Method and system for authenticating power plant personnel, equipment and medium

Abstract

The invention relates to the technical field of face recognition, and discloses a method and system for authenticating power plant personnel, and the method comprises the steps: S1, collecting face images of the power plant personnel, and generating a training set; s2, improving a FaceCNN neural network in combination with a DRNet structure, and constructing an improved face authentication network model; s3, using the training set and the loss function to guide the improved face recognition network model to learn, and outputting the trained improved face recognition network model; and S4, collecting face images of the power plant personnel, inputting the face images into the trained improved face authentication network model, collecting the face images of the power plant personnel in real time, and completing identity authentication of the power plant personnel through information comparison. The system comprises an acquisition unit, a model construction unit and an authentication unit. The invention further discloses electronic equipment and a computer readable storage medium. The safety management level of the power plant is improved, and the reliability and safety of power supply are ensured.

Description

Technical Field

[0001] The present invention relates to the field of face recognition technology, and in particular to a method, system, device and medium for authenticating power plant personnel, which are used to improve the safety management level of the power plant and ensure the reliability and safety of power supply. Background Art

[0002] As an important energy production and supply base, the safety and stability of power plants are crucial to the normal operation of the entire society. Power plants involve a large number of equipment, control systems and sensitive information, so it is necessary to ensure that only authorized personnel can enter and operate related facilities. Strict management of the identity of power plant personnel can effectively prevent unauthorized personnel from entering key areas, thereby ensuring the safe operation of power plants and preventing potential safety accidents.

[0003] First, identity authentication management can ensure the authenticity of the identity of power plant personnel and prevent identity fraud and illegal entry. Through identity authentication, the power plant can accurately identify everyone entering the plant area and ensure that they have the corresponding authority and qualifications. Secondly, identity authentication management helps to record and track the activities of personnel. Once a security incident occurs, the relevant personnel can be quickly located and corresponding measures can be taken. In addition, identity authentication management can also prevent internal personnel from abusing their power or engaging in illegal activities, ensuring that the internal management and operation of the power plant are standardized and orderly.

[0004] In short, managing the identity authentication of power plant personnel is an important measure to ensure the safe, stable and efficient operation of the power plant. Through a strict identity authentication process, the overall safety management level of the power plant can be effectively improved to ensure the reliability and safety of power supply.

[0005] The present invention provides a method and system, device and medium for authenticating power plant personnel, which can accurately identify and verify the identity of power plant employees through an improved face recognition model. Using the present invention, power plants can effectively manage personnel entry and exit, ensuring that only authorized personnel can enter key areas, thereby improving the safety and operational efficiency of power plants. Summary of the invention

[0006] The present invention provides a method, system, device and medium for authenticating power plant personnel, which not only improves the safety management level of the power plant, but also ensures the reliability and safety of power supply.

[0007] The present invention is implemented by the following technical solution: A method for authenticating power plant personnel comprises the following steps:

[0008] Step S1, collecting facial images of power plant personnel, annotating the facial images of the power plant personnel, generating a data set and dividing it into a training set and a test set;

[0009] Step S2, improving the FaceCNN neural network in combination with the structure of DRNet to construct an improved face recognition network model;

[0010] Step S3, using the training set and loss function to guide the learning of the improved face recognition network model, and outputting the trained improved face recognition network model;

[0011] Step S4, collect facial images of power plant personnel, input the facial images of power plant personnel into the trained improved facial recognition network model, generate trained facial images of power plant personnel and store them in the database of the system for authenticating power plant personnel, collect facial images of power plant personnel in real time and complete the identity authentication of power plant personnel through information comparison.

[0012] In order to better implement the present invention, further, the method for improving the FaceCNN neural network in step S2 in combination with the structure of DRNet includes:

[0013] Replace all convolutional layers in the FaceCNN neural network with DRNet.

[0014] In order to better implement the present invention, further, the improved face recognition network model in step S2 includes a feature extraction module and a feature output module connected in sequence from front to back.

[0015] In order to better implement the present invention, further, the feature extraction module includes:

[0016] The feature extraction module includes a first DRNet layer, a first mixed pooling layer, a second DRNet layer, a third DRNet layer, a second mixed pooling layer, a fourth DRNet layer, a fifth DRNet layer, a sixth DRNet layer, a third mixed pooling layer, a seventh DRNet layer, an eighth DRNet layer, a fourth mixed pooling layer, a ninth DRNet layer and a Dropout layer, which are sequentially connected from front to back;

[0017] The first mixed pooling layer includes a first average pooling layer and a first maximum pooling layer connected in parallel, the second mixed pooling layer includes a second average pooling layer and a second maximum pooling layer connected in parallel, the third mixed pooling layer includes a third average pooling layer and a third maximum pooling layer connected in parallel, and the fourth mixed pooling layer includes a fourth average pooling layer and a fourth maximum pooling layer connected in parallel.

