Face recognition monitoring method

Through high-resolution camera and image processing technology, facial features are extracted, the information database of authorized personnel is established and encrypted and stored, which solves the problem of insufficient real-time and accuracy of the existing hotel facial recognition monitoring system, and improves recognition efficiency and security , eliminates data accumulation and security risks.

CN118982885AInactive Publication Date: 2024-11-19HUNAN CHENGXI INFORMATION TECH CO LTD

Patent Information

Application Number
CN202410978744.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing hotel facial recognition monitoring system is insufficient in real-time and accuracy during the acquisition and processing of facial image data, and cannot delete and update facial data in a timely manner, resulting in low efficiency in security risks and abnormal processing.

Method used

Using high-resolution camera and image processing technology, facial features are extracted through convolutional neural networks, combined with principal component analysis for real-time comparison, establish an information database of authorized personnel, and encrypted storage and backup in the central management system to automatically trigger abnormal alarms and data deletion.

Benefits of technology

It improves the accuracy and real-time nature of facial recognition, avoids recognition delays and misjudgments, ensures security and management efficiency, eliminates potential security risks, and provides detailed data records and backups.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982885A_ABST
    Figure CN118982885A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of safety monitoring, in particular to a face recognition monitoring method, which comprises the following steps: when a person goes to a foreground to check in, scanning a face through a foreground camera, acquiring face image data, uploading the face image data to a central management system, and establishing an authorized person information base; cameras are installed on a door, an elevator, a fire fighting access entrance and exit and a corridor of a hotel, face image data of hotel personnel are collected in real time and compared with data in an authorized personnel information base, when the comparison result is matched, it is judged that the hotel personnel are legal check-in personnel and normal passing is allowed, and when the comparison result is not matched, abnormal alarm is automatically triggered, and the safety of the hotel is guaranteed. And when the check-out procedure is handled, the system automatically deletes the face image data of the check-out personnel from the authorized personnel information base and cancels the access authority of the check-out personnel. According to the invention, the safety management efficiency and response speed of the hotel can be significantly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring, and in particular to a face recognition monitoring method. Background Art

[0002] With the development of science and technology and the progress of society, the hotel industry has higher and higher requirements for security management. Traditional hotel security management methods mainly rely on manual monitoring and access card systems, which have great security risks and management loopholes. With the continuous advancement of artificial intelligence and biometric technology, intelligent monitoring systems based on face recognition have gradually become an effective means to improve the level of hotel security management. Facial recognition technology can accurately identify and verify the identity of people by collecting and analyzing facial features through cameras, which not only improves security, but also improves user experience and management efficiency.

[0003] Although the existing hotel face recognition monitoring system can improve security to a certain extent, there are still some technical problems. First, the collection and processing process of facial image data is complicated, and the real-time and accuracy are insufficient, which may lead to recognition delays or misjudgments during peak hours. Secondly, the facial data management of check-out personnel is not perfect, and it cannot be deleted and updated in time, which poses potential safety hazards. Finally, the alarm mechanism of the existing system is not flexible enough, the processing efficiency of abnormal situations is low, and it is unable to quickly respond to and handle the intrusion of abnormal personnel. Summary of the invention

[0004] Based on the above purpose, the present invention provides a face recognition monitoring method.

[0005] A face recognition monitoring method comprises the following steps:

[0006] S1: When a person goes to the front desk to check in, the front desk camera scans the person's face to obtain the facial image data of the person;

[0007] S2: Upload the facial image data of the registered person to the hotel's central management system and establish an authorized person information database, which contains the person's facial image data, name, room number and check-in time;

[0008] S3: Install cameras at the hotel's main entrance, elevators, fire escape entrances and corridors to collect facial image data of hotel staff in real time;

[0009] S4: comparing the real-time collected facial image data with the facial image data in the authorized personnel information database;

