Light supplement control method and device for multi-mode module, storage medium and computer equipment

Abstract

According to the light supplementing control method and device for the multi-mode module, the storage medium and the computer equipment, the distance between the to-be-recognized object and the module is detected firstly, and then whether the to-be-recognized image of the to-be-recognized object is obtained or not is determined, so that the recognition accuracy and efficiency are improved, and unnecessary energy consumption is effectively avoided. Meanwhile, whether the light supplement lamp is turned on or not is determined according to the recognition result, false triggering operation is effectively reduced, interference of the light supplement lamp on a close-range screen is avoided, unnecessary power consumption is reduced, and therefore the method and the device are particularly suitable for identity verification scenes needing high reliability. Besides, the biological characteristics are identified by adopting a biological identification algorithm, so that the identification accuracy and safety are improved, and the false triggering operation is further reduced.

Description

Technical Field

[0001] This application relates to the field of biometric technology, and in particular to a method, apparatus, storage medium and computer equipment for supplemental lighting control of a multimodal module. Background Technology

[0002] Currently, multimodal biometric terminals typically use supplementary lighting to illuminate the area when identifying biometric features. This process often employs fixed lighting, supplementary lighting control technology triggered by infrared distance sensors, or smart camera technology that combines image recognition with supplementary lighting control. Image algorithms can also be used to eliminate interference from the supplementary lighting on the QR code.

[0003] Existing technologies, such as fixed supplementary lighting, supplementary lighting control based on infrared distance sensors, or smart camera technology combining image recognition and supplementary lighting control, are prone to accidental triggering of the supplementary light. When the supplementary light shines on a screen at close range (such as a QR code display), it easily produces strong reflections, which interfere with the screen display content and cause QR code recognition failure. In addition, frequent activation of the supplementary light also causes unnecessary power consumption. Furthermore, existing technologies that use image algorithms to eliminate the interference of the supplementary light on QR codes are not very effective and have limitations in application scenarios. Summary of the Invention

[0004] The purpose of this application is to at least solve one of the above-mentioned technical defects, in particular the existing supplementary light control technology is prone to accidental triggering of the supplementary light, which leads to the inability to recognize the screen display content after it is interfered with. When using image algorithms to eliminate the interference of the supplementary light on the QR code, the elimination effect is not good and the application scenarios are limited.

[0005] This application provides a method for controlling supplemental lighting in a multimodal module, the method comprising:

[0006] When the distance between the object to be identified and this module is less than a preset distance threshold, the image of the object to be identified is acquired.

[0007] A preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained;

[0008] If the identification result indicates that the corresponding biometric feature has been identified, then the supplementary light is turned on;

[0009] If the identification result is that no corresponding biometric feature is identified, the supplementary light will not be turned on.

[0010] Optionally, when this module uses a near-infrared camera and a near-infrared fill light, acquiring the image of the object to be identified includes:

[0011] Turn on the near-infrared supplemental light;

[0012] Under the illumination of the near-infrared supplementary light, the infrared image captured by the near-infrared camera is obtained.

[0013] Optionally, the preset biometric algorithm is a palm vein detection algorithm or a palmprint detection algorithm;

[0014] The preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained, including:

[0015] The preset palm vein detection algorithm is activated to identify the palm vein features in the infrared image, and the identification result is obtained;

[0016] Alternatively, a preset palmprint detection algorithm can be activated to identify the palmprint in the infrared image and obtain the identification result.

[0017] Optionally, after the fill light is turned on, the system further includes:

[0018] The palm vein or palm print features in the infrared image are optimized.

[0019] Optionally, after the fill light is not turned on, the method further includes:

[0020] The non-palm vein or non-palm print features in the infrared image are optimized.

[0021] Optionally, when this module uses a color image camera, acquiring the image of the object to be identified includes:

[0022] Acquire the color image captured by the color image camera.

[0023] Optionally, the preset biometric algorithm is a palmprint detection algorithm;

[0024] The preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained, including:

[0025] The preset palmprint detection algorithm is activated to identify the palmprints in the color image, and the identification results are obtained.

[0026] Optionally, after the fill light is turned on, the system further includes:

[0027] The palm print features in the color image are optimized.

[0028] Optionally, after the fill light is not turned on, the method further includes:

[0029] The non-palmprint features in the color image are optimized.

[0030] Optionally, turning on the fill light includes:

[0031] The local exposure algorithm is invoked to detect the image brightness of a specified region in the image to be identified;

[0032] The illumination intensity of the fill light to be turned on is determined based on the image brightness.

[0033] Turn on the supplementary lighting according to the light intensity.

[0034] This application also provides a supplementary lighting control device for a multimodal module, including:

[0035] The image acquisition module is used to acquire the image of the object to be identified when the distance between the object to be identified and this module is less than a preset distance threshold.

[0036] The biometric module is used to activate a preset biometric algorithm to identify the biometric features in the image to be identified and obtain the identification result;

[0037] The supplementary light activation module is used to activate the supplementary light if the recognition result indicates that the corresponding biometric feature has been identified.

[0038] The supplementary light off module is used to prevent the supplementary light from being turned on if the recognition result is that no corresponding biometric feature is recognized.

[0039] This application also provides a computer-readable storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the supplementary lighting control method for the multimodal module as described in any of the above embodiments.

[0040] This application also provides a computer device, including: one or more processors, and memory;

[0041] The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the supplemental lighting control method for the multimodal module as described in any of the above embodiments.

[0042] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0043] The supplementary lighting control method, apparatus, storage medium, and computer equipment for multimodal modules provided in this application improve the accuracy and efficiency of recognition by first detecting the distance between the object to be identified and the module, and then deciding whether to acquire the image of the object to be identified. This also effectively avoids unnecessary energy consumption. Furthermore, this application determines whether to turn on the supplementary light based on the recognition result, which effectively reduces false triggering operations, avoids interference from the supplementary light on the screen at close range, and reduces unnecessary power consumption. Therefore, it is particularly suitable for identity verification scenarios requiring high reliability. In addition, this application improves the accuracy and security of recognition by using biometric algorithms to identify biometric features, thereby further reducing false triggering operations. Moreover, compared to eliminating interference from the supplementary light on the QR code through image algorithms later, the supplementary lighting control method of this application not only reduces computational costs and time delays but also can handle complex scenes and dynamically changing objects, thus having a wider range of applications. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart illustrating the supplementary lighting control method for a multimodal module provided in this application embodiment;

[0046] Figure 2 This is a schematic diagram illustrating the process of feature detection and optimization of infrared images provided in an embodiment of this application;

[0047] Figure 3 This is a schematic diagram illustrating the process of feature detection and optimization of a color image provided in an embodiment of this application;

[0048] Figure 4 A schematic diagram of the structure of a supplementary lighting control device for a multimodal module provided in this application embodiment;

[0049] Figure 5 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] In one embodiment, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating the supplementary lighting control method for a multimodal module provided in an embodiment of this application; this application provides a supplementary lighting control method for a multimodal module, the method including:

[0052] S110: When the distance between the object to be identified and this module is less than a preset distance threshold, the image of the object to be identified is acquired.

[0053] In this step, while the module is turned on, it can continuously detect whether there are any objects approaching the module. Once an object is detected, it can continuously receive the distance between the module and the object, and when the distance is less than a preset distance threshold, it can acquire the image to be identified corresponding to the object.

[0054] In this application, the multimodal module refers to a module integrating multiple biometric technologies, including but not limited to near-infrared cameras, color imaging cameras, and corresponding supplementary lighting. This module is designed to provide accurate, efficient, and secure identification services in scenarios requiring identity verification or biometric recognition. In specific applications, when the module detects an approaching object, it automatically initiates the corresponding identification process. The object to be identified in this application can be any entity requiring biometric recognition, including but not limited to human body parts (such as palms, fingers, and faces) or objects carrying biometric information (such as cards containing user biometric information, electronic device screens, etc.).

[0055] In practice, the distance between the object to be identified and the module can be detected in real time using various sensors, such as infrared distance sensors, ultrasonic sensors, or laser rangefinders. The preset distance threshold is a reasonable value pre-set based on the actual application scenario and requirements, used to determine whether the object to be identified is in a suitable location for biometric identification. Once the distance between the object to be identified and the module is detected to be less than the preset distance threshold, the module will automatically trigger an image acquisition device (such as a near-infrared camera or a color imaging camera) to acquire the image of the object to be identified, thereby providing the necessary image data for subsequent biometric identification and supplementary lighting control.

[0056] S120: Activate the preset biometric algorithm to identify the biometric features in the image to be identified and obtain the identification result.

[0057] In this step, after obtaining the image of the object to be identified through S110, this application can start a preset biometric algorithm to identify the biometric features in the image to be identified, and determine whether to turn on the supplementary light based on the identification result.

[0058] This application pre-configures a biometric algorithm within the module. This algorithm is used to identify biometric features requiring supplemental lighting, including but not limited to palm vein features, palmprint features, fingerprint features, and facial features. In specific implementations, the choice of biometric algorithm depends on the actual application scenario and requirements, as well as the characteristics of the object to be identified. For example, in scenarios requiring high-security authentication, a palm vein feature recognition algorithm can be used because palm vein features are unique and difficult to replicate, providing higher accuracy and security. In scenarios requiring high recognition speed, a palmprint feature recognition algorithm can be used because palmprint features are relatively easy to obtain and have a fast recognition speed. Facial feature recognition algorithms are suitable for scenarios requiring long-distance identification. Therefore, this application can configure one or more biometric algorithms according to actual needs, and at startup, the biometric algorithm to be activated is determined based on the content of the image to be identified; no restrictions are imposed here.

[0059] S130: If the recognition result is that the corresponding biometric feature has been identified, then turn on the supplementary light.

[0060] S140: If the identification result is that no corresponding biometric feature is identified, the supplementary light will not be turned on.

[0061] In the above steps, after the preset biometric algorithm is activated by S120 to identify the biometric features in the image to be identified and the identification result is obtained, this application can determine whether to turn on the supplementary light based on the identification result.

[0062] Specifically, after performing biometric identification on the image to be identified and obtaining the identification result, if the identification result is that the biometric features in the image to be identified, such as palm vein features or palm print features, are successfully identified, it indicates that the object to be identified is in a suitable location for biometric identification and its biometric features are clearly identifiable. At this time, in order to further improve the accuracy and efficiency of identification, this application will automatically turn on the supplementary light to enhance the image brightness of the object to be identified, making the biometric features more prominent and facilitating subsequent biometric comparison and verification.

[0063] If the identification result is that no corresponding biometric feature was detected, it indicates that the object to be identified may be in a location unsuitable for biometric identification, or the object may not possess the corresponding biometric feature, or its biometric feature may be affected by factors such as occlusion or blurring, resulting in inaccurate identification. In this case, to avoid unnecessary energy consumption and accidental triggering, this application will automatically turn off the supplementary light and not perform supplementary lighting operations. At the same time, this application can also optimize the acquired image to be identified according to specific circumstances, such as enhancing image contrast and sharpening image edges, to improve image quality and recognition accuracy.

[0064] By employing this supplementary lighting control method, this application can not only effectively avoid accidental triggering, reduce interference from the supplementary light to the screen at close range, and reduce unnecessary power consumption, but also improve the accuracy and efficiency of recognition, making it suitable for various scenarios requiring high-reliability identity verification.

[0065] In the above embodiments, by first detecting the distance between the object to be identified and the module, and then deciding whether to acquire the image of the object to be identified, the accuracy and efficiency of identification are improved, and unnecessary energy consumption is effectively avoided. Simultaneously, this application determines whether to turn on the supplementary light based on the identification result, which not only effectively reduces false triggering operations and avoids interference from the supplementary light on the screen at close range, but also reduces unnecessary power consumption. Therefore, it is particularly suitable for identity verification scenarios requiring high reliability. Furthermore, this application improves the accuracy and security of identification by using biometric algorithms to recognize biometric features, thereby further reducing false triggering operations. Moreover, compared to eliminating interference from the supplementary light on the QR code through image algorithms later, the supplementary light control method of this application not only reduces computational costs and time delays, but also can handle complex scenes and dynamically changing objects, thus having a wider range of applications.

[0066] In one embodiment, when this module uses a near-infrared camera and a near-infrared fill light, acquiring the image of the object to be identified in step S110 may include:

[0067] S111: Activate the near-infrared supplementary light.

[0068] S112: Under the illumination of the near-infrared supplementary light, acquire the infrared image captured by the near-infrared camera.

[0069] In this embodiment, because the functions of biometric terminals installed in different application scenarios vary, the component types of the multimodal modules in different biometric terminals also differ. For example, in some specific application scenarios, the multimodal module can be equipped with a near-infrared camera and a near-infrared illuminator to acquire infrared images of the object to be identified under near-infrared light. In this case, when the distance between the object to be identified and the module is detected to be less than a preset distance threshold, the module will first activate the near-infrared illuminator to provide sufficient light illumination for the object to be identified. Subsequently, under the illumination of the near-infrared illuminator, the module will use the near-infrared camera to acquire infrared images of the object to be identified.

[0070] It is understandable that the method of acquiring infrared images using a near-infrared camera in this application is not only suitable for well-lit environments, but also particularly suitable for nighttime or low-light environments, and can ensure that the quality of the acquired images meets the requirements of biometric recognition. Therefore, this acquisition method has a wide range of applications. Furthermore, the infrared images acquired by the near-infrared camera in this application can reflect the temperature distribution of the surface of the object to be identified, thereby highlighting biometric features such as palm veins and palm prints. By acquiring such infrared images, more accurate and reliable image data can be provided for subsequent biometric recognition. In practical implementation, the coordinated operation of the near-infrared camera and the near-infrared supplementary light enables this module to perform stable biometric recognition in various lighting environments, improving the accuracy and adaptability of the recognition.

[0071] In one embodiment, the preset biometric algorithm is a palm vein detection algorithm or a palmprint detection algorithm. In step S120, the preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result can include:

[0072] S121: Activate the preset palm vein detection algorithm to identify the palm vein features in the infrared image and obtain the identification result.

[0073] S122: Alternatively, activate the preset palmprint detection algorithm to identify the palmprint in the infrared image and obtain the identification result.

[0074] In this embodiment, this application provides two specific implementations of biometric algorithms to adapt to different application scenarios and needs. Specifically, when the multimodal module is equipped with a near-infrared camera and a near-infrared supplementary light, the palm vein detection algorithm can be preferentially used to identify palm vein features in the infrared image. Palm vein features, as a biometric feature within the human body, are unique and difficult to replicate, providing higher recognition accuracy and security. The infrared image acquired by the near-infrared camera clearly reflects the palm vein structure inside the palm of the object to be identified, thus facilitating accurate identification by the palm vein detection algorithm. If the recognition result is a successful identification of the palm vein features, it indicates that the object to be identified is in a suitable location for biometric identification, and its palm vein features are clearly identifiable. At this time, the supplementary light can be turned on to further enhance the image brightness, improving the accuracy and efficiency of the identification.

[0075] In addition, this application also provides a palmprint detection algorithm as another implementation method for biometrics. Palmprint features, as a biometric characteristic of the human body surface, are relatively easy to obtain and have a fast recognition speed, making them suitable for scenarios with high recognition speed requirements. When using a palmprint detection algorithm, recognition can also be performed using infrared images captured by a near-infrared camera. If the recognition result is a successful detection of the palmprint feature, a supplementary light can be turned on for illumination. However, if the recognition result is that the corresponding biometric feature is not detected, it indicates that the object to be identified may not possess the corresponding biometric feature, or that its biometric feature is affected by factors such as occlusion or blurring, resulting in inaccurate identification. In this case, to avoid unnecessary energy consumption and accidental triggering, the supplementary light can be turned off, and no illumination operation can be performed. Through this selection and implementation method of biometrics algorithm, this application can adapt to different application scenarios and needs, providing accurate, efficient, and secure biometric recognition services.

[0076] In one embodiment, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a process for feature detection and optimization of infrared images provided in an embodiment of this application; after the fill light is turned on, it may further include:

[0077] S151: Optimize the palm vein features or palm print features in the infrared image.

[0078] In this embodiment, after the supplementary lighting is turned on, to improve the accuracy and efficiency of biometric recognition, this application can further optimize the palm vein or palm print features in the infrared image. Specifically, the optimization process includes, but is not limited to, image enhancement, noise removal, and feature extraction steps to highlight the detailed information of the biometric features, reduce interference factors, and thus improve the accuracy and reliability of recognition. Through such optimization, this application can further improve the performance of biometric recognition, ensuring stable and accurate recognition services in various complex scenarios.

[0079] In one embodiment, the step of not turning on the fill light may further include:

[0080] S152: Optimize the non-palm vein features or non-palm print features in the infrared image.

[0081] In this embodiment, as Figure 2 As shown, to improve the flexibility and accuracy of subsequent image processing without turning on the supplementary light, this application can also optimize non-palm vein or non-palmprint features in the infrared image, such as QR codes or other objects that need to be identified. This optimization process may include, but is not limited to, image enhancement, contrast adjustment, and edge detection, aiming to improve image quality, highlight other possible biometric features or key information, and provide more valuable image data for subsequent analysis and recognition. Through this optimization strategy, this application can maintain effective image processing and recognition capabilities without turning on the supplementary light, enhancing the system's adaptability and robustness.

[0082] In one embodiment, when this module uses a color image camera, acquiring the image of the object to be identified in step S110 may include:

[0083] S211: Acquire the color image captured by the color image camera.

[0084] In this embodiment, when the multimodal module is equipped with a color image camera, it is used to acquire color images of the object to be identified. Unlike near-infrared cameras, color image cameras can operate in visible light, capturing images with rich colors and clear details. Therefore, in well-lit environments, this module can preferentially use the color image camera for image acquisition. Alternatively, if only a color image camera is available in this module, this application can acquire color images using that color image camera.

[0085] In practice, when the distance between the target object and the module is less than a preset distance threshold, the module will directly activate the color image camera to acquire a color image of the target object. Subsequently, the module will use a pre-set biometric algorithm to identify the biometric features in the color image. This biometric algorithm can be a palm vein detection algorithm, a palmprint detection algorithm, or a facial feature recognition algorithm, depending on the specific application scenario and requirements.

[0086] It is worth noting that because the images captured by the color imaging camera are rich in color and clear in detail, this module can more easily identify detailed information about biometric features during biometric recognition, thereby improving the accuracy and efficiency of the recognition. At the same time, color images can also provide more reference information for subsequent biometric comparison and verification, further enhancing the reliability of the recognition.

[0087] In summary, this application provides a multi-modal module illumination control method, achieving stable and accurate biometric recognition under different lighting conditions. Whether using a combination of a near-infrared camera and a near-infrared illuminator, or a color image camera alone, this application can flexibly select the optimal image acquisition and recognition method according to actual application scenarios and needs, providing users with efficient and secure identity verification services.

[0088] In one embodiment, the preset biometric algorithm is a palmprint detection algorithm.

[0089] In S120, a preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result can include:

[0090] S221: Activate the preset palmprint detection algorithm to identify the palmprint in the color image and obtain the identification result.

[0091] In this embodiment, when the multimodal module is equipped with a color image camera and a palmprint detection algorithm is selected for biometric recognition, the module uses the color image camera to acquire a color image of the object to be identified. Compared to infrared images, color images are richer in color and clearer in detail, making it easier for the palmprint detection algorithm to identify the detailed information of palmprint features. After the palmprint detection algorithm is started, it accurately identifies the palmprint features in the color image and outputs the recognition result. If the recognition result is that the palmprint features are successfully identified, it indicates that the object to be identified is in a suitable location for biometric recognition, and its palmprint features are clearly identifiable. At this time, the module will turn on the supplementary light to further enhance the image brightness, making the palmprint features more prominent, which is convenient for subsequent biometric comparison and verification. However, if the recognition result is that no palmprint features are identified, it indicates that the object to be identified may not have palmprint features, or its palmprint features may be affected by factors such as occlusion or blurring, making accurate identification impossible. In this case, the module will turn off the supplementary light to avoid unnecessary energy consumption and accidental triggering. Through this palmprint detection algorithm, this application can provide accurate and efficient palmprint feature recognition services in well-lit environments.

[0092] In one embodiment, such as Figure 3 As shown, Figure 3 This is a schematic diagram of a process for feature detection and optimization of a color image provided in an embodiment of this application; after turning on the fill light, it may further include:

[0093] S161: Optimize the palm print features in the color image.

[0094] In this embodiment, after turning on the supplementary light, to improve the accuracy and efficiency of palmprint feature recognition, this application can further optimize the palmprint features in the color image. Specifically, the optimization process includes, but is not limited to, image enhancement, color correction, and feature extraction steps, aiming to highlight the detailed information of the palmprint features, reduce interference factors, and thus improve the accuracy and reliability of recognition. Through such optimization, this application can further improve the performance of palmprint feature recognition, ensuring stable and accurate recognition services even in well-lit environments. This optimization strategy not only enhances the system's adaptability but also improves the user experience, making the identity verification process more efficient and convenient.

[0095] In one embodiment, the step of not turning on the fill light may further include:

[0096] S162: Optimize the non-palmprint features in the color image.

[0097] In this embodiment, as Figure 3As shown, to enhance the diversity and flexibility of subsequent image processing without turning on the fill light, this application can also optimize non-palmprint features in the color image. This optimization includes, but is not limited to, image enhancement, color balance adjustment, and detail sharpening, aiming to improve the overall image quality and highlight other possible biometric features or key information, such as QR codes, facial features, and finger contours. Such optimization not only helps improve the image's visualization effect but also provides more valuable image data for subsequent analysis and recognition. Through this strategy, this application can maintain effective image processing and recognition capabilities even without turning on the fill light, further enhancing the system's robustness and practicality.

[0098] In one embodiment, turning on the fill light in S130 may include:

[0099] S131: Call the local exposure algorithm to detect the image brightness of a specified area in the image to be identified.

[0100] S132: Determine the illumination intensity of the fill light to be turned on based on the image brightness.

[0101] S133: Turn on the supplementary light according to the light intensity.

[0102] In this embodiment, before turning on the fill light, the present application first detects the image brightness of a specified area in the image to be identified by calling a local exposure algorithm. This local exposure algorithm can be an AE (Auto Exposure) local exposure algorithm or other local exposure algorithms, and the choice is made according to the actual situation; no limitation is made here. The local exposure algorithm of this application can detect the brightness of a specific area in the image, thereby more accurately reflecting the brightness of that area and avoiding the inaccuracies and interference that may be caused by global exposure. Subsequently, based on the detected image brightness, the present application determines the illumination intensity of the fill light to be turned on.

[0103] Specifically, if the image brightness of a designated area is low, this application will correspondingly increase the illumination intensity of the supplementary light to ensure that the area receives sufficient light; conversely, if the image brightness of the designated area is already high enough, this application will appropriately reduce the illumination intensity of the supplementary light to avoid overexposure of the image or waste of energy due to excessive light. Through this method of determining illumination intensity, this application can flexibly adjust the brightness of the supplementary light to adapt to different lighting environments and recognition needs.

[0104] Finally, based on the determined light intensity, this application can precisely control the activation of the supplementary lighting, ensuring sufficient illumination while minimizing energy consumption and interference. This supplementary lighting control strategy not only improves the accuracy and efficiency of biometric identification but also enhances the system's energy efficiency and practicality, thereby providing users with a more efficient and secure identity verification service.

[0105] The supplementary lighting control device for the multimodal module provided in the embodiments of this application will be described below. The supplementary lighting control device for the multimodal module described below can be referred to in correspondence with the supplementary lighting control method for the multimodal module described above.

[0106] In one embodiment, such as Figure 4 As shown, Figure 4 This application provides a schematic diagram of the structure of a supplementary lighting control device for a multimodal module. The application also provides a supplementary lighting control device for a multimodal module, which may include an image acquisition module 210, a biometric identification module 220, a supplementary lighting activation module 230, and a supplementary lighting deactivation module 240, specifically including the following:

[0107] The image acquisition module 210 is used to acquire the image of the object to be identified when the distance between the object to be identified and the module is less than a preset distance threshold.

[0108] The biometric module 220 is used to activate a preset biometric algorithm to identify the biometric features in the image to be identified and obtain the identification result.

[0109] The supplementary light activation module 230 is used to activate the supplementary light if the recognition result indicates that the corresponding biometric feature has been identified.

[0110] The supplementary light off module 240 is used to prevent the supplementary light from being turned on if the recognition result is that no corresponding biometric feature is recognized.

[0111] In the above embodiments, by first detecting the distance between the object to be identified and the module, and then deciding whether to acquire the image of the object to be identified, the accuracy and efficiency of identification are improved, and unnecessary energy consumption is effectively avoided. Simultaneously, this application determines whether to turn on the supplementary light based on the identification result, which not only effectively reduces false triggering operations and avoids interference from the supplementary light on the screen at close range, but also reduces unnecessary power consumption. Therefore, it is particularly suitable for identity verification scenarios requiring high reliability. Furthermore, this application improves the accuracy and security of identification by using biometric algorithms to recognize biometric features, thereby further reducing false triggering operations. Moreover, compared to eliminating interference from the supplementary light on the QR code through image algorithms later, the supplementary light control method of this application not only reduces computational costs and time delays, but also can handle complex scenes and dynamically changing objects, thus having a wider range of applications.