[0018] In order to better implement the present invention, further, the structure of the feature output module includes:

[0019] The feature output module includes a fully connected layer, a Softmax layer and a Triplet loss function layer.

[0020] In order to better implement the present invention, further, step S3 includes:

[0021] The loss function is a Triplet loss function;

[0022] The loss function is expressed as:

[0023] Where f(x) represents the embedding function, is the square of the Euclidean distance between the anchor sample and the negative sample in the embedding space.

[0024] In order to better implement the present invention, further, step S4 includes:

[0025] The facial images of power plant personnel are collected in real time. When the collected facial images of power plant personnel are found to exist in the database through information comparison, the authentication of the employee is recorded and released; when the collected facial images of power plant personnel are not found to exist in the database through information comparison, a warning is issued.

[0026] The present invention also provides a system for authenticating power plant personnel, comprising a collection unit, a model building unit and an authentication unit, wherein:

[0027] A collection unit, used for collecting facial images of power plant personnel, annotating the facial images of the power plant personnel, generating a data set and dividing the data set into a training set and a test set;

[0028] A model building unit, used to improve the FaceCNN neural network in combination with the structure of DRNet to build an improved face recognition network model; used to guide the learning of the improved face recognition network model using the training set and loss function, and output the trained improved face recognition network model;

[0029] The authentication unit is used to collect facial images of power plant personnel, input the facial images of power plant personnel into a trained improved facial authentication network model, generate trained facial images of power plant personnel and store them in the database of the system for authenticating power plant personnel, collect facial images of power plant personnel in real time and complete the identity authentication of power plant personnel through information comparison.

[0030] The present invention also provides an electronic device, which includes a processor and a memory; the processor includes the system for authenticating power plant personnel recorded in the second aspect above.

[0031] The present invention also provides a computer-readable storage medium, which includes instructions; when the instructions are executed on the electronic device described in the third aspect, the electronic device executes the method described in the first aspect.

[0032] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0033] (1) The present invention provides a method, system, device, and medium for authenticating power plant personnel. The present invention improves the FaceCNN neural network by combining the DRNet structure, and successfully develops an efficient, accurate, and robust face authentication model suitable for power plant personnel authentication, which not only improves the safety management level of power plants, but also provides strong technical support for other scenarios that require high-precision face recognition technology;

[0034] (2) The present invention provides a method, system, device, and medium for authenticating power plant personnel. The improved face recognition model shows higher robustness and accuracy when processing images with complex backgrounds and different lighting conditions. This enables the model to run stably in various practical application scenarios, reducing false positives and false negatives. In addition, the improved model also has a faster processing speed, and can complete the authentication tasks of a large number of personnel in a short time, greatly improving the efficiency of power plant personnel management. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention is further described in conjunction with the following drawings and embodiments, and all the concepts and innovations of the present invention should be regarded as the disclosed contents and the protection scope of the present invention.

[0036] Figure 1 A method for authenticating power plant personnel and a method flow diagram in a system, device, and medium provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the structure of DRNet in a method, system, device, and medium for authenticating power plant personnel provided in an embodiment of the present application;

[0038] Figure 3 A structural diagram of FaccCNN in a method, system, device, and medium for authenticating power plant personnel provided in an embodiment of the present application;

[0039] Figure 4 A structural diagram of an improved face recognition network model in a method, system, device, and medium for authenticating power plant personnel provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "disposed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] Embodiment 1:

[0043] A method, system, device, and medium for authenticating power plant personnel in this embodiment, such as Figure 1 As shown, the present invention further improves and optimizes the existing FaceCNN neural network by combining the structure of the deep residual network (DRNet). Through these improvements, we have obtained a more powerful and efficient face recognition model. The model performs well in authenticating power plant personnel and can accurately identify and verify the identities of power plant employees. Using the improved face recognition model, power plants can effectively manage personnel entry and exit, ensuring that only authorized personnel can enter key areas, thereby improving the safety and operational efficiency of power plants.

[0044] The improved face recognition model showed higher robustness and accuracy when processing images with complex backgrounds and different lighting conditions. This enables the model to run stably in a variety of practical application scenarios, reducing false positives and false negatives. In addition, the improved model also has a faster processing speed, which can complete the authentication tasks of a large number of people in a short time, greatly improving the efficiency of personnel management in power plants.

[0045] This paper improves the FaceCNN neural network by combining the DRNet structure, and successfully develops an efficient, accurate and robust face recognition model suitable for power plant personnel authentication. This not only improves the safety management level of power plants, but also provides strong technical support for other scenarios that require high-precision face recognition technology.