[0010] S5: When the real-time collected facial image data matches the facial image data in the authorized personnel information database, the person is determined to be a legal check-in person and is allowed to pass normally. When the real-time collected facial image data does not match the facial image data in the authorized personnel information database, the person is determined to be an abnormal person, and the central management system automatically triggers an abnormal alarm to remind hotel staff to verify;

[0011] S6: After receiving the abnormal alarm, the hotel staff will immediately go to the abnormal location to verify and take corresponding measures;

[0012] S7: When the registered person checks out, the central management system automatically deletes his / her facial image data from the authorized person information database and cancels his / her entry and exit rights;

[0013] S8: The central management system regularly backs up and archives the authorized personnel information database and monitoring data for subsequent query and tracing.

[0014] Optionally, the S1 specifically includes:

[0015] S11, camera scanning and image acquisition: The front desk is equipped with cameras of various angles, and the cameras have high definition and suitable lighting conditions, which can accurately capture the facial features of the check-in personnel. When the personnel go to the front desk to check in, the cameras of various angles will automatically start or be triggered by the staff to scan the personnel's face;

[0016] S12, facial image data extraction: The camera identifies and extracts the facial image data of the occupants through image processing and face recognition algorithms.

[0017] Optionally, the S2 specifically includes:

[0018] S21, associated information: facial image data is associated with personal information, including name, room number and check-in time, to establish a complete authorized personnel information database;

[0019] S22, data storage: the facial image data and the corresponding associated information are stored in the hotel's central management system, and an authorized personnel information database is established. Encrypted storage technology is used during storage to ensure that the data is not stolen or tampered with by unauthorized access;

[0020] S23, Feedback mechanism: The central management system is configured with an interactive interface and a feedback mechanism designed to prompt whether the facial image data of the occupants has been successfully acquired and stored, so as to make corrections or handle abnormal situations in a timely manner.

[0021] Optionally, the S3 specifically includes:

[0022] S31, Camera installation and configuration: Cameras are installed at gates, elevators, fire escape entrances and corridors. The angles and heights are adjusted to optimize facial image acquisition. The cameras are connected to the hotel's central management system to ensure real-time data transmission.

[0023] S32, real-time image acquisition: the camera captures the facial images of people passing by in real time through the built-in image sensor, and continuously shoots image frames through the camera to generate a video stream;

[0024] S33, image processing: transmitting the generated video stream to the central management system in real time, and performing image processing on the video stream through the central management system, including face detection, image segmentation and feature extraction, to extract face image data;

[0025] S34, data storage: the extracted facial image data is transmitted to the central management system through an encrypted network protocol, and the facial image data is temporarily stored in the central management system for subsequent identity comparison;

[0026] S35, real-time monitoring: The central management system is equipped with a display interface that displays image data from the camera in real time for security personnel to monitor and view.

[0027] Optionally, the S4 specifically includes:

[0028] S41, calculating similarity measurement: calculating the Euclidean distance between the feature vector extracted from the face image data and the feature vector extracted from each face image data in the authorized person information database;

[0029] S42, comparison and matching: setting a threshold of the Euclidean distance to determine whether the face image and the facial image match.

[0030] Optionally, the S5 specifically includes:

[0031] S51, match determination: make a determination based on the similarity measurement result. If the Euclidean distance is less than the preset threshold, the person is determined to be a legitimate person and is allowed to pass. If the Euclidean distance is not greater than the preset threshold, the person is determined to be an abnormal person and the alarm process is triggered.

[0032] S52, abnormal alarm: generate an alarm signal, including the image of the abnormal person and the comparison result, and execute the preset alarm operation.

[0033] Optionally, the alarm operation preset in S52 specifically includes:

[0034] Sound alarm: trigger the sound alarm at the front desk or security monitoring room to sound an alarm;

[0035] Visual alarm: Display alarm information on the monitoring screen at the front desk or security monitoring room, including real-time images of abnormal personnel and comparison results;

[0036] Notify hotel staff: Notify hotel staff through a variety of methods, including SMS, email, and hotel internal management applications.

