Intelligent lock control method and device based on image recognition and electronic equipment

Abstract

The invention discloses an intelligent lock control method and device based on image recognition and electronic device.The intelligent lock control method based on image recognition comprises the steps that a first mode image is obtained through a first recognition module, image preprocessing is conducted on the first mode image, and a first preprocessed image is obtained; if the first pre-processed image is an image with unknown features, performing unknown reason analysis on the image with unknown features; if the reason analysis result is that the lens is shielded, recording shielding position information corresponding to the shielding, and confirming a camera type corresponding to the shielding position information; if the first recognition module is a face module and the camera type is a near-infrared camera, sending a recognition module switching instruction; and performing feature recognition on the third mode feature, and confirming the unlocking of the intelligent lock according to a feature recognition result. According to the method, the anti-interference capability of the system is enhanced, the identification effectiveness and timeliness of biological characteristics are improved, and the identification stability of the system is kept.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a smart lock control method, device and electronic equipment based on image recognition. Background Art

[0002] As smart homes become increasingly popular, smart door locks are becoming more and more popular as the first line of defense for access safety. Among the smart door lock authentication methods, facial recognition and palm vein recognition are among the more secure ones. Among them, 3D facial recognition technology is to collect rich facial information, such as facial shape, texture, depth, etc., with higher accuracy, so as to compare information with pre-stored facial information; palm vein recognition technology uses near-infrared rays to illuminate the palm, and the sensor senses the light reflected by the palm. The key is that the hemoglobin in the red blood cells flowing into the veins will absorb near-infrared rays near the wavelength of 760nm, resulting in less reflection in the vein part. The strength of the reflected near-infrared rays is used to identify the location of the veins and generate a vein pattern on the image. Then the read vein data is compared with the pre-stored palm vein data for identification.

[0003] In 3D face recognition system or palm vein recognition system, face or palm vein recognition can usually be realized simultaneously through a camera module composed of the same set of cameras and near-infrared lamps. The camera module is usually placed in the transparent panel area on the lock body for protection, and the transparent panel area is inevitably stained with water droplets or dirt, which affects the shooting effect of the camera module and interferes with the accuracy and effectiveness of face or palm vein recognition. Summary of the invention

[0004] The embodiments of the present invention provide a smart lock control method, device and electronic device based on image recognition to solve the problem that a camera module is generally arranged in a transparent panel area on the lock body for protection, and the transparent panel area is inevitably stained with water droplets or dirt, thereby affecting the shooting effect of the camera module and interfering with the accuracy and effectiveness of face or palm vein recognition.

[0005] A smart lock control method based on image recognition, comprising: A first pattern image is acquired through a first recognition module, and image preprocessing is performed on the first pattern image to acquire a first preprocessed image, wherein the first recognition module is any one of a face module or a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module; If the first preprocessed image is an image with unknown features, performing an unknown cause analysis on the image with unknown features to obtain a cause analysis result; If the cause analysis result is that the lens is blocked, the blocking position information corresponding to the blocking is recorded, and the camera type corresponding to the blocking position information is confirmed to determine whether it affects the second recognition module; If the first recognition module is a face module and the camera type is a near infrared camera, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; Perform feature recognition on the third mode feature, obtain feature recognition results, and confirm the opening of the smart lock based on the feature recognition results.

[0006] An intelligent lock control device based on image recognition, comprising: A first pre-processed image acquisition module, used to acquire a first pattern image through a first recognition module, perform image pre-processing on the first pattern image, and acquire a first pre-processed image, wherein the first recognition module is any one of a face module or a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module; a cause analysis result acquisition module, configured to perform an unknown cause analysis on the image with unknown features to obtain a cause analysis result if the first preprocessed image is an image with unknown features; A camera type confirmation module, for recording the occlusion position information corresponding to the occlusion if the cause analysis result shows that the lens is blocked, and confirming the camera type corresponding to the occlusion position information, so as to confirm whether it affects the second recognition module; An instruction sending module, used for sending a switching identification module instruction if the first identification module is a face module and the camera type is a near infrared camera, so as to receive a third mode feature input by the user through any one of the other identification modules as a third identification module; The feature recognition result acquisition module is used to perform feature recognition on the third mode feature, obtain the feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

[0007] An electronic device, comprising: a microprocessor supporting at least two biometric feature recognitions, and a functional module electrically connected to the microprocessor, the functional module comprising: a camera module, an infrared lighting source, a face module, a palm vein module, a distance sensing module, a light sensing module, a memory module, an Ethernet communication module, a speaker, an electromagnetic lock control module, and a power supply module, the Ethernet communication module being connected to a remote control terminal via Ethernet; A memory module is used to store preset feature data of at least two types of biometric identification and a computer program in the memory module that can be run on a microprocessor. When the computer program is executed by the microprocessor, the above-mentioned smart lock control method based on image recognition is implemented; the microprocessor controls the camera module and the near-infrared light emitting tube to identify the face or palm vein.

[0008] The light-sensitive sensor module is used to detect ambient light information and send the ambient light information to the microprocessor, so that the microprocessor switches the working mode of the camera in the camera module according to the ambient light information; The camera module is arranged at the lower side of the transparent panel, including at least one visible light camera and at least one near infrared camera, and a visible light filter is embedded in the transparent panel; at least two near infrared light emitting tubes are evenly distributed around each camera, and at least one near infrared light emitting tube is evenly distributed between every two cameras, and the near infrared light emitting tube is used to provide infrared fill light function for the camera in the camera module; The above-mentioned smart lock control method, device and electronic device based on image recognition can promptly analyze the causes of biometric images obtained during shooting that do not meet the recognition requirements, and can promptly switch to other effective biometric recognition modes when it is determined that the camera is obstructed, such as by dirt. This enhances the anti-interference ability of the system while improving the effectiveness and timeliness of biometric recognition and maintaining the recognition stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0010] Figure 1 A schematic diagram of an application environment of a smart lock control method based on image recognition in one embodiment of the present invention is depicted; Figure 2 A first flow chart of a smart lock control method based on image recognition in a first embodiment of the present invention is shown; Figure 3 A schematic diagram of a smart lock of a smart lock control method based on image recognition in a first embodiment of the present invention is shown; Figure 4 A second flow chart of a smart lock control method based on image recognition in one embodiment of the present invention is shown; Figure 5 A schematic diagram of a first pre-processed image with dirt captured by a camera in a smart lock control method based on image recognition in a first embodiment of the present invention is shown; Figure 6 A third flow chart of a smart lock control method based on image recognition in a fourth embodiment of the present invention is shown; Figure 7 A fourth flow chart of a smart lock control method based on image recognition in a seventh embodiment of the present invention is shown; Figure 8 A schematic diagram of an intelligent lock control device based on image recognition in an eighth embodiment of the present invention is shown; Fig. 9 A schematic diagram of an electronic device according to an embodiment of the present invention is shown.

