Numerical control machine tool operation authority management system based on face recognition

Abstract

The invention relates to the technical field of operation authority management, and discloses a numerical control machine tool operation authority management system based on face recognition, which comprises a face recognition unit, a face database, a communication unit and an authority management unit, the human face recognition unit performs accurate recognition, and unauthorized personnel cannot operate due to no database corresponding human face feature data, so that misoperation is prevented; the authority management unit calculates the matching degree by using a Euclidean distance formula and a cosine similarity formula, so that the recognition accuracy is improved, and the system security is guaranteed; the human body sensor performs infrared detection and is automatically started when a person enters a sensing range, and the industrial computer controls the camera to collect images without manual operation; the authority management unit can quickly acquire authority information and send the authority information to the numerical control machine tool through the communication unit, thereby improving operation efficiency; face data are stored in a relational database in a structured mode with job numbers as main keys, and management is convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of operation authority management, and in particular to a numerical control machine tool operation authority management system based on face recognition. Background Art

[0002] With the development of manufacturing industry, CNC machine tools play a vital role in industrial production. However, there are some urgent problems in the management of CNC machine tool operation rights.

[0003] In the traditional CNC machine tool operation authority management mode, most of them rely on manual allocation, such as restricting access to the machine tool through keys, access cards or simple password systems. These methods have many disadvantages. First, keys or access cards are easy to be lost, stolen or copied. Once they fall into the hands of unauthorized personnel, they can easily obtain the operation rights of the CNC machine tool, which may lead to misoperation, damage to the machine tool, scrapping of processed workpieces, and even safety accidents, posing a threat to the personal safety of operators. Password systems have the risk of password leakage. For example, if the operator records the password in an easily accessible place for easy memory, or sets a password that is too simple, unauthorized personnel may crack the password and enter the system.

[0004] In addition, in complex production environments, where multiple personnel and multiple shifts are common, traditional management methods make it difficult to accurately and quickly identify and authorize the specific permissions of each operator, resulting in chaotic permission management. Moreover, with the expansion of enterprise scale and the improvement of production automation, the demand for refined and intelligent management of CNC machine tool operation permissions is becoming more urgent.

[0005] At the same time, face recognition technology has developed rapidly in recent years, and has shown significant advantages in accuracy, convenience and security. Applying face recognition technology to CNC machine tool operation authority management can effectively overcome the shortcomings of traditional management methods, achieve accurate identification of operators and precise management of authority, and meet the dual requirements of modern manufacturing for production safety and efficiency. Summary of the invention

[0006] The purpose of the present invention is to provide a CNC machine tool operation authority management system based on face recognition, which solves the technical problems raised in the background technology.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A CNC machine tool operation authority management system based on face recognition, the system consists of software and hardware parts;

[0009] The software part includes:

[0010] A face recognition unit, used to extract and recognize facial features of operators;

[0011] Extraction and recognition is to obtain the face image through the camera, and then locate the feature points and extract the feature vector;

[0012] A face database is used to store the face feature data and corresponding operation authority information of all operators who have been authorized in advance;

[0013] Communication unit, used for data exchange with CNC machine tools;

[0014] The permission management unit is used to search for corresponding operation permissions in the face database according to the face recognition result;

[0015] The hardware part includes:

[0016] Human body sensor, which uses infrared sensing technology to detect whether the operator is within the sensing range;

[0017] The camera, under the control of the industrial computer, collects images of operators within the sensing range;

[0018] Industrial computer, which is the core control part, is used to coordinate the work of the hardware part and support the operation of the software part;

[0019] The server is used to store the face database and provide data query and management services.

[0020] As a further solution of the present invention: the detection method of the human body sensor is as follows:

[0021] Among them, the human body sensor adopts an infrared human body sensor, which determines whether the operator is within the sensing range by detecting the infrared rays emitted by the human body;

[0022] When the infrared human body sensor detects a human body and the infrared intensity emitted by it exceeds a predetermined infrared intensity threshold, it is determined that an operator is within the sensing range;

[0023] As a further solution of the present invention: wherein, the industrial computer is used to receive signals from a human body sensor, and at the same time control the camera to capture images and run a face recognition algorithm, and communicate with a server and a CNC machine tool.