[0037] Optionally, the corresponding measures taken in S6 specifically include:

[0038] S61, verifying the identity of the person: face-to-face communication with the abnormal person, asking about his / her identity and check-in information, requiring the abnormal person to produce his / her identity certificate (such as ID card, passport, etc.) and check-in certificate (such as room card, check-in registration information, etc.), and verifying the information;

[0039] S62, Safety measures: During the process of confirming the identity of abnormal persons, staff should remain vigilant to ensure the safety of themselves and those around them;

[0040] S63, False Alarm Handling: If it is confirmed to be a false alarm after verification, the staff shall apologize to the abnormal person, mark the alarm as a false alarm in the central management system, and update the authorized personnel information database to ensure that there will be no false alarm next time;

[0041] S64, Unauthorized Personnel Handling: If it is confirmed that the abnormal person is an unauthorized person, the staff should take immediate measures.

[0042] Optionally, the S7 specifically includes:

[0043] S71, check-out information verification: When a person requests to check out at the front desk, the central management system verifies the identity information of the person checking out through facial recognition and related information to ensure that the person is a legitimate check-in person;

[0044] S72, data deletion: the central management system searches the authorized personnel information database, finds the facial image data and related information matching the check-out personnel, deletes the facial image data and other related information of the personnel, and cancels the access rights of the personnel;

[0045] S73, confirmation information: After the data is deleted, the central management system generates a notification to confirm that the check-out is successful. After the front desk staff confirms the information through the preset interactive interface, they confirm to the check-out personnel that the check-out is successful and all entry and exit permissions have been cancelled.

[0046] Beneficial effects of the present invention:

[0047] The present invention uses a high-resolution camera and image processing technology to ensure that facial features of people can be clearly captured under various lighting conditions. The facial image data collected at the front desk is extracted by convolutional neural network, and the facial image data collected in real time is extracted by principal component analysis, which greatly improves the accuracy and real-time performance of face recognition. At the same time, the real-time video stream can be efficiently processed and compared to ensure that legal occupants can be quickly and accurately identified during peak hours, avoiding recognition delays and misjudgments.

[0048] In the present invention, when a person checks out, the central management system will automatically delete his / her facial image data from the authorized personnel information database and cancel his / her access rights. This not only prevents the accumulation of expired data, but also eliminates potential safety hazards. The central management system has a data backup function to ensure that no data loss or misoperation occurs during the data deletion process, and provides detailed records for subsequent review and management, thereby improving security and reliability.

[0049] The present invention automatically triggers an abnormal alarm when the real-time collected facial image data does not match the data in the authorized personnel information database, and notifies the hotel staff to go to the scene to verify the situation. It supports multiple alarm modes to ensure that relevant personnel can respond and handle abnormal situations in a timely manner. After receiving the alarm, the hotel staff will go to the location where the abnormality occurred to verify and take corresponding measures, such as requiring the abnormal person to leave or reporting the abnormality. Through this automated abnormality handling mechanism, the hotel's safety management efficiency and response speed are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A schematic diagram of the method steps of an embodiment of the present invention;

[0052] Figure 2 Schematic diagram of step S3 of an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0054] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0055] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0056] like Figure 1-Figure 2 As shown, a face recognition monitoring method comprises the following steps:

[0057] S1: When a person goes to the front desk to check in, the front desk camera scans the person's face to obtain the facial image data of the person;

[0058] S2: Upload the facial image data of the registered person to the hotel's central management system and establish an authorized person information database, which contains the person's facial image data, name, room number and check-in time;

[0059] S3: Install cameras at the hotel's main entrance, elevators, fire escape entrances and corridors to collect facial image data of hotel staff in real time;

[0060] S4: comparing the real-time collected facial image data with the facial image data in the authorized personnel information database;

[0061] S5: When the real-time collected facial image data matches the facial image data in the authorized personnel information database, the person is determined to be a legal check-in person and is allowed to pass normally. When the real-time collected facial image data does not match the facial image data in the authorized personnel information database, the person is determined to be an abnormal person, and the central management system automatically triggers an abnormal alarm to remind hotel staff to verify;

[0062] S6: After receiving the abnormal alarm, the hotel staff will immediately go to the abnormal location to verify and take corresponding measures;

[0063] S7: When the registered person checks out, the central management system automatically deletes his / her facial image data from the authorized person information database and cancels his / her entry and exit rights;

[0064] S8: The central management system regularly backs up and archives the authorized personnel information database and monitoring data for subsequent query and tracing.