[0011] Description of reference numerals: 10. Visible light camera; 20. Near infrared camera; 30. Infrared lighting source. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] The smart lock control method based on image recognition provided by the embodiment of the present invention can be applied in Figure 1 In the application environment, the smart lock control method based on image recognition is applied in the smart lock control system based on image recognition, and the smart lock control system based on image recognition includes a smart lock and a remote control terminal, wherein the smart lock communicates with the remote control terminal, including various forms of smart terminals, such as mobile phones or smart watches, through the network to realize remote control unlocking of the smart lock. The smart lock determines whether the user's characteristics match the preset biometric characteristics by performing biometric identification on the user, thereby controlling the opening and closing of the door lock through the electromagnetic lock control module. The smart lock can be mainly used in smart home environments, especially in various places that require access control, such as residences, offices, hotels, etc., and can significantly improve the recognition accuracy of smart locks in various environments. The remote control terminal can be implemented with an independent remote control terminal, such as a mobile terminal or a remote control terminal cluster composed of multiple remote control terminals.

[0014] Concept explanation: 3D face recognition: 3D structured light recognition is a stereoscopic imaging through a 3D camera module, which can identify the three-dimensional coordinate information of each point in the field of view, so that the computer can obtain the 3D data of the space and restore the complete three-dimensional world, and realize various intelligent three-dimensional positioning. Among them, the 3D camera module includes a built-in speckle projector, a visible light camera (RGB camera) for obtaining 2D information of the face, a near-infrared camera for global exposure, and an infrared lighting source. The principle of 3D face recognition is to use a near-infrared light projector to emit about 30,000 infrared structured light points onto the photographed object. The wavelength of the near-infrared light used is 700-2526nm, so that the brightness of a specific lighting area or a specific visual target is much higher than that of other targets and surrounding areas. The near-infrared camera collects the face depth information, and then the face 2D information and face depth information are superimposed through calculation and processed into face 3D information.

[0015] Palm vein recognition: Palm vein recognition uses the property of hemoglobin in the blood to absorb near-infrared light, and uses a near-infrared camera to obtain vein images under near-infrared light. Light with a wavelength between 750nm and 1000nm can penetrate the human epidermis better. The oxygenated hemoglobin and reduced hemoglobin in the blood have a relatively high absorption rate for near-infrared light in the wavelength range of 750nm to 1000nm, while the water in the human tissue has a relatively low absorption rate in this wavelength range. Therefore, under the irradiation of near-infrared light, the palm vein part will appear dark due to the absorption of more light, while other tissue cells in the palm will appear bright due to the reflection of water, thus obtaining a clear palm vein image with unique personal characteristics. Palm veins grow under the epidermis of the human body and cannot be directly observed under visible light conditions.

[0016] Embodiment 1 like Figure 2 As shown, a smart lock control method based on image recognition is provided, and the method is applied in Figure 1 The microprocessor of the smart lock in FIG. 1 is used as an example to illustrate the specific steps including: S110. Acquire a first pattern image through a first recognition module, perform image preprocessing on the first pattern image, and acquire a first preprocessed image, wherein the first recognition module is any one of a face module and a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module.

[0017] Specifically, the face module is a module for realizing face feature recognition, and may include a visible light camera 10, a near infrared camera 20, and an infrared illumination source 30; the palm vein module is a module for realizing palm vein feature recognition, and includes a near infrared camera 20 and an infrared illumination source 30, and the infrared illumination source 30 may specifically include a near infrared light emitting tube. At least two near infrared light emitting tubes are distributed near each camera, and at least one near infrared light emitting tube is evenly distributed between two cameras, and the near infrared light emitting tube is used to provide infrared fill light function for the camera.

[0018] Because both the face module and the palm vein module include a near infrared camera 20 and an infrared illumination source 30, and the face module has an additional visible light camera 10 compared to the palm vein module. In order to save production costs, most manufacturers generally set up a common near infrared camera 20 and infrared illumination source 30 when implementing the two recognition modes, such as Figure 3 As shown, a visible light camera 10 for face recognition is additionally provided. By such a configuration, the manufacturer can realize dual recognition of face mode and palm vein mode through a relatively simple and relatively low-cost architecture.

[0019] The difference between the two is that the effective distance of face recognition is mainly affected by the camera resolution, algorithm optimization and specific application scenarios. In a 1:1 scenario at a short distance (such as within 0.4 meters to 1 meter, especially 0.4~0.8 meters in front of the camera), the accuracy of face recognition is high. However, with the increase of recognition distance, the decrease of distance and the increase of the number of face databases, the accuracy of face recognition will gradually decrease; while the effective distance of palm vein recognition is generally between 5~20 centimeters. This recognition method is not only convenient and easy to use, but also highly safe and hygienic. Palm vein recognition performs identity authentication by capturing the venous blood vessel image on the surface of the palm. Since each person's palm vein characteristics are unique, this recognition method has high accuracy and reliability.

[0020] Therefore, when a shared camera is used to distinguish whether the biometric feature is a face or a palm vein, a distance determination method or an image pattern feature confirmation method can be used for determination. Currently, after a distance sensor is generally used to confirm the feature of the target biometric feature, a camera is used to capture a biometric feature image of the target biometric feature, such as a face feature image or a palm vein feature image.

