CN114898475A - Underground personnel identity identification method and device, electronic equipment and readable storage medium - Google Patents
Underground personnel identity identification method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN114898475A CN114898475A CN202210523280.9A CN202210523280A CN114898475A CN 114898475 A CN114898475 A CN 114898475A CN 202210523280 A CN202210523280 A CN 202210523280A CN 114898475 A CN114898475 A CN 114898475A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- face
- similarity
- personnel
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000007613 environmental effect Effects 0.000 claims abstract description 49
- 230000010365 information processing Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 9
- 230000001815 facial effect Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
Abstract
The application provides a method and a device for identifying identities of underground personnel, electronic equipment and a readable storage medium, and relates to the technical field of identity identification, wherein the method comprises the following steps: acquiring face information and voiceprint information of a person to be identified; matching the face information with face information to be matched in a face feature database based on the face information, determining face confidence and face feature similarity, and matching the voiceprint information with voiceprint information to be matched, which belongs to the same person as the face information to be matched, in a voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity; determining an environment penalty factor (representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition) according to the face confidence coefficient and the voiceprint confidence coefficient; and determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor so as to identify the identity. The method and the device can improve the accuracy of identity recognition of personnel in complex environments such as underground and the like or in severe environments.
Description
Technical Field
The present application relates to the field of identity recognition technologies, and in particular, to a method and an apparatus for identifying identities of downhole personnel, an electronic device, and a readable storage medium.
Background
For the detection of personnel identity in scenes with unstable advantages and disadvantages of underground and other environmental conditions, the traditional method usually adopts manual detection and is limited by the influence of scene environments, and the prior art also adopts fingerprint identification and face identification to identify personnel identity. However, fingerprint identification is difficult to manage underground, so that the method is not suitable for fingerprint identification, and human face identification is easily interfered by more serious factors of the environment, so that the identity of a person cannot be accurately judged.
Disclosure of Invention
The application aims to provide a method and a device for identifying the identity of underground personnel, electronic equipment and a readable storage medium, which can improve the accuracy of identifying the identity of the underground personnel in complex or severe environments.
In a first aspect, the present invention provides a method for identifying the identity of a downhole person, comprising: acquiring face information and voiceprint information of a person to be identified; matching with face information to be matched in a face feature database based on the face information, determining face confidence and face feature similarity, matching with voiceprint information to be matched in a voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity; the method comprises the steps that face information to be matched in a face feature database and voiceprint information to be matched in a voiceprint feature database belong to the same matched object; determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient; the environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition; and determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor, and identifying the identity of the personnel to be identified based on the similarity of the personnel.
In an alternative embodiment, the environmental penalty factors include a first environmental penalty factor for face recognition and a second environmental penalty factor for voiceprint recognition; determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient, wherein the environment penalty factor comprises the following steps: merging the face confidence coefficient and the voiceprint confidence coefficient to obtain a reference datum; determining a first environment penalty factor based on the face confidence coefficient and a reference standard, wherein the first environment penalty factor is used as a reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence coefficient and the reference benchmark, wherein the second environment penalty factor is used as a reference weight of the similarity of the voiceprint features.
In an alternative embodiment, determining an environmental penalty factor based on the face confidence and the voiceprint confidence includes: determining a first environment penalty factor based on the face confidence, the reference standard and the underground environment parameters, and using the first environment penalty factor as the reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence, the reference benchmark and the underground environment parameters, wherein the second environment penalty factor is used as a reference weight of the voiceprint feature similarity.
In an alternative embodiment, the downhole environment parameters include at least a downhole brightness value and a downhole noise volume; determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient, wherein the environment penalty factor comprises the following steps: determining a first environment penalty factor based on the face confidence, the reference standard and the underground brightness value, and using the first environment penalty factor as the reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence, the reference benchmark and the underground noise volume, wherein the second environment penalty factor is used as a reference weight of the voiceprint feature similarity.
In an alternative embodiment, determining the similarity of the person based on the similarity of the face features, the similarity of the voiceprint features and the environmental penalty factor includes: determining face reference similarity based on the face feature similarity and a first environment penalty factor; determining the voiceprint reference similarity based on the voiceprint feature similarity and the second environment penalty factor; and determining the similarity of the persons based on the face reference similarity and the voiceprint reference similarity.