[0024] As a further solution of the present invention: the permission management unit is as follows:

[0025] StepA1, extract n feature vectors obtained by the face recognition unit and mark them as A = (a1, a2, ... an);

[0026] Step A2, extracting facial feature data of each operator from the face database, selecting facial feature data corresponding to an operator, and marking n feature vectors therein as B = (b1, b2, ... bn);

[0027] StepA3, calculate the matching degree between A and B through the Euclidean distance formula;

[0028] The Euclidean distance formula is as follows:

[0029]

[0030] Where D (A，B) is the matching degree between A and B, i = 1, 2, ... n, i represents the nth eigenvector;

[0031] StepA4: Compare the matching degree between A and B with the preset matching degree threshold:

[0032] If the matching degree between A and B is greater than the matching degree threshold, it is determined that the extraction result of the operator identification by the face recognition unit successfully matches the facial feature data of the operator in the face database, and then the operation authority information corresponding to the facial feature data is obtained;

[0033] Otherwise, it is determined that the extraction result of the operator identification by the face recognition unit is not matched successfully with the facial feature data of the operator in the face database, and then the extraction result of the operator identification by the face recognition unit is matched with the facial feature data of other operators in the face database until the match is successful or the facial feature data of all operators in the face database are matched;

[0034] Step A5, the operation authority information extracted in Step A4 is sent to the CNC machine tool through the communication unit. The CNC machine tool determines and allows the operator to perform operations based on the received authority information.

[0035] As a further solution of the present invention: if the face recognition result has no corresponding face feature data in the face database, it means that the corresponding person does not have the operation authority for the CNC machine tool.

[0036] As a further solution of the present invention: in Step A3 of the rights management unit, the matching degree between A and B is calculated by the cosine similarity formula;

[0037] The cosine similarity formula is as follows:

[0038]

[0039] Where Y (A，B)is the matching degree between A and B, i=1, 2, ... n, i represents the nth eigenvector, A·B represents the dot product between A and B, |A| represents the modulus of A; B| represents the modulus of B.

[0040] As a further solution of the present invention: wherein the communication unit adopts any one of the Modbus protocol or the Profibus protocol.

[0041] As a further solution of the present invention: wherein the facial feature data and its corresponding operation authority information are stored in a structured manner;

[0042] Among them, the face database adopts a relational database, with the operator's unique identifier as the primary key, and then establishes an association with the face feature vector and operation authority information. Among them, the unique identifier uses the operator's work number, and the work number is unique.

[0043] As a further solution of the present invention: wherein, the extraction and recognition technology of the operator's facial features in the face recognition unit is implemented by the following prior art:

[0044] Face detection technology based on feature templates, which defines several face templates, matches the input image with the templates, and determines whether it is a human face based on the degree of match;

[0045] Regression-based feature point location technology estimates the location of feature points by directly using the discriminant features around the feature points; such as using support vector regression: it predicts the location of feature points based on the input face image features;

[0046] The feature vector extraction technology based on principal component analysis regards the face image as a high-dimensional vector, projects it into a low-dimensional space through the PCA algorithm, extracts the main feature components, and forms a feature vector.

[0047] Beneficial effects of the present invention:

[0048] Accurately identify operators: The facial features of operators are extracted and identified through the face recognition unit to ensure that only authorized personnel can operate CNC machine tools. When the face recognition result does not have corresponding facial feature data in the face database, the corresponding personnel do not have operation permissions, effectively preventing unauthorized personnel from misoperation and reducing security risks.

[0049] Multi-dimensional matching ensures accuracy: The permission management unit uses the Euclidean distance formula and the cosine similarity formula to calculate the matching degree between feature vectors, which improves the accuracy and reliability of face recognition and further enhances the security of the system.

[0050] Intelligent induction start: The human body sensor of the hardware part uses infrared induction technology to detect whether the operator is within the sensing range. When an operator is detected within the sensing range, the industrial computer controls the camera to collect images, without the operator manually starting the recognition system, which improves the convenience and efficiency of operation.

[0051] Quick permission acquisition: The permission management unit can quickly search for the corresponding operation permission in the face database according to the face recognition results, and send the operation permission information to the CNC machine tool through the communication unit, so that the operator can quickly obtain the operation permission and improve work efficiency.

[0052] Multiple communication protocols: The communication unit adopts either Modbus protocol or Profibus protocol. You can select the appropriate communication protocol according to actual needs to interact with CNC machine tools, with high flexibility and compatibility.