[0021] When the face module is used as the first recognition module, the palm vein module is used as the second recognition module; correspondingly, when the palm vein module is used as the first recognition module, the face recognition module is used as the second recognition module.

[0022] The first mode image is a biometric feature image captured by a camera of the first recognition module, and is a facial feature image or a palm vein feature image.

[0023] The first preprocessing of the image is to remove the information that interferes with the image in the color image captured by the camera and reduce the amount of calculation. Before extracting the characteristic values ​​such as correlation coefficient, edge information, frequency domain energy, etc., the image is grayed and denoised to highlight the useful information to form a preliminary feature image, which facilitates the subsequent analysis and calculation of the feature image and achieves faster and more accurate results.

[0024] Furthermore, feature extraction of the first mode image first requires determining whether the image meets the feature significance standard. It is understandable that if the captured biometric features are interfered by environmental factors or hardware factors, it is difficult to extract sufficient feature information that meets the matching requirements from the captured image, that is, when the first mode image does not meet the feature significance standard, the first pre-processed image becomes a feature-unclear image, and feature matching cannot be continued. At this time, the user should be promptly reminded to switch the biometric input mode.

[0025] Furthermore, environmental factors include dim light, etc., hardware factors include defects in the camera, or obstructions on the transparent panel corresponding to the camera, and factors that constitute obstruction include: water drops, dirt or oil stains, etc.

[0026] Preferably, the smart lock control method based on image recognition provided in this embodiment, after step S110, as Figure 4 As shown, after obtaining the first preprocessed image, the following steps are specifically included: S1101. If the first preprocessed image is a feature-clear image, feature recognition is performed based on the feature-clear image, a feature recognition result is obtained, and the opening of the smart lock is confirmed based on the feature recognition result.

[0027] Specifically, the feature-clear image is a first pattern image captured by the system that meets the requirements for feature extraction in terms of clarity, illumination and other dimensions, and a feature recognition result that meets the comparison requirements can be extracted through the first pattern image.

[0028] It can be understood that when the first preprocessed image is a feature-clear image, the comparison of facial or palm vein features can be carried out smoothly, and the opening of the smart lock can be quickly confirmed through the feature recognition result.

[0029] S120. If the first preprocessed image is an image with unknown features, perform an unknown cause analysis on the image with unknown features to obtain a cause analysis result.

[0030] Specifically, the feature-unclear image is an image in which the biometric information carried by the first mode image does not meet the feature significance standard. At this time, the present embodiment can continue to perform the unknown cause analysis based on the feature-unclear image, that is, to confirm what factors cause the feature to be unknown, and the analysis result, such as lens occlusion or dim light, is the cause analysis result.

[0031] The image recognition-based smart lock control method provided in this embodiment can continue to perform unknown cause analysis on the image with unknown features when the first preprocessed image is an image with unknown features, instead of immediately reminding the user to switch the recognition mode when the image is an image with unknown features. By obtaining the cause analysis results, the user can be more efficiently reminded which recognition mode to switch to, avoiding the use of invalid feature recognition modes again.

[0032] S130. If the cause analysis result is that the lens is blocked, the blocking position information corresponding to the blocking is recorded, and the camera type corresponding to the blocking position information is confirmed, so as to determine whether it affects the second recognition module.

[0033] Specifically, the face module and palm vein module provided in this embodiment share a near-infrared camera and an infrared illumination source. When there is dirt on the near-infrared camera, both modules cannot extract features. In the first pre-processed image with dirt, a lot of information is difficult to recognize, and although the area of ​​mud on the transparent panel is very small, in the first pre-processed image captured by the camera, the area covered by dirt such as mud occupies a large part of the image area, seriously affecting the image clarity, such as Figure 5 shown.

[0034] If only the visible light camera of the face module is dirty, it will not affect the face module recognition. If the face module recognition fails, the system can prompt the user to continue the identity authentication in palm vein recognition mode, or the user can switch to other authentication methods according to their own preferences, such as fingerprint recognition, palm print recognition, password input or NFC card authentication.

[0035] This embodiment can use an image edge information algorithm to extract the pixel position of the obstruction such as water droplets or dirt on the image, that is, the obstruction position information. Image edge information is very important information of the image. It is generally believed that the edge of the object in the image is the area where the gray value changes. The change of the gray value in the tangential direction of the edge is relatively gentle, and the change of the gray value in the normal direction of the edge is relatively drastic. At the same time, the edge information of the image can also represent the change of the image depth.

[0036] When the user stands in front of the camera module, the depth of field in front of the camera module is large, the depth information is richer, and the area with depth changes has more edge information, so the image quality can be evaluated using the edge information of the image. When the lens surface is clean, the image captured by the camera is clearer and sharper, and the image contains more edge information. When the lens surface is covered with dirt, it is more difficult to distinguish the object from the image, and no edge information can be detected in the area covered by the dirt, and the edge information of the entire image is also less.

[0037] In this embodiment, a convolution operator can be used to perform convolution operation on the image to extract the image edge. The first-order operator can be one of the Robert operator, the Prewitt operator and the Sobel operator. The image sequence convolution operation is performed on the images taken by all cameras (including images without dirt and images with dirt), and the edge information in the image sequence without dirt and the dirty image sequence can be extracted to obtain the image edge information image. The edge information contained in the image sequence without dirt is more than the edge information in the dirty image sequence. The edge information in the image can be used as a basis for judging whether the lens surface is dirty. If it is detected that the edge information of the image has been at a low value or suddenly decreases, the camera surface is likely to be contaminated.

[0038] The image with more edge information and more obvious edges of faces or palm veins is identified as a clear image, that is, there is no dirty image; The image edge positions where there is less edge information, especially in the area covered by dirt and where almost no edge information can be extracted, are recorded as occlusion position information.

[0039] The location information can be used to infer the target camera corresponding to the shooting of the first mode image, and confirm whether the target camera is a near-infrared camera or a visible light camera.

[0040] S140. If the first recognition module is a face module and the camera type is a near infrared camera, send a recognition module switching instruction to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module.