In an optional embodiment, the identity recognition of the person to be recognized based on the similarity of the persons includes: and when the similarity of the persons exceeds a specified threshold value, determining the persons to be identified as authorized persons.
In an optional embodiment, the identity recognition of the person to be recognized based on the similarity of the persons includes: and starting timing after the personnel similarity is obtained, and determining the personnel to be identified as the authorized personnel when the time length of the personnel similarity exceeding the specified threshold exceeds the time threshold.
In a second aspect, the present invention provides a downhole personnel identification device, comprising: the information acquisition module is used for acquiring the face information and the voiceprint information of the person to be identified; the information processing module is used for matching with the face information to be matched in the face feature database based on the face information, determining face confidence and face feature similarity, and matching with the voiceprint information to be matched in the voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity; the method comprises the steps that face information to be matched in a face feature database and voiceprint information to be matched in a voiceprint feature database belong to the same matched object; the determining module is used for determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient; the environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition; and the identity recognition module is used for determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor so as to identify the personnel to be recognized according to the similarity of the personnel.
In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the downhole personnel identification method according to any one of the preceding embodiments.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer executable instructions which, when invoked and executed by a processor, cause the processor to carry out the method of downhole personal identification of any one of the preceding embodiments.
The application provides a method and a device for identifying the identity of underground personnel, electronic equipment and a readable storage medium, the method comprises the steps of firstly obtaining face information and voiceprint information of a person to be identified, matching the face information with face information to be matched in a face feature database based on the face information, determining face confidence and face feature similarity, matching the voiceprint information with voiceprint information to be matched belonging to the same matching object in a voiceprint feature database based on the voiceprint information, determining voiceprint confidence and voiceprint feature similarity, then determining an environment penalty factor of reference weight for representing the similarity of the face features and the similarity of the voiceprint features under the current environment condition according to the face confidence coefficient and the voiceprint confidence coefficient, and then determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor, and finally identifying the identity of the personnel to be identified based on the similarity of the personnel. According to the method, after the face similarity and the voiceprint similarity are obtained, the environmental penalty factors of the face feature similarity and the voiceprint feature similarity during personnel identity recognition are determined according to the environmental conditions, so that the reference threshold values of the current face feature similarity and the voiceprint feature similarity can be determined according to the environmental factors, personnel identity recognition is performed, and the accuracy of the personnel identity recognition in complex environments such as underground or severe environments is improved.
Drawings
In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings needed to be used in the detailed description of the present application or the prior art description will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for identifying the identity of a downhole person according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a specific method for identifying the identity of downhole personnel provided by an embodiment of the present application;
fig. 3 is a structural diagram of a downhole personnel identification device according to an embodiment of the present application;
fig. 4 is a structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
With the development of artificial intelligence technology and 5G technology, the application of artificial intelligence in the intelligent detection direction is more and more extensive, and is influenced by factors such as environment, the method for detecting the identity of underground personnel cannot only rely on a computer vision algorithm, and because the underground environment is complex, the identification effect is poor due to the environmental influence, errors are easy to occur in the identity identification of the personnel.
At present, the identity of a person is generally identified in a traditional way, such as manual observation, but the method is relatively high in manpower consumption. The fingerprint identification method can also be used in the related technology, but the underground management is difficult, so the method is not suitable for fingerprint identification, and if the method only depends on a face identification algorithm, the method is often interfered by various factors, so the identity of the current personnel cannot be accurately judged. Based on this, the embodiment of the application provides an underground personnel identity identification method, an underground personnel identity identification device, an electronic device and a readable storage medium, which can determine the current reference threshold values of the face feature similarity and the voiceprint feature similarity according to environmental factors so as to identify personnel identities and improve the accuracy of identification of personnel identities in complex environments such as underground and the like or in severe environments.
The embodiment of the application provides an underground personnel identity identification method, and as shown in figure 1, the method mainly comprises the following steps:
and step S110, acquiring the face information and the voiceprint information of the person to be identified.
The face information can be acquired through image acquisition equipment of the area to be detected, and the face information is obtained by extracting the image information acquired by the image acquisition equipment through a face recognition algorithm.
The voiceprint information can be acquired through the sound sensor of the area to be detected, and in order to ensure the accuracy of the voiceprint information, the voiceprint information acquired by the sound sensor can be filtered, denoised, enhanced and the like to obtain the voiceprint information.
