use face unlocking; when receiving the indication information of determining to use face unlocking, control the face image acquisition unit to collect the face image to be verified.

[0102] In some embodiments, the control unit 401 is further used to: control the facial image acquisition unit to acquire a first facial image to be verified under a first acquisition environment; the first acquisition environment includes a brightness parameter and a distance parameter; determine whether the image quality of the first facial image to be verified meets a preset quality standard; if so, control the facial image acquisition unit to acquire multiple facial images to be verified again based on the first acquisition environment, and determine the final facial image to be verified based on the multiple facial images to be verified; if not, determine a second acquisition environment based on the gap between the image quality and the preset quality standard, control the facial image acquisition unit to acquire multiple second facial images to be verified under the second acquisition environment, and determine the final facial image to be verified based on the multiple second facial images to be verified.

[0103] In some embodiments, the comparison unit 402 is further used to: determine a target first facial image from the first facial image; the average similarity between the target first facial image and the multiple facial images is greater than the first similarity; determine the maximum similarity and the minimum similarity between the target first facial image and the multiple facial images; determine a first integrated similarity based on a preset first similarity integration rule, the average similarity, the maximum similarity and the minimum similarity; if the first integrated similarity is greater than the second similarity, determine that there is a matching first facial image; wherein the second similarity is greater than the first similarity; if the first integrated similarity is less than the second similarity, determine that there is no matching first facial image.

[0104] In some embodiments, the preset first similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the maximum similarity and a preset adjustment value; wherein the preset adjustment value is determined based on the difference between the second similarity and the first similarity; if the difference between the average similarity and the maximum similarity is less than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the average similarity and the preset adjustment value; if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the first integrated similarity based on the maximum similarity and the minimum similarity.

[0105] In some embodiments, the comparison unit 402 is further used to: determine a target second facial image from the second facial image based on the number of verifications of the second facial image and a preset number of verifications; the number of verifications is used to represent the number of times the second facial image is compared with other facial images to be verified; determine the maximum similarity, minimum similarity and average similarity between the target second facial image and the multiple facial images; determine a second integrated similarity based on a preset second similarity integration rule, the average similarity, the maximum similarity and the minimum similarity; the second integrated similarity is the second comparison result.

[0106] In some embodiments, the preset second similarity integration rule includes: if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the maximum similarity and the minimum similarity; if the difference between the average similarity and the maximum similarity is less than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the average similarity; if the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, determining the second integrated similarity based on the maximum similarity and a preset adjustment value.

[0107] In some embodiments, the comparison unit 402 is further used to: if the first comparison result indicates that there is a matching first facial image, determine whether the similarity indicated by the second comparison result is greater than a first preset similarity; if so, determine that the verification result is verified to be passed, and the door cannot be unlocked directly; if not, determine that the verification result is verified to be passed, and the door can be unlocked directly; if the first comparison result indicates that there is no matching first facial image, determine whether the similarity indicated by the second comparison result is less than a second preset similarity; if so, determine that the verification result is verified to be failed, and re-verification is required; if not, determine that the verification result is verified to be failed, and an alarm prompt message needs to be output.

[0108] In some embodiments, the control unit 401 is further used to: if the verification result is that the verification is passed and the lock cannot be unlocked directly, control the fingerprint verification unit to determine the fingerprint verification result; control the smart lock core according to the fingerprint verification result; if the verification result is that the verification fails and re-verification is required, control the fingerprint verification unit to determine the fingerprint verification result; control the smart lock core according to the fingerprint verification result and the verification result; if the verification result is that the verification fails and an alarm prompt message needs to be output, control the smart lock core to remain closed, and control the alarm unit to output an alarm prompt message.

[0109] like Figure 5 As shown, an embodiment of the present application further provides a controller, including a processor 501 and a memory 502, wherein the processor 501 and the memory 502 are communicatively connected, and the controller can serve as the execution subject of the aforementioned control method.

[0110] The processor 501 and the memory 502 are electrically connected, directly or indirectly, to enable data transmission or interaction. For example, these components may be electrically connected via one or more communication buses or signal buses. The aforementioned control methods each include at least one software functional module that can be stored in the memory 502 in the form of software or firmware.