[0041] Specifically, this embodiment discusses the situation when the first recognition module is a face module and the camera type is a near-infrared camera. At this time, the second recognition module is a palm vein module. As can be seen from the above, when the shared near-infrared camera is blocked, the imaging of the face module and the palm vein module is affected. At this time, this embodiment can prompt the user to switch to the third mode feature in addition to the face recognition and palm vein recognition modes through prompts. During the day, it can be a text prompt on the display interface and a voice prompt. At night, it can only be a text prompt on the interface of the smart lock to prompt the user to switch to the third mode feature in addition to the face recognition and palm vein recognition modes. The third mode feature can be confirmed according to the user's current input, such as fingerprint mode features, palm print mode features, password input, NFC wireless signal, Bluetooth wireless signal or terminal remote control signal light.

[0042] The image recognition-based smart lock control method provided in this embodiment can promptly remind the user to switch to the effective third mode feature, thereby preventing the user from repeatedly inputting unrecognizable features, thereby affecting the recognition efficiency.

[0043] S150. Perform feature recognition on the third mode feature, obtain the feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

[0044] Specifically, this embodiment can perform feature recognition based on the third mode feature input by the user to obtain a feature recognition result. When the input third mode feature matches the preset third biometric feature stored in the smart lock, it can be confirmed that the user is an authorized user, and an opening signal can be sent to the electromagnetic lock control module of the smart lock to open the smart lock.

[0045] The image recognition-based smart lock control method provided in this embodiment can promptly analyze the causes of biometric images obtained during shooting that do not meet the recognition requirements, and can promptly switch to other effective biometric recognition modes when it is determined that the camera is obstructed, such as by dirt. This enhances the anti-interference ability of the system while improving the effectiveness and timeliness of biometric recognition and maintaining the recognition stability of the system.

[0046] Embodiment 2 The smart lock control method based on image recognition provided in this embodiment, after step S130, as Figure 4 As shown, after confirming the camera type corresponding to the occlusion position information, the following steps are specifically included: S1301. If the first recognition module is a face module and the camera type is a visible light camera, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module.

[0047] S1302. If the first recognition module is a palm vein module and the camera type is a near infrared camera, a switch recognition module instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module.

[0048] S1303. Perform feature recognition on the third mode feature or the second mode feature, obtain the feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

[0049] Specifically, when the first recognition module is a face module and the camera type is a visible light camera, that is, when the occlusion exists in the visible light camera, it affects the face module recognition but has no effect on the palm vein recognition. At this time, the palm vein module as the second recognition module can continue to perform pattern recognition. In this embodiment, the user can be prompted to switch to the second mode feature and the third mode feature except face recognition through prompts. During the day, the prompts can be both text prompts on the display interface and voice prompts. At night, the prompts can be only text prompts on the interface of the smart lock to prompt the user to switch to the second mode feature and the third mode feature except face recognition. The third mode feature can be confirmed according to the user's current input, such as fingerprint mode features, palm print mode features, password input, NFC wireless signal, Bluetooth wireless signal or terminal remote control signal light.

[0050] When the first recognition module is a palm vein module and the camera type is a near-infrared camera, that is, at this time, occlusion exists in the near-infrared camera, which affects both the face module recognition and the palm vein recognition. At this time, the face module as the second recognition module cannot continue to perform pattern recognition. This embodiment can prompt the user to switch to the third mode feature in addition to face recognition and palm vein recognition, perform feature extraction and feature comparison, and thus control the opening of the smart lock.

[0051] There is no situation where the first recognition module is a palm vein module and the camera type is a visible light camera, because the palm vein module only activates the near-infrared camera. Therefore, this situation does not need to be discussed.

[0052] The implementation process of 3D face recognition generally requires four steps: face image acquisition and detection, face image preprocessing, face image feature extraction, and face image matching and recognition.

[0053] 1. Face image acquisition and detection: Record the image in the form of static or dynamic images through a camera as a pattern image, and determine the position and size of the face through face detection. Specifically, the Adaboost face detection algorithm can be used to detect the position and image information of the front face based on integral graph, cascade detector and Adaboost algorithm.

[0054] 2. Face image preprocessing: Due to the different factors such as the location and light of the image acquisition, the quality of the image also varies greatly. Image preprocessing can remove information that interferes with the image, improve the quality of the image, highlight useful information as a feature-defined image, and facilitate the subsequent analysis and calculation of the feature image.

[0055] 3. Face image feature extraction: By analyzing and calculating the feature-defined image after preprocessing, the facial features of the person in the image, such as the nose, eyes, chin, mouth, etc., are extracted. The positional relationship between these features is calculated, and the geometric features between them are used as the feature information to be compared for face recognition.

[0056] 4. Face image matching and recognition: Search and compare the feature information to be compared with the user image information stored in its own database. When the matching degree between the two reaches the matching threshold, the user information can be confirmed to achieve the purpose of unlocking.

[0057] The implementation process of palm vein recognition generally requires four steps: palm vein image acquisition and detection, palm vein image preprocessing, palm vein image feature extraction, and palm vein image matching and recognition.

[0058] 1. Palm vein image acquisition and detection: Record the image as a pattern image in the form of static images, dynamic images, etc. through a camera or other means. When acquiring palm vein images, the hand does not need to touch the device, and the recognition can be completed by gently placing it. In this way, the hand does not need to touch the device, and it will not be unrecognizable due to contamination by dirt on the hand, and the influence of external factors such as temperature can be ignored.

[0059] 2. Palm vein image preprocessing: Due to the different factors such as the location and light of the image acquisition, the quality of the image also varies greatly. The purpose of image preprocessing is mainly to remove information that interferes with the image, improve the quality of the image, and highlight the useful information as a feature-clear image. Preprocessing includes vein segmentation, smoothing, vein thinning, and burr trimming to obtain a feature-clear image that meets the comparison standards.

[0060] 3. Palm vein image feature extraction: By analyzing and calculating the feature-defined image after preprocessing, the feature information of the palm vein in the image to be compared is extracted, such as the moment feature vector of the vein skeleton.

[0061] 4. Palm vein image matching and recognition: Use feature matching algorithms, such as support vector machines, to search and compare the feature information to be matched with the user image information stored in its own database. When the matching degree between the two reaches a certain ratio, the user information can be confirmed and the purpose of unlocking can be achieved.