And step S120, matching the face information with the face information to be matched in the face feature database based on the face information, determining face confidence and face feature similarity, and matching the voiceprint information with the voiceprint information to be matched in the voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity.
When a person enters a region to be detected, image acquisition equipment (such as a camera) transmits a captured image to a face recognition model, the face recognition model detects face features (such as face position, size and the like) and face confidence, and the face feature similarity between the current face and the face in the database is calculated.
The voiceprint confidence and the voiceprint feature similarity are determined based on the voiceprint information, voiceprint features (such as tone, frequency and the like) and the voiceprint confidence can be detected through the voiceprint recognition model, the voiceprint features and the voiceprint confidence are matched with the voiceprint information in the database, and the voiceprint feature similarity between the current voiceprint features and the database is calculated.
The face information to be matched in the face feature database and the voiceprint information to be matched in the voiceprint feature database belong to the same matching object. In one implementation, the similarity between the person to be tested and the face in the face feature database can be calculated firstly, then the voiceprint information of the same person is taken from the voiceprint database, the voiceprint similarity between the person to be tested and the person is calculated, and by analogy, the similarity between the person to be tested and each person in the database is calculated; in another embodiment, the similarity between the person to be measured and the voiceprint in the voiceprint database may be calculated first, then the face information of the same person is obtained from the face feature database, the similarity between the person to be measured and the face of the person is calculated, and so on, the similarity between the person to be measured and each person in the database is calculated.
And step S130, determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient.
Because the influence of factors such as light, noise, personnel's facial sheltering from among the complex environment such as pit, when carrying out personnel's identification, in order to promote personnel's discernment accuracy, need combine face identification and voiceprint discernment to confirm that current discernment environmental condition is more favorable to computer vision or computer sense of hearing, with the accuracy of guaranteeing personnel's identification.
The environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition.
And step S140, determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor, and identifying the identity of the personnel to be identified based on the similarity of the personnel.
After the environment penalty factor is determined, the environment penalty factor can be used as a reference, and the final person similarity is determined by combining the face feature similarity and the voiceprint feature similarity.
According to the method for identifying the identity of the underground personnel, after the face similarity and the voiceprint similarity are obtained, the environmental penalty factors of the face feature similarity and the voiceprint feature similarity during the identity identification of the underground personnel can be determined according to the environmental conditions, so that the reference threshold values of the current face feature similarity and the voiceprint feature similarity can be determined according to the environmental factors, the identity of the underground personnel can be identified, and the accuracy of the identity identification of the underground personnel with complex environments or severe environments can be improved.
The face confidence and the face feature similarity are determined based on the face information, the face information can be firstly subjected to feature extraction to obtain face features and face confidence, and then the face feature similarity is determined based on the face features and the face feature database.
In an alternative embodiment, the face feature extraction may be performed by a preselected Neural network, such as a Convolutional Neural Network (CNN), a residual error network, and the like. In practical application, after feature extraction is performed on face information, face features such as face positions, face sizes, facial features details and the like and face confidence corresponding to the extracted face features can be obtained.
The face features can be characterized in a face feature matrix mode, after face confidence is obtained, face similarity calculation can be carried out by multiplying a face model identification current face feature matrix with a feature matrix in a database to obtain face feature similarity:
sim face =feature r *feature i
wherein, sim face Representing the degree of similarity, feature of human face r Representing the feature matrix of the currently detected face i Representing a matrix of facial features in a database.
In an optional embodiment, when determining the voiceprint confidence and the voiceprint feature similarity based on the voiceprint information, the voiceprint information may be first subjected to feature extraction to obtain the voiceprint feature and the voiceprint confidence, and then the voiceprint feature similarity is determined based on the voiceprint feature and the voiceprint feature database.
When the voiceprint information is subjected to feature extraction, a voiceprint model can be adopted for recognition so as to obtain the currently detected voiceprint features and the voiceprint confidence.
Then, when the voiceprint feature similarity is calculated according to the voiceprint features, the voiceprint model can identify the multiplication of the current voiceprint feature matrix and the feature matrix in the database and divide the multiplication by the product of the square sum root of the two matrixes to obtain a similar feature value:
dot voice =feature c *feature n
wherein, sim voice Representing sound similarity, feature c Feature matrix representing the currently detected voiceprint n Representing a voiceprint feature matrix in a database.