[0111] Processor 501 can be an integrated circuit chip with signal processing capabilities. Processor 501 can be a general-purpose processor, including a CPU (Central Processing Unit), an NP (Network Processor), etc.; it can also be a digital signal processor, an application-specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0112] The memory 502 can store various software programs and modules, such as the program instructions / modules corresponding to the image processing method and apparatus provided in the embodiments of the present invention. The processor 501 executes the software programs and modules stored in the memory 502 to perform various functional applications and data processing, thereby implementing the methods in the embodiments of the present application.

[0113] The memory 502 may include, but is not limited to, RAM (Random Access Memory), ROM (Read Only Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electric Erasable Programmable Read-Only Memory), etc.

[0114] I understand. Figure 5 The structure shown is only for reference. The controller may also include Figure 5More or fewer components than shown, or with Figure 5 Different configurations shown.

[0115] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0119] The foregoing descriptions of specific exemplary embodiments of the present application are for purposes of illustration and description. These descriptions are not intended to limit the present application to the precise forms disclosed, and it is apparent that many variations and modifications are possible in light of the foregoing teachings. The exemplary embodiments are selected and described for the purpose of explaining the specific principles of the present application and their practical application, thereby enabling those skilled in the art to realize and utilize the various exemplary embodiments of the present application and various options and modifications. The scope of the present application is intended to be defined by the claims and their equivalents.

Claims

1. A control method for an intelligent face recognition door lock, characterized in that: The intelligent face recognition door lock includes: an intelligent lock core, a detection unit and a face image acquisition unit, and the control method includes: When the detection unit detects that the target user is approaching the intelligent face recognition door lock, the face image acquisition unit is controlled to acquire the face image to be verified; Comparing the facial image to be verified with a first facial image in a first database to obtain a first comparison result; the first facial image is a preset trusted facial image, and the first comparison result is used to indicate whether there is a matching first facial image; comparing the facial image to be verified with a second facial image in a second database to obtain a second comparison result; the second facial image is a facial image obtained in real time from a target database, the target database being used to update untrustworthy facial images in real time; and the second comparison result is used to indicate a degree of similarity between the facial image to be verified and the second facial image; A verification result is determined according to the first comparison result and the second comparison result, and the smart lock core is controlled according to the verification result.

2. The control method according to claim 1, characterized in that: Before controlling the facial image acquisition unit to acquire the facial image to be verified, the control method further includes: Determining that the distance between the target user and the smart face recognition door lock is less than a preset distance, outputting a voice prompt message; the voice prompt message is used to indicate whether to use face unlocking; Correspondingly, controlling the facial image acquisition unit to acquire the facial image to be verified includes: When the indication information of determining to adopt face unlocking is received, the face image acquisition unit is controlled to acquire the face image to be verified.

3. The control method according to claim 1, wherein: The controlling the facial image acquisition unit to acquire the facial image to be verified comprises: Controlling the facial image acquisition unit to acquire a first facial image to be verified under a first acquisition environment; the first acquisition environment includes a brightness parameter and a distance parameter; Determining whether the image quality of the first face image to be verified meets a preset quality standard; If so, controlling the facial image acquisition unit to acquire multiple facial images to be verified again based on the first acquisition environment, and determining a final facial image to be verified based on the multiple facial images to be verified; If not, determine the second acquisition environment based on the gap between the image quality and the preset quality standard, control the facial image acquisition unit to acquire multiple second facial images to be verified under the second acquisition environment, and determine the final facial image to be verified based on the multiple second facial images to be verified.

4. The control method according to claim 1, wherein: The facial image to be verified includes multiple facial images, and comparing the facial image to be verified with a first facial image in a first database to obtain a first comparison result includes: Determining a target first facial image from the first facial image; wherein an average similarity between the target first facial image and the plurality of facial images is greater than a first similarity; Determining a maximum similarity and a minimum similarity between the target first facial image and the plurality of facial images; Determining a first integrated similarity according to a preset first similarity integration rule, the average similarity, the maximum similarity, and the minimum similarity; If the first integrated similarity is greater than the second similarity, determining that a matching first facial image exists; wherein the second similarity is greater than the first similarity; If the first integrated similarity is less than the second similarity, it is determined that there is no matching first facial image.