[0062] Embodiment 3 The smart lock control method based on image recognition provided in this embodiment further specifically includes the following steps after step S140, that is, after sending the instruction to switch the recognition module: S1401. Send a panel cleaning instruction to clean the transparent panel corresponding to the near-infrared camera.

[0063] Specifically, the panel cleaning instruction is an instruction to notify the system or user to clean the lens. If the system carries a self-cleaning mechanism, the self-cleaning operation can be started based on the panel cleaning instruction. If the system prompts, it can be a text prompt on the display interface and a voice prompt during the day, and at night it can only be a text prompt on the smart lock interface to prompt the user to clean the specific target lens with dirty obstructions, so as to restore the normal use of the smart lock face mode and palm vein mode.

[0064] S1402. After a preset cleaning waiting time, determine the information change result of the shielding position information.

[0065] Specifically, machine cleaning or manual cleaning requires a certain amount of time. This application can capture images of the target lens that was previously dirty by waiting for the time to clean the camera, that is, after the preset cleaning waiting time, to confirm whether the dirt at the occlusion has been effectively cleaned, that is, whether the image at the occlusion position has changed. The information change results include no change in position and reduced position information. The reduced position information can be less than the original occlusion position information or no occlusion position information. Less than the original occlusion position information indicates that the dirt on the target lens has not been completely cleaned. At this time, if the biometric feature can be captured, it will not affect the face or palm vein recognition mode. It depends on whether the first mode feature captured by the lens matches the preset first feature.

[0066] S1403. If the information change result is a decrease in position information, repeat the step of using the first recognition module to acquire the first pattern image.

[0067] Specifically, the determination process of the information change result includes: obtaining the occlusion position information corresponding to the current image as the second position information by continuing to shoot the current image through the target camera corresponding to the dirt. Taking the occlusion position information corresponding to the feature unknown image as the first position information, comparing whether the second position information is smaller than the first position information, when the second position information is smaller than the first position information, it indicates that the area of ​​the polluted area is reduced.

[0068] S1404. If the information change result is that the position information does not change, then send a repair information to the remote control terminal, the repair information including the blocked position information.

[0069] Specifically, when the information change result is that the position information remains unchanged, it means that the dirt has not been effectively removed. There may be a problem with the internal hardware of the camera at the lens. At this time, it is necessary to send a repair information to the remote control end so that maintenance personnel can promptly confirm the specific location of the hardware damage based on the obstructed position information to improve maintenance efficiency.

[0070] Embodiment 4 The smart lock control method based on image recognition provided in this embodiment, after step S120, that is, after obtaining the cause analysis result, as shown in FIG. Figure 4 and Figure 6 As shown, it also specifically includes the following steps: S1201. If the cause analysis result is that the lens light is insufficient, the light source position information corresponding to the insufficient light source is recorded, and the infrared light source position corresponding to the light source position information is confirmed to confirm whether it affects the second recognition module.

[0071] S1202. If the first recognition module is a face module and the infrared light source is located at a face infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module.

[0072] S1203. If the first recognition module is a face module and the infrared light source is a common infrared light source, a recognition module switching instruction is sent to receive a third pattern feature input by the user through any one of the other recognition modules as a third recognition module.

[0073] S1204. If the first recognition module is a palm vein module and the infrared light source is a common infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module.

[0074] S1205. If the first recognition module is a face module and the infrared light source is a palm vein infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module.

[0075] S1206. Perform feature recognition on the third mode feature or the second mode feature, obtain the feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

[0076] Specifically, when the light is insufficient, the system can improve the shooting brightness by setting up multiple infrared lighting sources, namely near-infrared emitting tubes. However, near-infrared emitting tubes are precise active light sources, which may be damaged and attenuated after long-term use, and also affect the normal shooting function of the camera.

[0077] In the near-infrared shooting mode corresponding to the face module, the camera uses a near-infrared wavelength of 700 to 2526 nm, preferably a near-infrared wavelength of 700 to 1100 nm. Palm vein recognition uses the property of hemoglobin in the blood to absorb near-infrared light, and uses an infrared-sensitive camera to obtain vein images under near-infrared light with a wavelength of 700nm-1000nm. From the above information, it can be seen that the palm vein mode and the face mode use near-infrared light of basically the same wavelength, that is, the two modes have similar light sensitivity. It is understandable that if the infrared light source shared by the two modes affects the recognition effect of any mode, it will also have an impact on the other recognition mode.

[0078] The smart lock provided by the present application has at least two near-infrared light emitting tubes distributed near each camera, that is, a facial infrared light source and a palm vein infrared light source are distributed near one side of the visible light camera and the near-infrared camera, and a shared infrared light source is also arranged between the visible light camera and the near-infrared camera. If there is a problem with the near-infrared light emitting tube distributed on one side of the visible light camera or the near-infrared camera, it only affects the shooting of the face module or the palm vein module, and the palm vein module can continue to work normally. However, when there is a problem with the shared near-infrared light emitting tube arranged between the visible light camera and the near-infrared camera, both the face mode and the palm vein mode cannot work normally.

[0079] In this embodiment, the image captured by the image edge information algorithm can still extract the position with insufficient pixels, that is, the light source position information. It can be understood that when the light is insufficient, the edge information of the face or palm veins is also blurred and invisible, thereby confirming whether the type of light source corresponding to the light source position information is a shared infrared light source or a unilateral light source. The unilateral light source includes a face infrared light source and a palm vein infrared light source.

[0080] Embodiment 5 The smart lock control method based on image recognition provided in this embodiment, in step S1201, namely confirming the infrared light source position corresponding to the light source position information, specifically includes the following steps: S2011. If the first recognition module is a face module, and the light source position information exists in the 2D image taken with visible light, then the light source type corresponding to the light source position information is a face infrared light source.

[0081] S2012. If the first recognition module is a face module, and the light source position information exists in the depth image taken by the near-infrared camera, the light source type corresponding to the light source position information is a common infrared light source.