Further, the above-mentioned environment penalty factors include a first environment penalty factor for face recognition and a second environment penalty factor for voiceprint recognition, and when determining the environment penalty factors according to the face confidence and the voiceprint confidence, the first environment penalty factor for face recognition and the second environment penalty factor for voiceprint recognition may be determined respectively:
and combining the face confidence coefficient and the voiceprint confidence coefficient to obtain a reference standard, determining a first environment penalty factor based on the face confidence coefficient and the reference standard, and determining a second environment penalty factor based on the voiceprint confidence coefficient and the reference standard.
In one example, the first environmental penalty factor and the second environmental penalty factor may be determined using the following equations:
wherein alpha is face Representing a first environmental penalty, α voice Representing a second environment penalty factor, voice con Representing voiceprint confidence, face con Representing face confidence, face con +voice con Indicating a reference datum.
In order to accurately determine the environmental penalty factor in consideration of the complexity of the downhole environment, in one embodiment, a first environmental penalty factor may be determined based on the face confidence, the reference benchmark, and the downhole environment parameter as a reference weight for the face feature similarity, and a second environmental penalty factor may be determined based on the voiceprint confidence, the reference benchmark, and the downhole environment parameter as a reference weight for the voiceprint feature similarity. The underground environment parameters are further introduced by determining the reference weight of the face feature similarity and the reference weight of the voiceprint feature similarity, so that the method is more suitable for identifying the identity of the personnel in the underground complex environment, and the accuracy of identifying the identity of the personnel in the underground is improved.
The downhole environment parameters at least comprise a downhole brightness value and a downhole noise volume, and when determining the environment penalty factors, specifically, a first environment penalty factor can be determined based on the face confidence, the reference standard and the downhole brightness value to be used as a reference weight of the face feature similarity, and a second environment penalty factor can be determined based on the voiceprint confidence, the reference standard and the downhole noise volume to be used as a reference weight of the voiceprint feature similarity.
For example, for the determination manner of the first environmental penalty factor, when the downhole brightness value is lower than the accurate recognition threshold of the facial image acquisition device, a smaller weight may be set to the first environmental penalty factor, because the situations of blurring, inaccuracy and the like of the facial image acquisition may occur due to the influence of the downhole brightness value, at this time, the person recognition may be performed by relying on the voiceprint feature more. The setting standard of the downhole brightness value may be adaptively determined according to the facial image capturing device, and is not specifically limited herein.
For another example, for the determination method of the second environment penalty factor, since the personnel may be performing downhole operation during identification, when obtaining voiceprint information of the personnel to be identified, the obtained voiceprint information may also be distorted due to downhole noise, and therefore, when the volume of the downhole noise is higher than 45-55 db (the range is adaptively selected), a smaller weight may be set for the second environment penalty factor, thereby avoiding situations such as inaccurate voiceprint information obtaining due to the influence of the downhole noise, and at this time, the personnel may be identified by relying on human face features more. The above-mentioned selectable range of values of the volume of the downhole noise is merely an example and is not particularly limited.
In an optional embodiment, when determining the similarity of the person based on the similarity of the face features, the similarity of the voiceprint features and the environmental penalty factor, the similarity of the face reference may be determined based on the similarity of the face features and the first environmental penalty factor, the similarity of the voiceprint reference may be determined based on the similarity of the voiceprint features and the second environmental penalty factor, and the similarity of the person may be determined based on the similarity of the face reference and the similarity of the voiceprint reference.
In one example, the final person similarity may be obtained by multiplying and summing the face feature similarity and the voiceprint feature similarity by corresponding environment penalty factors, respectively, see the following formula:
sim=sim face *α face +sim voice *α voice
where sim represents the person similarity.
Further, after the similarity of the persons is determined, when the similarity of the persons is determined to exceed a specified threshold, the persons to be identified are determined as persons with authority, otherwise, the persons without authority are determined.
Optionally, after the similarity of the persons is determined, in order to further improve the verification accuracy of the authorized persons, timing may be started after the similarity of the persons is obtained, when it is determined that the time length when the similarity of the persons exceeds the specified threshold exceeds the time threshold, the person to be identified is determined as the person with the authority, otherwise, it is determined that the person without the authority exists. For example, after the similarity of the person is obtained, timing is started, when the similarity of the person continuously exceeds a set time threshold value for one second and the person to be identified does not leave the identification area, the person to be identified is determined as an authorized person, optionally, in order to ensure the efficiency of person identification and avoid that the identification result is displayed slowly when the number of the person to be identified is large, the time threshold value may be set to a time range within 5 seconds. The setting of the time threshold may be used as a reference, and in practical applications, other time thresholds may also be selected, and are not specifically limited herein.