[0065] S1 specifically includes:

[0066] S11, camera scanning and image acquisition: The front desk is equipped with cameras of various angles, and the cameras have high definition and suitable lighting conditions, which can accurately capture the facial features of the check-in personnel. When the personnel go to the front desk to check in, the cameras of various angles will automatically start or be triggered by the staff to scan the personnel's face;

[0067] S12, facial image data extraction: The camera uses image processing and face recognition algorithms to identify and extract facial image data of the occupants, including:

[0068] (1) Image preprocessing: After image acquisition, images may need to be preprocessed, including denoising, contrast enhancement, brightness adjustment, etc., to improve image quality;

[0069] Denoising: The denoising method uses Gaussian filtering, which is expressed as:

[0070] Among them, I in is the input image, I out is the output image, σ is the standard deviation, and k is the radius of the filter;

[0071] Enhance contrast: Use histogram equalization to enhance contrast, expressed as:

[0072] Where P(i) is the cumulative probability of image gray value i, N is the total number of pixels in the image, and C(r) is the enhanced gray value;

[0073] (2) Face detection algorithm: Use Haar cascade classifier to identify the face area in the image. Haar cascade classifier can quickly locate the position of the face in the image;

[0074] The Haar cascade classifier is a cascade model obtained by training a classifier based on the Haar feature to detect faces. The Haar feature is expressed as: H = ∑ i (AB), where H is the Haar eigenvalue, A is the sum of pixel values ​​in a specific area, and B is the sum of pixel values ​​in another specific area;

[0075] (3) Multi-scale detection: Scan the image at different scales to ensure that faces at different distances and angles can be detected;

[0076] (4) Face alignment: Use a face alignment algorithm (such as Dlib’s 68-point face markers) to adjust the face image to a standard position, which helps improve the accuracy of subsequent feature extraction. Through geometric transformations (such as rotation and scaling), the face image is adjusted to a standardized perspective and size.

[0077] Dlib’s 68-point face landmarks: align faces using 68 key points;

[0078] Face alignment is performed using the affine transformation matrix A, expressed as:

[0079] p′=Ap+t, where p is the facial key point, p′ is the aligned key point, and t is the translation vector;

[0080] (5) Feature extraction: Use deep learning models (such as convolutional neural networks (CNN)) to extract facial features. The model can extract high-dimensional feature vectors from facial images to represent the unique features of the face, and convert the extracted feature vectors into fixed-length facial embeddings for subsequent similarity comparisons.

[0081] Convolutional Neural Network: extracts high-dimensional vectors of facial features;

[0082] The calculation of the convolutional layer is expressed as: Among them, F out is the feature map after convolution, F in is the input image and K is the convolution kernel.

[0083] S2 specifically includes:

[0084] S21, associated information: facial image data is associated with personal information, including name, room number and check-in time, to establish a complete authorized personnel information database;

[0085] S22, data storage: the facial image data and the corresponding associated information are stored in the hotel's central management system, and an authorized personnel information database is established. Encrypted storage technology is used during storage to ensure that the data is not stolen or tampered with by unauthorized access;

[0086] S23, Feedback mechanism: The central management system is configured with an interactive interface and a feedback mechanism designed to prompt whether the facial image data of the occupants has been successfully acquired and stored, so as to make corrections or handle abnormal situations in a timely manner.