[0046] Embodiment 2:

[0047] This embodiment is further optimized on the basis of embodiment 1. The DRNet structure is as follows: Figure 2 As shown in the figure, "C" represents data concatenation and "+" represents data addition. In DRNet, any neuron in the i-1th layer is connected to all neurons in the i-th layer (i represents the sequence number of any layer in the hidden layer). In the hidden layer of DRNet, the output of the first i-1 layers is concatenated as the input of the i-th layer to form a densely connected module. At this time, each layer can directly receive the feature information extracted by the previous layers, so that both shallow and deep features are more fully utilized, which strengthens the flow of feature information between hidden layers, can improve the utilization rate of feature information in each layer, and to a certain extent reduces the number of parameters of the network model.

[0048] The present invention introduces the DRNet structure based on FaccCNN, aiming to further improve the performance of face recognition through deeper feature extraction and enhanced feature representation capabilities. The DRNet structure makes full use of the advantages of the residual network (ResNet) and the densely connected network (DenseNet), and realizes the effective extraction and transmission of features through the specially designed RDB.

[0049] The other parts of this embodiment are the same as those of Embodiment 1, and thus will not be described in detail.

[0050] Embodiment 3:

[0051] This embodiment is further optimized on the basis of the above embodiment 1 or 2. Figure 2 As shown in the figure, each convolution layer of FaceCNN is followed by a Maxout layer. Maxout is essentially a forward propagation network. It is a small network structure that converts linear input into nonlinear output. It can be regarded as the activation function layer of a deep convolutional network. FaceCNN uses a combination of maximum pooling and average pooling to retain the background information and texture information of the image to the greatest extent. The specific method is to perform maximum pooling and average pooling on the image after convolution operation and Maxout activation, and cascade the two pooling results as new feature outputs. FaceCNN performs Dropout operation before the Softmax layer. When training the deep network, a certain proportion of neurons are randomly discarded, while these neurons are retained during testing. This method is used to prevent overfitting of the model and improve the generalization ability of the model.

[0052] The other parts of this embodiment are the same as any of the above embodiments 1-2, so they are not repeated here.

[0053] Embodiment 4:

[0054] This embodiment is further optimized based on any one of the above embodiments 1-3. Figure 3As shown, the improved face recognition network model includes a feature extraction module and a feature output module connected from front to back, the feature extraction module includes the first DRNet layer, the first mixed pooling layer, the second DRNet layer, the third DRNet layer, the second mixed pooling layer, the fourth DRNet layer, the fifth DRNet layer, the sixth DRNet layer, the third mixed pooling layer, the seventh DRNet layer, the eighth DRNet layer, the fourth mixed pooling layer, the ninth DRNet layer and the Dropout layer connected from front to back; the first mixed pooling layer includes the first average pooling layer and the first maximum pooling layer connected in parallel, the second mixed pooling layer includes the second average pooling layer and the second maximum pooling layer connected in parallel, the third mixed pooling layer includes the third average pooling layer and the third maximum pooling layer connected in parallel, and the fourth mixed pooling layer includes the fourth average pooling layer and the fourth maximum pooling layer connected in parallel. The structure of the feature output module includes a fully connected layer, a Softmax layer and a Triplet loss function layer.

[0055] Specifically, we introduced the deep residual connection of DRNet to solve the gradient vanishing problem that may occur during training, thereby improving the training efficiency and convergence speed of the model. In the improved face authentication network model, DRNet was introduced to adjust the convolutional layer and pooling layer of FaceCNN to better extract facial features.

[0056] The other parts of this embodiment are the same as any one of the above embodiments 1-3, so they are not repeated here.

[0057] Embodiment 5:

[0058] This embodiment is further optimized based on any one of the above embodiments 1-4, and the loss function is a Triplet loss function, which is expressed as: Among them, f(x) represents the embedding function, a represents the anchor sample, p is the positive sample, n is the negative sample, For anchor samples and negative samples in the embedding space, the Triplet loss function aims to ensure that the distance between the anchor sample and the positive sample is less than the square of the Euclidean distance between the anchor sample and the negative sample plus a preset margin. In order to improve the efficiency of training and the performance of the model, it is very important to select appropriate Triplet samples. Samples that are too simple or too difficult should be avoided. A commonly used strategy is to select semi-hard samples.

[0059] The other parts of this embodiment are the same as any one of the above embodiments 1-4, so they are not repeated here.

[0060] Embodiment 6:

[0061] The present invention also provides a system for authenticating power plant personnel that matches the method, including a collection unit, a model building unit and an authentication unit.

[0062] The present invention also provides an electronic device, which includes a processor and a memory; the processor includes the system for authenticating power plant personnel as described above.

[0063] Embodiment 7:

[0064] The present invention also provides a computer-readable storage medium, which includes instructions; when the instructions are executed on the electronic device described in the above embodiment, the electronic device executes the method described in the above embodiment. Optionally, the computer-readable storage medium may be a memory.

[0065] The processor involved in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0066] The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0067] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not 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 embodiments of the present application.

[0068] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0070] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0071] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one device or distributed on multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0072] In addition, each functional module in each embodiment of the present application may be integrated into one device, or each module may exist physically separately, or two or more modules may be integrated into one device.

[0073] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing a computer program instruction on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may contain one or more servers, data centers and other data storage devices that can be integrated with a medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0074] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification or equivalent change made to the above embodiment based on the technical essence of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for authenticating power plant personnel, characterized in that: The following steps are involved: Step S1, collecting facial images of power plant personnel, annotating the facial images of the power plant personnel, generating a data set and dividing it into a training set and a test set; Step S2, improving the FaceCNN neural network in combination with the structure of DRNet to construct an improved face recognition network model; Step S3, using the training set and loss function to guide the learning of the improved face recognition network model, and outputting the trained improved face recognition network model; Step S4, collect facial images of power plant personnel, input the facial images of power plant personnel into the trained improved facial recognition network model, generate trained facial images of power plant personnel and store them in the database of the system for authenticating power plant personnel, collect facial images of power plant personnel in real time and complete the identity authentication of power plant personnel through information comparison.

2. A method for authenticating power plant personnel according to claim 1, characterized in that: The method for improving the FaceCNN neural network in step S2 by combining the structure of DRNet includes: Replace all convolutional layers in the FaceCNN neural network with DRNet.

3. A method for authenticating power plant personnel according to claim 1, characterized in that: The improved face recognition network model in step S2 includes a feature extraction module and a feature output module connected in sequence from front to back.

4. A method for authenticating power plant personnel according to claim 3, characterized in that: The feature extraction module includes: the feature extraction module includes a first DRNet layer, a first mixed pooling layer, a second DRNet layer, a third DRNet layer, a second mixed pooling layer, a fourth DRNet layer, a fifth DRNet layer, a sixth DRNet layer, a third mixed pooling layer, a seventh DRNet layer, an eighth DRNet layer, a fourth mixed pooling layer, a ninth DRNet layer and a Dropout layer connected sequentially from front to back; The first mixed pooling layer includes a first average pooling layer and a first maximum pooling layer connected in parallel, the second mixed pooling layer includes a second average pooling layer and a second maximum pooling layer connected in parallel, the third mixed pooling layer includes a third average pooling layer and a third maximum pooling layer connected in parallel, and the fourth mixed pooling layer includes a fourth average pooling layer and a fourth maximum pooling layer connected in parallel.

5. A method for authenticating power plant personnel according to claim 3, characterized in that: The structure of the feature output module includes: The feature output module includes a fully connected layer, a Softmax layer and a Triplet loss function layer.

6. A method for authenticating power plant personnel according to claim 1, characterized in that: The step S3 comprises: The loss function is a Triplet loss function; The loss function is expressed as: Where f(x) represents the embedding function, is the square of the Euclidean distance between the anchor sample and the negative sample in the embedding space.

7. A method for authenticating power plant personnel according to claim 1, characterized in that: The step S4 comprises: The facial images of power plant personnel are collected in real time. When the collected facial images of power plant personnel are found to exist in the database through information comparison, the authentication of the employee is recorded and released; when the collected facial images of power plant personnel are not found to exist in the database through information comparison, a warning is issued.

8. A system for authenticating power plant personnel, characterized in that: It includes a collection unit, a model building unit and an authentication unit, wherein: the collection unit is used to collect facial images of power plant personnel, annotate the facial images of the power plant personnel, generate a data set and divide it into a training set and a test set; A model building unit, used to improve the FaceCNN neural network in combination with the structure of DRNet to build an improved face recognition network model; used to guide the learning of the improved face recognition network model using the training set and loss function, and output the trained improved face recognition network model; The authentication unit is used to collect facial images of power plant personnel, input the facial images of power plant personnel into a trained improved facial authentication network model, generate trained facial images of power plant personnel and store them in the database of the system for authenticating power plant personnel, collect facial images of power plant personnel in real time and complete the identity authentication of power plant personnel through information comparison.

9. An electronic device, characterized in that: It comprises a processor and a memory; the processor includes the system for authenticating power plant personnel as claimed in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes instructions; when the instructions are executed on the electronic device as claimed in claim 9, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.

Images