Further, when no authorized person is determined, an alarm can be triggered to avoid the entry of non-authorized persons.
For convenience of understanding, fig. 2 shows a flow chart of an overall underground personnel identification method, identification of personnel identification information is performed through combination of face identification and voiceprint identification, after face similarity and voiceprint similarity are obtained, environmental penalty factors of the face feature similarity and the voiceprint feature similarity during personnel identification are determined according to environmental conditions, and therefore reference thresholds of the face feature similarity and the voiceprint feature similarity can be determined according to environmental factors, personnel identification is performed, whether personnel are authorized or not is judged, and accuracy of identification of personnel in complex environments such as underground and the like or in severe environments is improved.
The embodiment of the invention also provides an underground personnel identity recognition device, which is shown in the figure 3 and comprises the following parts:
the information acquisition module 31 is used for acquiring face information and voiceprint information of a person to be identified;
the information processing module 32 is used for matching with the face information to be matched in the face feature database based on the face information to determine the face confidence coefficient and the face feature similarity, and matching with the voiceprint information to be matched in the voiceprint feature database based on the voiceprint information to determine the voiceprint confidence coefficient and the voiceprint feature similarity; the method comprises the steps that face information to be matched in a face feature database and voiceprint information to be matched in a voiceprint feature database belong to the same matched object;
a determining module 33, configured to determine an environmental penalty factor according to the face confidence and the voiceprint confidence; the environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition;
and the identity recognition module 34 is configured to determine the similarity of the person based on the similarity of the face features, the similarity of the voiceprint features, and the environmental penalty factor, so as to perform identity recognition on the person to be recognized according to the similarity of the person.
In some embodiments, the environmental penalty factors include a first environmental penalty factor for face recognition and a second environmental penalty factor for voiceprint recognition; a determining module 33, further configured to: merging the face confidence coefficient and the voiceprint confidence coefficient to obtain a reference datum; determining a first environment penalty factor based on the face confidence coefficient and a reference standard, wherein the first environment penalty factor is used as a reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence coefficient and the reference benchmark, wherein the second environment penalty factor is used as a reference weight of the similarity of the voiceprint features.
In some embodiments, the determining module 33 is further configured to: determining a first environment penalty factor based on the face confidence, the reference standard and the underground environment parameters, and using the first environment penalty factor as the reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence, the reference benchmark and the underground environment parameters, and using the second environment penalty factor as a reference weight of the voiceprint feature similarity.
In some embodiments, the downhole environment parameters include at least a downhole brightness value and a downhole noise volume; the determining module 33 is further configured to: determining a first environment penalty factor based on the face confidence, the reference standard and the underground brightness value, and using the first environment penalty factor as the reference weight of the face feature similarity; and determining a second environment penalty factor based on the voiceprint confidence, the reference benchmark and the underground noise volume, wherein the second environment penalty factor is used as a reference weight of the voiceprint feature similarity.
In some embodiments, the identification module 34 is further configured to: determining face reference similarity based on the face feature similarity and a first environment penalty factor; determining the voiceprint reference similarity based on the voiceprint feature similarity and the second environment penalty factor; and determining the similarity of the persons based on the face reference similarity and the voiceprint reference similarity.
In some embodiments, after determining the similarity of the people, the apparatus further includes an authority determination module configured to: and when the similarity of the persons exceeds a specified threshold value, determining the persons to be identified as authorized persons.
In some embodiments, the permission determination module is further configured to: and starting timing after the personnel similarity is obtained, and determining the personnel to be identified as the authorized personnel when the time length of the personnel similarity exceeding the specified threshold exceeds the time threshold.
The implementation principle and the generated technical effects of the underground personnel identification device provided by the embodiment of the application are the same as those of the embodiment of the method, and for brief description, corresponding contents in the embodiment of the underground personnel identification method can be referred to where the embodiment of the underground personnel identification device is not mentioned.