[0087] S3 specifically includes:

[0088] S31, Camera installation and configuration: Select cameras with high resolution and good low-light performance to ensure clear facial images in all environmental conditions. Camera installation locations cover gates, elevators, fire escape entrances and corridors. Adjust the angle and height to optimize facial image acquisition. Connect the camera to the hotel's central management system to ensure real-time data transmission;

[0089] S32, real-time image acquisition: the camera captures the facial images of people passing by in real time through the built-in image sensor, and continuously shoots image frames through the camera to generate a video stream;

[0090] S33, image processing: transmitting the generated video stream to the central management system in real time, and performing image processing on the video stream through the central management system, including face detection, image segmentation and feature extraction, to extract face image data;

[0091] (1) Face detection: Use HOG+SVM to identify the facial area in the image;

[0092] HOG+SVM: Uses Histogram of Oriented Gradients (HOG) features and Support Vector Machine (SVM) for face detection;

[0093] The HOG feature is expressed as: Among them, hist i is the statistical value of each directional gradient histogram, and N is the number of histograms;

[0094] (2) Image segmentation: Use a semantic segmentation model (such as U-Net) to segment the facial area from the background. The specific steps are as follows:

[0095] a. Image and label data: Prepare a dataset containing facial images and corresponding segmentation labels (masks). The label data is usually a binary image representing the facial area (foreground) and the background area.

[0096] bU-Net model structure: The structure of the U-Net model is divided into two parts: encoder and decoder:

[0097] Encoder (downsampling path): extracts features through a series of convolutional and pooling layers, and gradually reduces the spatial resolution;

[0098] Decoder (upsampling path): restores the spatial resolution through a series of upsampling layers and convolutional layers, and generates segmentation masks;

[0099] c. Convolutional layer and pooling layer: The input image passes through two layers of convolution operations, each of which is followed by a ReLU activation function, and then passes through a maximum pooling layer to reduce the spatial resolution, expressed as:

[0100] xi+1 =ReLU(Conv(x i ));

[0101] p i =MaxPool(x i+1 );

[0102] d. Upsampling layer and convolution layer: Use the upsampling layer (deconvolution or upsampling) to increase the spatial resolution, and then generate the feature map through two layers of convolution operations, expressed as:

[0103] u i =UpSample(p i );

[0104] c i =ReLU(Conv(u i ));

[0105] e. Skip connection: Connect the feature map in the encoder with the feature map in the decoder to retain high-resolution information, expressed as:

[0106] m i =Concat(c i , p j ), where p j is the feature map of the corresponding layer in the encoder;

[0107] f. Output layer: The last convolution operation generates a segmentation mask of the same size as the input image, expressed as:

[0108] y=Sigmoid(Conv(m i )), where the Sigmoid activation function limits the output value to the range [0, 1], which is used to represent the probability that a pixel belongs to the foreground (face) or background;

[0109] g. Cross entropy loss: The difference between the predicted mask and the true mask is calculated using a binary cross entropy loss function, expressed as:

[0110] Among them, y i is the true label, p i is the prediction probability, N is the number of pixels;

[0111] h. Model training: Use a gradient descent algorithm (such as Adam) to minimize the loss function and train the U-Net model to optimize its parameters, expressed as:

[0112] Among them, θ is the model parameter and θ is the learning rate;

[0113] i. Real-time image segmentation: For each frame of the real-time video stream, the trained U-Net model is used for prediction to generate a segmentation mask, which is expressed as: Extracting facial regions based on segmentation masks;

[0114] (3) Feature extraction: After image segmentation, the facial region is extracted from the segmentation mask and feature extraction is performed using principal component analysis. The specific steps are as follows:

[0115] a. Extract facial region from segmentation mask:

[0116] Apply segmentation mask: Apply the segmentation mask to the original image to extract the facial region, expressed as:

[0117] I face (x, y) = I original (x, y)·M(x, y), where, I face (x, y) is the extracted facial image, I original (x, y) is the original image, M(x, y) is the segmentation mask;