[0053] Structured storage: Facial feature data and its corresponding operation permission information are stored in a relational database in a structured manner, with the operator's unique identifier (employee number) as the primary key, and an association is established with the facial feature vector and operation permission information to facilitate data query, management and maintenance.

[0054] Advanced face recognition technology: The facial recognition unit uses existing advanced technologies such as face detection technology based on feature templates, feature point positioning technology based on regression, and feature vector extraction technology based on principal component analysis to extract and identify the operator's facial features, ensuring the accuracy and stability of face recognition.

[0055] Industrial computer core control: As the core control part, the industrial computer coordinates the work of the hardware part and supports the operation of the software part to ensure the stable and efficient operation of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] Figure 1 The present invention discloses a system block diagram of the software part of a numerical control machine tool operation authority management system based on face recognition.

[0058] Figure 2 It is a flow chart of the hardware part of a CNC machine tool operation authority management system based on face recognition in the present invention. DETAILED DESCRIPTION

[0059] 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 only 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.

[0060] Embodiment 1

[0061] See also Figure 1 As shown, the present invention is a CNC machine tool operation authority management system based on face recognition, comprising:

[0062] A face recognition unit, used to extract and recognize facial features of operators;

[0063] Extraction and recognition is to obtain the face image through the camera, and then locate the feature points and extract the feature vector;

[0064] In this embodiment, the extraction and recognition technology of the operator's facial features in the face recognition unit is an existing technology, which is mainly implemented by the following existing technologies:

[0065] Face detection technology based on feature templates, which defines several face templates, matches the input image with the templates, and determines whether it is a human face based on the degree of match;

[0066] Regression-based feature point location technology estimates the location of feature points by directly using the discriminant features around the feature points; such as using support vector regression: it predicts the location of feature points based on the input face image features;

[0067] The feature vector extraction technology based on principal component analysis treats the face image as a high-dimensional vector, projects it into a low-dimensional space through the PCA algorithm, extracts the main feature components, and forms a feature vector;

[0068] A face database is used to store the face feature data and corresponding operation authority information of all operators who have been authorized in advance;

[0069] Among them, facial feature data and its corresponding operation permission information are stored in a structured manner;

[0070] In this embodiment, a relational database is used, with the operator's unique identifier as the primary key, and then an association is established with the facial feature vector and the operation authority information, wherein the unique identifier is the operator's work number, and the work number is unique;

[0071] Communication unit, used for data exchange with CNC machine tools;

[0072] In this embodiment, the communication unit adopts any one of the Modbus protocol or the Profibus protocol;

[0073] The permission management unit is used to search for corresponding operation permissions in the face database according to the face recognition result;

[0074] The specific method is as follows:

[0075] StepA1, extract n feature vectors obtained by the face recognition unit and mark them as A = (a1, a2, ... an);

[0076] Step A2, extracting facial feature data of each operator from the face database, selecting facial feature data corresponding to an operator, and marking n feature vectors therein as B = (b1, b2, ... bn);

[0077] StepA3, calculate the matching degree between A and B through the Euclidean distance formula;

[0078] The Euclidean distance formula is as follows:

[0079]

[0080] Where D (A，B) is the matching degree between A and B, i = 1, 2, ... n, i represents the nth eigenvector;

[0081] StepA4: Compare the matching degree between A and B with the preset matching degree threshold:

[0082] If the matching degree between A and B is greater than the matching degree threshold, it is determined that the extraction result of the operator identification by the face recognition unit successfully matches the facial feature data of the operator in the face database, and then the operation authority information corresponding to the facial feature data is obtained;

[0083] Otherwise, it is determined that the extraction result of the operator identification by the face recognition unit is not matched successfully with the facial feature data of the operator in the face database, and then the extraction result of the operator identification by the face recognition unit is matched with the facial feature data of other operators in the face database until the match is successful or the facial feature data of all operators in the face database are matched;

[0084] In this embodiment, if the face recognition result has no corresponding face feature data in the face database, it means that the corresponding person does not have the operation authority for the CNC machine tool;

[0085] Step A5, sending the operation authority information extracted in Step A4 to the CNC machine tool through the communication unit, and the CNC machine tool determines and allows the operator to perform operations based on the received authority information;

[0086] In this embodiment, it is possible to achieve accurate management of the CNC machine tool operation authority. At the same time, the CNC machine tool is also used to record the operator's operation content, including but not limited to operation time, operation instructions and other information, for subsequent production management and data analysis;

[0087] This embodiment 1 uses mature face recognition technology to achieve accurate identification of CNC machine tool operators, ensuring that only authorized personnel can operate the machine tool, thereby improving operational safety. The facial feature data and operation authority information are stored in a structured manner through a relational database, which is convenient for management and query, and the work number is used as a unique identifier to ensure the accuracy and uniqueness of the data. The Modbus protocol or Profibus protocol is used to interact with the CNC machine tool to ensure the stability and reliability of data transmission. Through precise authority management, unauthorized personnel can be effectively prevented from operating the machine tool. At the same time, the CNC machine tool records the operator's operation content, which is helpful for subsequent production management and data analysis.

[0088] Embodiment 2

[0089] As the second embodiment of the present invention, when the present application is specifically implemented, compared with the first embodiment, the technical solution of the present embodiment is different from the first embodiment only in that in the present embodiment, in Step A3 of the rights management unit, the matching degree between A and B is calculated by the cosine similarity formula;

[0090] The cosine similarity formula is as follows:

[0091]

[0092] Where Y (A，B) is the matching degree between A and B, i=1, 2, ... n, i represents the nth eigenvector, A·B represents the dot product between A and B, |A| represents the modulus of A; B| represents the modulus of B.

[0093] Based on the first embodiment, this embodiment adds the cosine similarity formula to calculate the matching degree between feature vectors, thereby improving the accuracy and reliability of face recognition. Multiple matching degree calculation methods can verify each other, further ensuring the correctness of the recognition result.

[0094] Embodiment 3

[0095] See also Figure 2As shown, as the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is that in this embodiment, the system consists of a software part and a hardware part;

[0096] Among them, the software part consists of a face recognition unit, a face database, a communication unit, and a permission management unit;

[0097] The hardware part includes:

[0098] Human body sensor, which uses infrared sensing technology to detect whether the operator is within the sensing range;

[0099] Among them, the infrared human body sensor determines whether the operator is within the sensing range by detecting the infrared rays emitted by the human body;

[0100] When the infrared human body sensor detects a human body and the infrared intensity emitted by it exceeds a predetermined infrared intensity threshold, it is determined that an operator is within the sensing range;

[0101] The camera, under the control of the industrial computer, collects images of operators within the sensing range;

[0102] In this embodiment, the parameters corresponding to the resolution and frame rate of the camera are selected according to the actual application scenario requirements. For example, a camera with a resolution of 1920×1080 and a frame rate of 30fps is selected, which can meet the face recognition requirements in most factory environments to ensure that face images can be acquired clearly and quickly.

[0103] Industrial computer, which is the core control part, is used to coordinate the work of the hardware part and support the operation of the software part;

[0104] In this embodiment, the industrial computer receives the signal from the human body sensor, controls the camera to collect images, runs the face recognition algorithm, and communicates with the server and the CNC machine tool;

[0105] The server is used to store the face database and provide data query and management services.

[0106] In this embodiment, the software part cooperates closely with various units related to face recognition, and can realize efficient face recognition and authority management. The human body sensor of the hardware part adopts infrared sensing technology, which can quickly detect whether the operator is within the sensing range, improving the response speed and energy saving of the system. Selecting a camera with appropriate parameters can meet the face recognition needs in most factory environments, ensure clear and fast acquisition of face images, and improve recognition efficiency. As the core control part, the industrial computer coordinates the hardware work and supports the software operation to ensure the stable operation of the entire system. The server stores the face database and provides data query and management services, which facilitates the centralized management and maintenance of data.

[0107] Embodiment 4

[0108] As the fourth embodiment of the present invention, when the present application is specifically implemented, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second and third embodiments.

[0109] This embodiment combines all the advantages of embodiments one, two and three, and realizes a more powerful and more complete CNC machine tool operation authority management function based on face recognition.

[0110] By combining and implementing multiple solutions, the stability, accuracy and reliability of the system are improved, which can better meet the needs of actual production.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0112] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A CNC machine tool operation authority management system based on face recognition, characterized in that: The system consists of software and hardware parts; The software part includes: A face recognition unit is used to extract and recognize the facial features of the operator based on face detection technology, feature point positioning technology and feature vector extraction technology, and obtain a feature vector extraction of the operator's corresponding face; A face database is used to store the face feature data and corresponding operation authority information of all operators who have been authorized in advance; Communication unit, used for data exchange with CNC machine tools; The permission management unit is used to search for corresponding operation permissions in the face database according to the face recognition result; The hardware part includes: Human body sensor, which uses infrared sensing technology to detect whether the operator is within the sensing range; The camera, under the control of the industrial computer, collects images of operators within the sensing range; Industrial computer, which is the core control part, is used to coordinate the work of the hardware part and support the operation of the software part; The server is used to store the face database and provide data query and management services.

2. According to claim 1, a CNC machine tool operation authority management system based on face recognition is characterized in that: The permission management unit is as follows: StepA1, extract n feature vectors obtained by the face recognition unit and mark them as A = (a1, a2, ... an); Step A2, extracting facial feature data of each operator from the face database, selecting facial feature data corresponding to an operator, and marking n feature vectors therein as B = (b1, b2, ... bn); StepA3, calculate the matching degree between A and B by using the Euclidean distance formula or the cosine similarity formula; Step A4, compare the matching degree between A and B with the preset matching degree threshold, and determine whether the extraction result of the face recognition unit for the operator is successfully matched with the face feature data of the corresponding operator in the face database based on the comparison result: Then, according to the successful matching result, the operation permission information corresponding to the corresponding facial feature data is obtained; Step A5, the operation authority information extracted in Step A4 is sent to the CNC machine tool through the communication unit. The CNC machine tool determines and allows the operator to perform operations based on the received authority information.

3. According to claim 2, a CNC machine tool operation authority management system based on face recognition is characterized in that: The comparison method in StepA3 is as follows: If the matching degree between A and B is greater than the matching degree threshold, it is determined that the extraction result of the operator identification by the face recognition unit successfully matches the facial feature data of the operator in the face database, and then the operation authority information corresponding to the facial feature data is obtained; Otherwise, it is determined that the extraction result of the face recognition unit's identification of the operator does not match the facial feature data of the operator in the face database successfully, and then the extraction result of the face recognition unit's identification of the operator is matched with the facial feature data of other operators in the face database until the match is successful or the facial feature data of all operators in the face database are matched.

4. According to claim 2, a CNC machine tool operation authority management system based on face recognition is characterized in that: In StepA3, the Euclidean distance formula is as follows: Where D (A，B) is the matching degree between A and B, i=1, 2, ... n, i represents the nth eigenvector.

5. The CNC machine tool operation authority management system based on face recognition according to claim 2 is characterized in that: In StepA3, the cosine similarity formula is as follows: Where Y (A，B) is the matching degree between A and B, i = 1, 2, ... n, i represents the nth eigenvector, A·B represents the dot product between A and B, |A| represents the modulus of A; B | Represents the modulus of B.

6. The CNC machine tool operation authority management system based on face recognition according to claim 2 is characterized in that: in, If the face recognition result has no corresponding face feature data in the face database, it means that the corresponding person does not have the operation authority for the CNC machine tool.

7. The CNC machine tool operation authority management system based on face recognition according to claim 1 is characterized in that: in, The communication unit adopts either Modbus protocol or Profibus protocol.

8. The CNC machine tool operation authority management system based on face recognition according to claim 1 is characterized in that: in, Facial feature data and its corresponding operation permission information are stored in a structured manner; Among them, the face database adopts a relational database, with the operator's unique identifier as the primary key, and then establishes an association with the face feature vector and operation authority information. Among them, the unique identifier uses the operator's work number, and the work number is unique.

9. The CNC machine tool operation authority management system based on face recognition according to claim 1, characterized in that: The detection method of the human body sensor is as follows: Among them, the human body sensor adopts an infrared human body sensor, which determines whether the operator is within the sensing range by detecting the infrared rays emitted by the human body; When the infrared human body sensor detects a human body and the infrared intensity emitted by the human body exceeds a predetermined infrared intensity threshold, it is determined that an operator is within the sensing range.

10. The CNC machine tool operation authority management system based on face recognition according to claim 1, characterized in that: in, The industrial computer is used to receive signals from human body sensors, control the camera to capture images and run face recognition algorithms, and communicate with servers and CNC machine tools.

Images