An electronic device is further provided in the embodiment of the present application, as shown in fig. 4, which is a schematic structural diagram of the electronic device, where the electronic device 100 includes a processor 41 and a memory 40, the memory 40 stores computer-executable instructions that can be executed by the processor 41, and the processor 41 executes the computer-executable instructions to implement any one of the above methods for identifying the identity of the downhole person.
In the embodiment shown in fig. 4, the electronic device further comprises a bus 42 and a communication interface 43, wherein the processor 41, the communication interface 43 and the memory 40 are connected by the bus 42.
The Memory 40 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, etc. may be used. The bus 42 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 42 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
The processor 41 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 41. The Processor 41 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory, and the processor 41 reads the information in the memory, and completes the steps of the method for identifying the identity of the downhole person in the foregoing embodiment in combination with the hardware thereof.
The embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the method for identifying an identity of a downhole person, and specific implementation may refer to the foregoing method embodiment, and details are not described herein again.
The computer program product of the method, the apparatus, the electronic device, and the readable storage medium for identifying the identity of the downhole personnel provided in the embodiments of the present application includes a computer readable storage medium storing program codes, instructions included in the program codes may be used to execute the method described in the foregoing method embodiments, and specific implementations may refer to the method embodiments and are not described herein again.
Unless specifically stated otherwise, the relative steps, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present application.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or orientations or positional relationships that the products of the present invention are conventionally placed in use, and are used only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present application. Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Furthermore, the terms "horizontal", "vertical", "overhang" and the like do not imply that the components are required to be absolutely horizontal or overhang, but may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the present application, it should also be noted that, unless expressly stated or limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and can include, for example, fixed connections, detachable connections, or integral connections; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A method for identifying the identity of underground personnel is characterized by comprising the following steps:
acquiring face information and voiceprint information of a person to be identified;
matching the face information with face information to be matched in a face feature database based on the face information, determining face confidence and face feature similarity, and matching the voiceprint information with voiceprint information to be matched in a voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity; the face information to be matched in the face feature database and the voiceprint information to be matched in the voiceprint feature database belong to the same matched object;
determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient; the environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition;
determining the similarity of personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor, and identifying the identity of the personnel to be identified based on the similarity of the personnel.
2. The downhole personnel identification method of claim 1, wherein the environmental penalty factors comprise a first environmental penalty factor for face recognition and a second environmental penalty factor for voiceprint recognition;
determining an environmental penalty factor according to the face confidence and the voiceprint confidence, comprising:
merging the face confidence coefficient and the voiceprint confidence coefficient to obtain a reference standard;
determining the first environment penalty factor based on the face confidence and the reference benchmark, wherein the first environment penalty factor is used as a reference weight of the face feature similarity;
and determining the second environment penalty factor based on the voiceprint confidence coefficient and the reference benchmark to serve as the reference weight of the voiceprint feature similarity.
3. The method for identifying the identity of the underground personnel according to claim 2, wherein the step of determining an environmental penalty factor according to the face confidence and the voiceprint confidence comprises the following steps:
determining the first environment penalty factor based on the face confidence, the reference benchmark and the underground environment parameters as the reference weight of the face feature similarity;
and determining the second environment penalty factor based on the voiceprint confidence, the reference benchmark and the underground environment parameters to serve as the reference weight of the voiceprint feature similarity.
4. The method of claim 3, wherein the downhole environment parameters comprise at least a downhole brightness value and a downhole noise volume;
determining an environmental penalty factor according to the face confidence and the voiceprint confidence, comprising:
determining the first environment penalty factor based on the face confidence, the reference benchmark and the underground brightness value to serve as the reference weight of the face feature similarity;
determining the second environmental penalty factor based on the voiceprint confidence, the reference benchmark, and the downhole noise volume as a reference weight for the voiceprint feature similarity.
5. The underground personnel identity recognition method of any one of claims 1-4, wherein determining the personnel similarity based on the face feature similarity, the voiceprint feature similarity and the environmental penalty factor comprises:
determining face reference similarity based on the face feature similarity and a first environment penalty factor;
determining a voiceprint reference similarity based on the voiceprint feature similarity and a second environment penalty factor;
and determining the similarity of the people based on the face reference similarity and the voiceprint reference similarity.
6. A downhole personnel identification method according to any of claims 1-5, wherein identifying the personnel to be identified based on the personnel similarity comprises:
and when the similarity of the personnel exceeds a specified threshold value, determining the personnel to be identified as authorized personnel.