[0118] b. Facial image normalization:

[0119] Image resizing: Resize facial images to a uniform size (e.g. m ×n ), expressed as:

[0120] I normalized = resize(I face , (m, n));

[0121] Image flattening: Flatten the two-dimensional facial image into a one-dimensional vector, expressed as:

[0122] x=flatten(I normalized ), where x is a vector of length m·n;

[0123] c. Construct the data matrix:

[0124] Data Matrix: All facial image vectors are combined into a data matrix X, where each column represents an image vector, expressed as: Where N is the number of images, x i is the flattened vector for each image:

[0125] d. Mean normalization:

[0126] Mean image: Calculate the mean image of all training images, expressed as:

[0127] Mean Normalization: Subtract the mean image from each image vector, expressed as:

[0128] e. Calculate the covariance matrix:

[0129] Covariance Matrix: Calculate the covariance matrix of the normalized data matrix, expressed as:

[0130] Eigenvalues ​​and Eigenvectors: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix, expressed as:

[0131] Cv i =λ i v i , where v i is the eigenvector, λ i is the eigenvalue;

[0132] f. Select the principal components:

[0133] Principal component selection: Select the first k principal components according to the size of the eigenvalue to form a projection matrix W, which is expressed as:

[0134] g. Projection to principal component space:

[0135] Feature vector: Project the facial image vector into the principal component space to obtain the feature vector, which is expressed as:

[0136] y=W T (x-μ), where x is the new facial image vector and y is the extracted feature vector;

[0137] S34, data storage: the extracted facial image data is transmitted to the central management system through an encrypted network protocol, and the facial image data is temporarily stored in the central management system for subsequent identity comparison;

[0138] S35, real-time monitoring: The central management system is equipped with a display interface that displays image data from the camera in real time for security personnel to monitor and view.

[0139] S4 specifically includes:

[0140] S41, calculating similarity measurement: calculating the Euclidean distance between the feature vector extracted from the face image data and the feature vector extracted from each face image data in the authorized person information database, expressed as:

[0141] Among them, y stored is the facial feature vector in the authorized personnel information database;

[0142] S42, comparison and matching: set a threshold of Euclidean distance to determine whether the face image and the facial image match, traverse all feature vectors in the authorized personnel information database, calculate the Euclidean distance between the feature vectors extracted from the face image data, and determine whether there is a feature vector whose Euclidean distance is less than the threshold.

[0143] S5 specifically includes:

[0144] S51, match determination: make a determination based on the similarity measurement result. If the Euclidean distance is less than the preset threshold, the person is determined to be a legitimate person and is allowed to pass. If the Euclidean distance is not greater than the preset threshold, the person is determined to be an abnormal person and the alarm process is triggered.

[0145] S52, abnormal alarm: generate an alarm signal, including the image of the abnormal person and the comparison result, and execute the preset alarm operation;

[0146] When an abnormal person is detected, an alarm is automatically triggered and relevant staff are notified to verify and handle the situation, thereby ensuring the safety management of the hotel.

[0147] The alarm operations preset in S52 specifically include:

[0148] Sound alarm: trigger the sound alarm at the front desk or security monitoring room to sound an alarm;

[0149] Visual alarm: Display alarm information on the monitoring screen at the front desk or security monitoring room, including real-time images of abnormal personnel and comparison results;

[0150] Notify hotel staff: Notify hotel staff through a variety of methods, including SMS, email, and hotel internal management applications.