[0082] S2013. If the first recognition module is a palm vein module, and the light source position information is close to a shared infrared light source, then the light source type corresponding to the light source position information is a shared infrared light source.

[0083] S2014. If the first recognition module is a palm vein module, and the light source position information is close to a palm vein infrared light source, then the light source type corresponding to the light source position information is a palm vein infrared light source.

[0084] Specifically, this embodiment can first determine the position of the test image where the light is insufficient. When the recognition module is a face module, the face image is synthesized by superimposing the 2D image taken by the visible light camera and the depth image taken by the near infrared camera. When the light of the 2D image is not clear but the depth image is clear, it can be determined that there is a problem with the infrared light source of the face. When the light of the 2D image is clear but the depth image is not clear, it can be determined that there is a problem with the shared infrared light source.

[0085] When the recognition module is a palm vein module, if the light source position information in the palm vein image is close to the shared infrared light source, that is, the palm vein features close to the palm vein infrared light source are almost blurred and invisible, while the features close to the shared infrared light source are visible, it can be determined that there is a problem with the shared infrared light source. Similarly, if the light source position information in the palm vein image is close to the palm vein infrared light source, that is, the palm vein features close to the palm vein infrared light source are almost blurred and invisible, while the features close to the shared infrared light source are visible, it can be determined that there is a problem with the palm vein infrared light source.

[0086] Embodiment 6 The image recognition-based smart lock control method provided in this embodiment further specifically includes the following steps after step S1201, that is, after confirming the infrared light source position corresponding to the light source position information: S6210. Perform lens self-inspection on the camera corresponding to the infrared light source position during the set system self-inspection period. The lens self-inspection includes occlusion self-inspection and light self-inspection, and obtain the lens self-inspection result.

[0087] S6220. If the lens self-inspection result is self-inspection failure, a repair information is sent to the remote control terminal, and the repair information includes occlusion position information and / or light source position information.

[0088] Specifically, the present embodiment can set the self-check time of the smart lock, which is generally at night when users are resting, such as 1 a.m., as the system self-check period. During this period, the smart lock can automatically take pictures of the corresponding environmental information in front of the current camera and compare the information, and can realize the self-check of occlusion and light, so as to obtain the self-check information of the device in time as the self-check result of the lens, and set self-cleaning or problem reporting in time when the corresponding problem occurs, instead of cleaning or problem reporting when the user finds the problem, so as to improve the self-check intelligence and reliability of the system.

[0089] Embodiment 7 The smart lock control method based on image recognition provided in this embodiment, before step S110, that is, before obtaining the first pattern image through the first recognition module, as shown in FIG. Figure 7 As shown, it also specifically includes the following steps: S1011. Detect the non-contact distance between the user and the smart lock through the distance sensor.

[0090] S1012. Determine at least one target camera required for the first recognition module based on the non-contact distance.

[0091] S1013. Collect a first mode image corresponding to the user through a target camera for feature recognition.

[0092] Specifically, when it is detected that the non-contact distance of the user is in the face recognition distance interval, such as 0.5 meters to 2 meters, the face module is started as the first recognition module, and the corresponding visible light camera and near-infrared camera are started as target cameras to collect the user's corresponding facial features; when the non-contact distance of the user is less than the distance in the face recognition distance interval, the palm vein module is started as the first recognition module, and the corresponding near-infrared camera is started as the target camera to collect the user's corresponding palm vein features.

[0093] The image recognition-based smart lock control method provided in this embodiment can promptly analyze the causes of biometric images obtained during shooting that do not meet the recognition requirements, and can promptly switch to other effective biometric recognition modes when it is determined that the camera is obstructed, such as by dirt. This enhances the anti-interference ability of the system while improving the effectiveness and timeliness of biometric recognition and maintaining the recognition stability of the system.

[0094] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0095] Embodiment 8 In one embodiment, a smart lock control device based on image recognition is provided, and the smart lock control device based on image recognition corresponds one-to-one to the smart lock control method based on image recognition in the above embodiment. Figure 8 As shown, the smart lock control device based on image recognition includes a first pre-processed image acquisition module 110, a cause analysis result acquisition module 120, a camera type confirmation module 130, an instruction sending module 140 and a feature recognition result acquisition module 150. The functional modules are described in detail as follows: The first preprocessed image acquisition module 110 is used to acquire a first pattern image through a first recognition module, perform image preprocessing on the first pattern image, and acquire a first preprocessed image, wherein the first recognition module is any one of a face module or a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module.

[0096] The cause analysis result acquisition module 120 is used to perform unknown cause analysis on the feature-unclear image to obtain a cause analysis result if the first pre-processed image is a feature-unclear image.

[0097] The camera type confirmation module 130 is used to record the blocking position information corresponding to the blocking if the cause analysis result is that the lens is blocked, and to confirm the camera type corresponding to the blocking position information, so as to confirm whether it affects the second recognition module.

[0098] The instruction sending module 140 is used to send a switching recognition module instruction if the first recognition module is a face module and the camera type is a near-infrared camera, so as to receive the third mode feature input by the user through any one of the other recognition modules as the third recognition module.

[0099] The feature recognition result acquisition module 150 is used to perform feature recognition on the third mode feature, obtain the feature recognition result, and confirm the opening of the smart lock according to the feature recognition result.

[0100] Furthermore, the smart lock control device also specifically includes the following modules: The switching recognition module instruction sending module 1301 is used to send a switching recognition module instruction if the first recognition module is a face module and the camera type is a visible light camera, so as to receive the third mode feature input by the user through any one of the other recognition modules as the third recognition module, or to receive the second mode feature input by the user through the second recognition module.

[0101] The switching recognition module instruction sending module 1302 is used to send a switching recognition module instruction if the first recognition module is a palm vein module and the camera type is a near-infrared camera, so as to receive the third mode feature input by the user as the third recognition module through any one of the other recognition modules.

[0102] The smart lock opening confirmation module 1303 is used to perform feature recognition on the third mode feature or the second mode feature, obtain the feature recognition result, and confirm the opening of the smart lock according to the feature recognition result.