5. The control method according to claim 4, characterized in that: The preset first similarity integration rule includes: If the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the maximum similarity and a preset adjustment value; wherein the preset adjustment value is determined based on the difference between the second similarity and the first similarity; If the difference between the average similarity and the maximum similarity is less than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the first integrated similarity based on the average similarity and the preset adjustment value; If the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, the first integrated similarity is determined based on the maximum similarity and the minimum similarity.

6. The control method according to claim 1, characterized in that: The facial image to be verified includes multiple facial images, and the step of comparing the facial image to be verified with a second facial image in a second database to obtain a second comparison result includes: Determining a target second facial image from the second facial image based on the number of verifications of the second facial image and a preset number of verifications; the number of verifications representing the number of times the second facial image is compared with other facial images to be verified; Determining a maximum similarity, a minimum similarity, and an average similarity between the target second facial image and the plurality of facial images; A second integrated similarity is determined according to a preset second similarity integration rule, the average similarity, the maximum similarity, and the minimum similarity; the second integrated similarity is the second comparison result.

7. The control method according to claim 6, characterized in that: The preset second similarity integration rule includes: If the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is less than the preset difference, determining the second integrated similarity based on the maximum similarity and the minimum similarity; If the difference between the average similarity and the maximum similarity is smaller than a preset difference, and the difference between the average similarity and the minimum similarity is smaller than the preset difference, determining the second integrated similarity based on the average similarity; If the difference between the average similarity and the maximum similarity is greater than a preset difference, and the difference between the average similarity and the minimum similarity is greater than the preset difference, the second integrated similarity is determined based on the maximum similarity and a preset adjustment value.

8. The control method according to claim 1, characterized in that: The determining a verification result according to the first comparison result and the second comparison result includes: If the first comparison result indicates that there is a matching first facial image, determining whether the similarity indicated by the second comparison result is greater than a first preset similarity; if so, determining that the verification result is a passed verification and the door cannot be unlocked directly; if not, determining that the verification result is a passed verification and the door can be unlocked directly; If the first comparison result indicates that there is no matching first facial image, determine whether the similarity indicated by the second comparison result is less than a second preset similarity; if so, determine that the verification result is failed and needs to be verified again; if not, determine that the verification result is failed and needs to output an alarm prompt message.

9. The control method according to claim 8, characterized in that: The smart face recognition door lock further includes: a fingerprint verification unit and an alarm unit, and the smart lock core is controlled according to the verification result, including: If the verification result is that the verification is passed and the lock cannot be unlocked directly, control the fingerprint verification unit to determine the fingerprint verification result; and control the smart lock cylinder according to the fingerprint verification result; If the verification result is that the verification fails and re-verification is required, controlling the fingerprint verification unit to determine the fingerprint verification result; and controlling the smart lock cylinder according to the fingerprint verification result and the verification result; If the verification result is that the verification fails and an alarm prompt message needs to be output, the smart lock cylinder is controlled to remain closed, and the alarm unit is controlled to output an alarm prompt message.

10. A control device for an intelligent face recognition door lock, characterized in that: The intelligent face recognition door lock includes: an intelligent lock core, a detection unit and a face image acquisition unit, and the control device includes: A control unit, configured to control the facial image acquisition unit to acquire a facial image to be verified when the detection unit detects that the target user is approaching the intelligent facial recognition door lock; a comparing unit, configured to compare the facial image to be verified with a first facial image in a first database to obtain a first comparison result; the first facial image being a preset trusted facial image, and the first comparison result being used to indicate whether there is a matching first facial image; The comparison unit is further configured to compare the facial image to be verified with a second facial image in a second database to obtain a second comparison result; the second facial image is a facial image obtained in real time from a target database, the target database being used to update untrustworthy facial images in real time, and the second comparison result is used to indicate a degree of similarity between the facial image to be verified and the second facial image; The control unit is further configured to determine a verification result based on the first comparison result and the second comparison result, and control the smart lock core based on the verification result.

Images