[0151] S6 takes corresponding measures, including:

[0152] S61, verifying the identity of the person: face-to-face communication with the abnormal person, asking about his / her identity and check-in information, requiring the abnormal person to produce his / her identity certificate (such as ID card, passport, etc.) and check-in certificate (such as room card, check-in registration information, etc.), and verifying the information;

[0153] S62, Safety measures: During the process of confirming the identity of abnormal persons, staff should remain vigilant to ensure the safety of themselves and those around them;

[0154] S63, False Alarm Handling: If it is confirmed to be a false alarm after verification, the staff shall apologize to the abnormal person, mark the alarm as a false alarm in the central management system, and update the authorized personnel information database to ensure that there will be no false alarm next time;

[0155] S64, Unauthorized Personnel Handling: If the abnormal person is confirmed to be an unauthorized person, the staff should take immediate measures, including:

[0156] Ask unauthorized persons to leave the hotel and record their information;

[0157] If the unauthorized person refuses to leave, staff can request assistance from security personnel and call the police if necessary;

[0158] Record the details of the incident, including the behavior, conversations and handling process of the abnormal personnel, for subsequent investigation and handling;

[0159] Hotel staff can effectively handle abnormal alarm events, ensure the safety and order of the hotel, and improve the level of security management.

[0160] S7 specifically includes:

[0161] S71, check-out information verification: When a person requests to check out at the front desk, the central management system verifies the identity information of the person checking out through facial recognition and related information to ensure that the person is a legitimate check-in person;

[0162] S72, data deletion: the central management system searches the authorized personnel information database, finds the facial image data and related information matching the check-out personnel, deletes the facial image data and other related information of the personnel, and cancels the access rights of the personnel;

[0163] S73, confirmation information: after the data is deleted, the central management system generates a notification to confirm that the check-out is successful. After the front desk staff confirms the information through the preset interactive interface, they confirm to the check-out personnel that the check-out is successful and all access rights have been cancelled;

[0164] The central management system can automatically delete facial image data and cancel access permissions when people check out, ensuring the accuracy and security of system data.

[0165] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A face recognition monitoring method, characterized in that: The following steps are involved: S1: When a person goes to the front desk to check in, the front desk camera scans the person's face to obtain the facial image data of the person; S2: Upload the facial image data of the registered person to the hotel's central management system to establish an authorized personnel information database; S3: Install cameras at the hotel's main entrance, elevators, fire escape entrances and corridors to collect facial image data of hotel staff in real time; S4: comparing the real-time collected facial image data with the facial image data in the authorized personnel information database; S5: When the real-time collected facial image data matches the facial image data in the authorized personnel information database, the person is determined to be a legal check-in person and is allowed to pass normally. When the real-time collected facial image data does not match the facial image data in the authorized personnel information database, the person is determined to be an abnormal person, and the central management system automatically triggers an abnormal alarm to remind hotel staff to verify; S6: After receiving the abnormal alarm, the hotel staff will immediately go to the abnormal location to verify and take corresponding measures; S7: When the registered person checks out, the central management system automatically deletes his / her facial image data from the authorized person information database and cancels his / her entry and exit rights; S8: The central management system regularly backs up and archives the authorized personnel information database and monitoring data for subsequent query and tracing.

2. A face recognition monitoring method according to claim 1, characterized in that: The S1 specifically includes: S11, camera scanning and image acquisition: The front desk is equipped with cameras at various angles to accurately capture the facial features of check-in personnel. When a person goes to the front desk to check in, the cameras at various angles will automatically start or be triggered by the staff to scan the person's face; S12, facial image data extraction: The camera identifies and extracts the facial image data of the occupants through image processing and face recognition algorithms.

3. A face recognition monitoring method according to claim 2, characterized in that: The S2 specifically includes: S21, associated information: facial image data associated with personal information, including name, room number and check-in time; S22, data storage: storing the facial image data and the corresponding associated information in the hotel's central management system to establish an authorized personnel information database; S23, feedback mechanism: The central management system is configured with an interactive interface and a feedback mechanism designed to prompt whether the facial image data of the occupants has been successfully acquired and stored.