[0112] In one embodiment, this application also provides a computer-readable storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the supplementary lighting control method for the multimodal module as described in any of the above embodiments.

[0113] In one embodiment, this application also provides a computer device, including: one or more processors, and memory.

[0114] The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the supplemental lighting control method for the multimodal module as described in any of the above embodiments.

[0115] Indicatively, such as Figure 5 As shown, Figure 5 This is a schematic diagram of the internal structure of a computer device 300 provided in an embodiment of this application. The computer device 300 can be provided as a server. (Refer to...) Figure 5 The computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions, such as application programs, that can be executed by the processing component 302. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 302 is configured to execute instructions to perform the supplemental lighting control method of the multimodal module in any of the above embodiments.

[0116] The computer device 300 may also include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate on an operating system stored in memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0117] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0119] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0120] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling supplemental lighting in a multimodal module, characterized in that, The method includes: When the distance between the object to be identified and this module is less than a preset distance threshold, the image of the object to be identified is acquired. A preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained; If the identification result indicates that the corresponding biometric feature has been identified, then the supplementary light is turned on; If the identification result is that no corresponding biometric feature is identified, the supplementary light will not be turned on.

2. The supplementary lighting control method for a multi-modal module according to claim 1, characterized in that, When this module uses a near-infrared camera and a near-infrared fill light, acquiring the image of the object to be identified includes: Turn on the near-infrared supplemental light; Under the illumination of the near-infrared supplementary light, the infrared image captured by the near-infrared camera is obtained.

3. The supplementary lighting control method for a multi-modal module according to claim 2, characterized in that, The preset biometric algorithm is a palm vein detection algorithm or a palmprint detection algorithm; The preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained, including: The preset palm vein detection algorithm is activated to identify the palm vein features in the infrared image, and the identification result is obtained; Alternatively, a preset palmprint detection algorithm can be activated to identify the palmprint in the infrared image and obtain the identification result.

4. The supplementary lighting control method for a multi-modal module according to claim 3, characterized in that, After turning on the fill light, it also includes: The palm vein or palm print features in the infrared image are optimized.

5. The supplementary lighting control method for a multimodal module according to claim 3, characterized in that, The method of not turning on the fill light also includes: The non-palm vein or non-palm print features in the infrared image are optimized.

6. The supplementary lighting control method for a multi-modal module according to claim 1, characterized in that, When this module uses a color image camera, acquiring the image of the object to be identified includes: Acquire the color image captured by the color image camera.

7. The supplementary lighting control method for a multimodal module according to claim 6, characterized in that, The preset biometric algorithm is a palmprint detection algorithm; The preset biometric algorithm is activated to identify the biometric features in the image to be identified, and the identification result is obtained, including: The preset palmprint detection algorithm is activated to identify the palmprints in the color image, and the identification results are obtained.

8. The supplementary lighting control method for a multimodal module according to claim 7, characterized in that, After turning on the fill light, it also includes: The palm print features in the color image are optimized.

9. The supplementary lighting control method for a multimodal module according to claim 7, characterized in that, The method of not turning on the fill light also includes: The non-palmprint features in the color image are optimized.

10. The supplementary lighting control method for a multimodal module according to any one of claims 1-9, characterized in that, Turning on the fill light includes: The local exposure algorithm is invoked to detect the image brightness of a specified region in the image to be identified; The illumination intensity of the fill light to be turned on is determined based on the image brightness. Turn on the supplementary lighting according to the light intensity.

11. A supplementary lighting control device for a multi-modal module, characterized in that, include: The image acquisition module is used to acquire the image of the object to be identified when the distance between the object to be identified and this module is less than a preset distance threshold. The biometric module is used to activate a preset biometric algorithm to identify the biometric features in the image to be identified and obtain the identification result; The supplementary light activation module is used to activate the supplementary light if the recognition result indicates that the corresponding biometric feature has been identified. The supplementary light off module is used to prevent the supplementary light from being turned on if the recognition result is that no corresponding biometric feature is recognized.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the supplemental lighting control method for the multimodal module as described in any one of claims 1 to 10.

13. A computer device, characterized in that, include: One or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the supplemental lighting control method for the multimodal module as described in any one of claims 1 to 10.

Images