[0103] Furthermore, the smart lock control device also specifically includes the following modules: The cleaning instruction sending module 1401 is used to send a panel cleaning instruction to clean the transparent panel corresponding to the near-infrared camera.

[0104] The information change result determination module 1402 is used to determine the information change result of the shielding position information after a preset cleaning waiting time.

[0105] The module 1403 is configured to repeatedly execute the step of acquiring the first pattern image by the first recognition module if the information change result is a decrease in the position information.

[0106] The repair information sending module 1404 is used to send repair information to the remote control terminal if the information change result is that the position information has not changed, and the repair information includes the blocked position information.

[0107] Furthermore, the smart lock control device also specifically includes the following modules: The smart lock opening confirmation module 1101 is used to perform feature recognition based on the feature-clear image if the first pre-processed image is a feature-clear image, obtain the feature recognition result, and confirm the opening of the smart lock according to the feature recognition result.

[0108] Furthermore, the smart lock control device also specifically includes the following modules: The infrared light source position confirmation module 1201 is used to record the light source position information corresponding to the light source with insufficient light if the cause analysis result is insufficient light in the lens, and confirm the infrared light source position corresponding to the light source position information, so as to confirm whether it affects the second recognition module.

[0109] The switching recognition module instruction sending module 1202 is used to send a switching recognition module instruction if the first recognition module is a face module and the infrared light source is located at a face infrared light source, so as to receive the third mode feature input by the user through any one of the other recognition modules as the third recognition module, or to receive the second mode feature input by the user through the second recognition module.

[0110] The switching recognition module instruction sending module 1203 is used to send a switching recognition module instruction if the first recognition module is a palm vein module and the infrared light source position is a common infrared light source, so as to receive the third mode feature input by the user as the third recognition module through any one of the other recognition modules.

[0111] The smart lock opening confirmation module 1204 is used to perform feature recognition on the third mode feature or the second mode feature, obtain the feature recognition result, and confirm the opening of the smart lock according to the feature recognition result.

[0112] Furthermore, the smart lock control device also specifically includes the following modules: The lens self-test module 6210 is used to perform a lens self-test on the camera corresponding to the infrared light source position during the set system self-test period. The lens self-test includes an occlusion self-test and a light self-test, and obtains the lens self-test result.

[0113] The warranty information sending module 6220 is used to send repair information to the remote control terminal if the lens self-inspection result is self-inspection failure, and the repair information includes occlusion position information and / or light source position information.

[0114] Furthermore, the smart lock control device also specifically includes the following modules: The non-contact distance detection module 1011 is used to detect the non-contact distance between the user and the smart lock through a distance sensor.

[0115] The target camera determination module 1012 is used to determine at least one target camera required to be used by the first recognition module according to the non-contact distance.

[0116] The feature recognition module 1013 is used to collect the first mode image corresponding to the user through the target camera for feature recognition.

[0117] For the specific definition of the smart lock control device based on image recognition, please refer to the definition of the smart lock control method based on image recognition above, which will not be repeated here. Each module in the above-mentioned smart lock control device based on image recognition can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0118] Embodiment 9 This embodiment also provides an electronic device, such as Fig. 9 As shown, it includes: a microprocessor supporting at least two biometric feature recognitions, and a functional module electrically connected to the microprocessor, the functional module including: a camera module, an infrared lighting source, a face module, a palm vein module, a distance sensing module, a light sensitive sensing module, a memory module, an Ethernet communication module, a speaker, an electromagnetic lock control module and a power supply module, and the Ethernet communication module is connected to the remote control terminal via Ethernet.

[0119] The distance sensing module is used to detect whether there is an object within the preset identification distance. The electromagnetic lock control module is used to perform the unlocking operation.

[0120] The light-sensitive sensor module is used to detect ambient light information and send the ambient light information to the microprocessor, so that the microprocessor switches the working mode of the camera in the camera module according to the ambient light information.

[0121] The camera module is arranged at the lower side of the transparent panel, including at least one visible light camera and at least one near infrared camera, and a visible light filter is embedded in the transparent panel. At least two near infrared light emitting tubes are evenly distributed around each camera, and at least one near infrared light emitting tube is evenly distributed between every two cameras. The near infrared light emitting tube is used to provide infrared fill light function for the camera in the camera module.

[0122] The microprocessor controls the camera module and the near-infrared light emitting tube to recognize the human face or palm veins and recognizes the human face pattern image or palm vein pattern image taken by the camera module.

[0123] When the microprocessor executes the computer program, the smart lock control method based on image recognition in the above embodiment is implemented, for example Figure 2 Alternatively, when the microprocessor executes the computer program, the functions of each module / unit of the smart lock control device based on image recognition in the above-mentioned embodiment are realized, for example Fig. 9 The functions of the modules 110 to 150 are shown in detail and will not be described again here to avoid repetition.

[0124] Embodiment 10 This embodiment also provides an electronic device, which specifically also includes: a lens self-cleaning mechanism disposed on the transparent panel for cleaning the camera area.

[0125] Specifically, the smart lock provided in this embodiment has a transparent panel with an automatic cleaning function, and the panel is integrated with a miniature lens self-cleaning device, which can automatically clean the transparent panel before identification to remove water droplets and dirt. The lens self-cleaning device cooperates with the smart lock control system based on image recognition provided in this embodiment, and can intelligently adjust the frequency and intensity of automatic cleaning according to environmental conditions and frequency of use; and after receiving the panel cleaning instruction, the lens self-cleaning device can be activated to clean the corresponding position of the camera on the transparent panel that has been recently soiled. In order to speed up the unlocking speed, the entire panel can be cleaned as needed, or only the corresponding position of the camera on the transparent panel that has been recently soiled can be cleaned.

[0126] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments of the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0127] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0128] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A smart lock control method based on image recognition, characterized in that: include: Acquire a first pattern image through a first recognition module, perform image preprocessing on the first pattern image, and acquire a first preprocessed image, wherein the first recognition module is any one of a face module or a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module; If the first pre-processed image is an image with unknown features, performing an unknown cause analysis on the image with unknown features to obtain a cause analysis result; If the cause analysis result is that the lens is blocked, then the blocking position information corresponding to the blocking is recorded, and the camera type corresponding to the blocking position information is confirmed, so as to confirm whether the second recognition module is affected; If the first recognition module is a face module and the camera type is a near infrared camera, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; Perform feature recognition on the third mode feature, obtain a feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

2. The smart lock control method based on image recognition according to claim 1, characterized in that: After confirming the camera type corresponding to the blocking position information, the method further includes: If the first recognition module is a face module and the camera type is a visible light camera, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module; If the first recognition module is a palm vein module and the camera type is a near infrared camera, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; Perform feature recognition on the third mode feature or the second mode feature, obtain a feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

3. The smart lock control method based on image recognition according to claim 1, characterized in that: After sending the instruction to switch the identification module, the method further includes: Sending a panel cleaning instruction to clean the transparent panel corresponding to the near-infrared camera; After a preset cleaning waiting time, determining an information change result of the shielding position information; If the information change result is a decrease in position information, repeating the step of the first recognition module acquiring the first pattern image; If the information change result is that the position information does not change, a repair information is sent to the remote control terminal, and the repair information includes the obstruction position information.

4. The smart lock control method based on image recognition according to claim 1, characterized in that: After obtaining the cause analysis result, the method further includes: If the cause analysis result is that the lens light is insufficient, then the light source position information corresponding to the insufficient light source is recorded, and the infrared light source position corresponding to the light source position information is confirmed, so as to confirm whether the second recognition module is affected; If the first recognition module is a face module and the infrared light source is located at a face infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module; If the first recognition module is a face module and the infrared light source is a common infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; If the first recognition module is a palm vein module and the infrared light source is a common infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; If the first recognition module is a face module and the infrared light source is a palm vein infrared light source, a recognition module switching instruction is sent to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module, or to receive a second mode feature input by the user through the second recognition module; Perform feature recognition on the third mode feature or the second mode feature, obtain a feature recognition result, and confirm the opening of the smart lock based on the feature recognition result.

5. The smart lock control method based on image recognition as claimed in claim 4, characterized in that: The confirming the infrared light source position corresponding to the light source position information includes: If the first recognition module is a face module, and the light source position information exists in the 2D image taken with visible light, then the light source type corresponding to the light source position information is a face infrared light source; If the first recognition module is a face module, and the light source position information exists in the depth image taken by the near-infrared camera, the light source type corresponding to the light source position information is a common infrared light source; If the first recognition module is a palm vein module, and the light source position information is close to a common infrared light source, then the light source type corresponding to the light source position information is a common infrared light source; If the first recognition module is a palm vein module, and the light source position information is close to a palm vein infrared light source, then the light source type corresponding to the light source position information is a palm vein infrared light source.

6. The smart lock control method based on image recognition as claimed in claim 4, characterized in that: After confirming the infrared light source position corresponding to the light source position information, the method further includes: Performing a lens self-test on the camera corresponding to the infrared light source position during a set system self-test period, wherein the lens self-test includes an occlusion self-test and a light self-test, and obtaining a lens self-test result; If the lens self-test result is self-test failure, a repair information is sent to the remote control terminal, and the repair information includes the blocking position information and / or the light source position information.

7. The smart lock control method based on image recognition according to claim 1, characterized in that: Before acquiring the first pattern image by the first recognition module, the method further includes: Detecting the non-contact distance between the user and the smart lock through a distance sensor; Determining at least one target camera required to be used by the first recognition module according to the non-contact distance; The target camera collects a first mode image corresponding to the user for feature recognition.

8. An intelligent lock control device based on image recognition, characterized in that: include: A first pre-processed image acquisition module, used to acquire a first pattern image through a first recognition module, perform image pre-processing on the first pattern image, and acquire a first pre-processed image, wherein the first recognition module is any one of a face module and a palm vein module, and the second recognition module is another module in the face module or the palm vein module that is different from the first recognition module; a cause analysis result acquisition module, configured to perform an unknown cause analysis on the unknown feature image to acquire a cause analysis result if the first preprocessed image is an image with unknown features; A camera type confirmation module, for recording the occlusion position information corresponding to the occlusion if the cause analysis result is that the lens is occluded, and confirming the camera type corresponding to the occlusion position information, so as to confirm whether the second recognition module is affected; An instruction sending module, configured to send a switching recognition module instruction if the first recognition module is a face module and the camera type is a near-infrared camera, so as to receive a third mode feature input by the user through any one of the other recognition modules as a third recognition module; The feature recognition result acquisition module is used to perform feature recognition on the third mode feature, obtain feature recognition results, and confirm the opening of the smart lock based on the feature recognition results.

9. An electronic device, characterized in that: include: A microprocessor supporting at least two types of biometric identification, and a functional module electrically connected to the microprocessor, the functional module comprising: a camera module, an infrared lighting source, a face module, a palm vein module, a distance sensing module, a light sensing module, a memory module, an Ethernet communication module, a speaker, an electromagnetic lock control module, and a power supply module, the Ethernet communication module being connected to a remote control terminal via Ethernet; A memory module, used to store preset feature data of at least two types of biometric identification and a computer program in the memory module and executable on the microprocessor, wherein when the computer program is executed by the microprocessor, the microprocessor implements the smart lock control method based on image recognition as described in any one of claims 1 to 7; the microprocessor controls the camera module and the near-infrared light emitting tube to identify a face or a palm vein; The light-sensitive sensing module is used to detect ambient light information and send the ambient light information to the microprocessor, so that the microprocessor switches the working mode of the camera in the camera module according to the ambient light information; The camera module is arranged on the lower side of the transparent panel, including at least one visible light camera and at least one near-infrared camera, and a visible light filter is embedded in the transparent panel; at least two near-infrared light emitting tubes are evenly distributed around each camera, and at least one near-infrared light emitting tube is evenly distributed between every two cameras. The near-infrared light emitting tube is used to provide infrared fill light function for the camera in the camera module.

10. The electronic device according to claim 9, characterized in that: Also includes: A lens self-cleaning mechanism is arranged on the transparent panel for cleaning the camera area.

Images