4. A face recognition monitoring method according to claim 3, characterized in that: The S3 specifically includes: S31, Camera installation and configuration: Cameras are installed at gates, elevators, fire escape entrances and corridors. The angles and heights are adjusted to optimize facial image acquisition, and the cameras are connected to the hotel's central management system. S32, real-time image acquisition: the camera captures the facial images of people passing by in real time through the built-in image sensor, and continuously shoots image frames through the camera to generate a video stream; S33, image processing: transmitting the generated video stream to the central management system in real time, and performing image processing on the video stream through the central management system, including face detection, image segmentation and feature extraction, to extract face image data; S34, data storage: the extracted facial image data is transmitted to the central management system through an encrypted network protocol, and the facial image data is temporarily stored in the central management system for subsequent identity comparison; S35, real-time monitoring: The central management system is equipped with a display interface that displays image data from the camera in real time for security personnel to monitor and view.

5. A face recognition monitoring method according to claim 4, characterized in that: The S4 specifically includes: S41, calculating similarity measurement: calculating the Euclidean distance between the feature vector extracted from the face image data and the feature vector extracted from each face image data in the authorized person information database; S42, comparison and matching: setting a threshold of the Euclidean distance to determine whether the face image and the facial image match.

6. A face recognition monitoring method according to claim 5, characterized in that: The S5 specifically includes: S51, match determination: make a determination based on the similarity measurement result. If the Euclidean distance is less than the preset threshold, the person is determined to be a legitimate person and is allowed to pass. If the Euclidean distance is not greater than the preset threshold, the person is determined to be an abnormal person and the alarm process is triggered. S52, abnormal alarm: generate an alarm signal, including the image of the abnormal person and the comparison result, and execute the preset alarm operation.

7. A face recognition monitoring method according to claim 6, characterized in that: The alarm operation preset in S52 specifically includes: Sound alarm: trigger the sound alarm at the front desk or security monitoring room to sound an alarm; Visual alarm: Display alarm information on the monitoring screen at the front desk or security monitoring room, including real-time images of abnormal personnel and comparison results; Notify hotel staff: Notify hotel staff through a variety of methods, including SMS, email, and hotel internal management applications.

8. The face recognition monitoring method according to claim 1, characterized in that: The corresponding measures taken in S6 specifically include: S61, verifying the identity of the person: face-to-face communication with the abnormal person, asking for his / her identity and check-in information, requiring the abnormal person to produce his / her identity certificate and check-in certificate, and verifying the information; S62, Safety measures: During the process of confirming the identity of abnormal persons, staff should remain vigilant to ensure the safety of themselves and those around them; S63, False Alarm Handling: If it is confirmed to be a false alarm after verification, the staff shall apologize to the abnormal person, mark the alarm as a false alarm in the central management system, and update the authorized personnel information database; S64, Unauthorized Personnel Handling: If it is confirmed that the abnormal person is an unauthorized person, the staff should take immediate measures.

9. The face recognition monitoring method according to claim 3, characterized in that: The S7 specifically includes: S71, check-out information verification: When a person requests to check out at the front desk, the central management system verifies the identity information of the person checking out through facial recognition and related information to ensure that the person is a legitimate check-in person; S72, data deletion: the central management system searches the authorized personnel information database, finds the facial image data and related information matching the check-out personnel, deletes the facial image data and other related information of the personnel, and cancels the access rights of the personnel; S73, confirmation information: After the data is deleted, the central management system generates a notification to confirm that the check-out is successful. After the front desk staff confirms the information through the preset interactive interface, they confirm to the check-out personnel that the check-out is successful and all entry and exit permissions have been cancelled.

Citation Information

Patent Citations

  • Hotel access personnel management method based on single-sample face recognition

    CN109166196A

  • System for remote access control of jail access way

    CN109830027A

  • Elevator entrance guard control method and device, storage medium and electronic equipment

    CN110002290A

  • Hotel management method and device

    CN110009787A

  • Hotel safety management method based on artificial intelligence

    CN110443923A

Cited By

  • Hotel unmanned check-in system and method based on face recognition

    CN119887454A

  • A hotel unmanned check-in system and method based on face recognition

    CN119887454B

  • Control authority distribution method and system for intelligent hotel

    CN120125388A