7. A downhole personnel identification method according to any of claims 1-5, wherein identifying the personnel to be identified based on the personnel similarity comprises:
and starting timing after the personnel similarity is obtained, and determining the personnel to be identified as authorized personnel when the time length of the personnel similarity exceeding a specified threshold exceeds a time threshold.
8. A downhole personnel identification device, comprising:
the information acquisition module is used for acquiring the face information and the voiceprint information of the person to be identified;
the information processing module is used for matching with the face information to be matched in the face feature database based on the face information, determining face confidence and face feature similarity, and matching with the voiceprint information to be matched in the voiceprint feature database based on the voiceprint information, and determining voiceprint confidence and voiceprint feature similarity; the face information to be matched in the face feature database and the voiceprint information to be matched in the voiceprint feature database belong to the same matched object;
the determining module is used for determining an environment penalty factor according to the face confidence coefficient and the voiceprint confidence coefficient; the environment penalty factor is used for representing the reference weight of the face feature similarity and the voiceprint feature similarity under the current environment condition;
and the identity recognition module is used for determining the similarity of the personnel based on the similarity of the human face features, the similarity of the voiceprint features and the environmental penalty factor so as to recognize the identity of the personnel to be recognized through the similarity of the personnel.
9. An electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the downhole personnel identification method of any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer-executable instructions which, when invoked and executed by a processor, cause the processor to carry out the downhole personnel identification method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210523280.9A CN114898475A (en) | 2022-05-13 | 2022-05-13 | Underground personnel identity identification method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210523280.9A CN114898475A (en) | 2022-05-13 | 2022-05-13 | Underground personnel identity identification method and device, electronic equipment and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114898475A true CN114898475A (en) | 2022-08-12 |
Family
ID=82722669
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210523280.9A Pending CN114898475A (en) | 2022-05-13 | 2022-05-13 | Underground personnel identity identification method and device, electronic equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114898475A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115631525A (en) * | 2022-10-26 | 2023-01-20 | 万才科技(杭州)有限公司 | Insurance instant matching method based on face edge point recognition |
-
2022
- 2022-05-13 CN CN202210523280.9A patent/CN114898475A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115631525A (en) * | 2022-10-26 | 2023-01-20 | 万才科技(杭州)有限公司 | Insurance instant matching method based on face edge point recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110047095B (en) | Tracking method and device based on target detection and terminal equipment | |
KR101632912B1 (en) | Method for User Authentication using Fingerprint Recognition | |
CN110532746B (en) | Face checking method, device, server and readable storage medium | |
CN110826418B (en) | Facial feature extraction method and device | |
CN111275040B (en) | Positioning method and device, electronic equipment and computer readable storage medium | |
CN110928862A (en) | Data cleaning method, data cleaning apparatus, and computer storage medium | |
CN111931548B (en) | Face recognition system, method for establishing face recognition data and face recognition method | |
CN109635625B (en) | Intelligent identity verification method, equipment, storage medium and device | |
CN111814612A (en) | Target face detection method and related device thereof | |
CN111814776A (en) | Image processing method, device, server and storage medium | |
CN114898475A (en) | Underground personnel identity identification method and device, electronic equipment and readable storage medium | |
CN113221842A (en) | Model training method, image recognition method, device, equipment and medium | |
CN113158730A (en) | Multi-person on-duty identification method and device based on human shape identification, electronic device and storage medium | |
CN112036269A (en) | Fall detection method and device, computer equipment and storage medium | |
CN116092228A (en) | Access control processing method and device for face shielding, access control equipment and medium | |
CN111274899B (en) | Face matching method, device, electronic equipment and storage medium | |
CN113239738B (en) | Image blurring detection method and blurring detection device | |
CN115761842A (en) | Automatic updating method and device for human face base | |
CN115909400A (en) | Identification method for using mobile phone behaviors in low-resolution monitoring scene | |
CN115019152A (en) | Image shooting integrity judgment method and device | |
CN112084874B (en) | Object detection method and device and terminal equipment | |
CN114220142A (en) | Face feature recognition method of deep learning algorithm | |
CN112750274A (en) | Facial feature recognition-based aggregation early warning system, method and equipment | |
CN113014914A (en) | Neural network-based single face-changing short video identification method and system | |
CN116152936B (en) | Face identity authentication system with interactive living body detection and method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |