CN113052197B - Method, device, equipment and medium for identity recognition - Google Patents
Method, device, equipment and medium for identity recognition Download PDFInfo
- Publication number
- CN113052197B CN113052197B CN201911382814.5A CN201911382814A CN113052197B CN 113052197 B CN113052197 B CN 113052197B CN 201911382814 A CN201911382814 A CN 201911382814A CN 113052197 B CN113052197 B CN 113052197B
- Authority
- CN
- China
- Prior art keywords
- feature
- identity
- target
- information
- behavior
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000006399 behavior Effects 0.000 claims description 138
- 230000001815 facial effect Effects 0.000 claims description 61
- 230000003542 behavioural effect Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 2
- 230000007774 longterm Effects 0.000 description 24
- 238000000605 extraction Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002650 habitual effect 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
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method, a device, equipment and a medium for identity identification. The method comprises the following steps: collecting target characteristic information of a target image; sequentially matching the first behavior characteristic information of the target image with the second behavior characteristic information in the identity characteristic database to obtain a behavior characteristic matching result; if the behavior feature matching result meets the preset condition, determining target second behavior feature information with the matching rate with the first behavior feature information being larger than a first threshold value in an identity feature database; and determining the target identity associated with the target second behavior characteristic information as an identity recognition result of the target image. According to the method, the device, the equipment and the medium for identifying the identity, which are provided by the embodiment of the invention, the accuracy of the identity identification result can be improved, and more accurate identity identification can be obtained.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to a method, an apparatus, a device, and a medium for identity recognition.
Background
With the gradual development of image recognition technology, the image recognition technology is increasingly widely applied to daily life.
For example, when the electronic device shoots a plurality of images of different users, the electronic device can identify the shot images through an image identification technology to obtain the users corresponding to each image. However, the current image recognition technology often generates deviation in the image recognition process, so that an accurate identity recognition result cannot be obtained frequently, and the accuracy of the identity recognition result is low.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a medium for identity identification, which can improve the accuracy of an identity identification result and obtain a relatively accurate identity identification result.
In a first aspect, there is provided a method of identity recognition, the method comprising:
collecting target characteristic information of a target image;
sequentially matching the first behavior characteristic information in the target characteristic information with the second behavior characteristic information in the identity characteristic database to obtain a behavior characteristic matching result;
if the behavior feature matching result meets the preset condition, determining target second behavior feature information with the matching rate with the first behavior feature information being larger than a first threshold value in an identity feature database;
and determining the target identity associated with the target second behavior characteristic information as an identity recognition result of the target image.
In a second aspect, there is provided an apparatus for identity recognition, the apparatus comprising:
the acquisition module is used for acquiring target characteristic information of a target image;
the first matching module is used for sequentially matching the first behavior characteristic information in the target characteristic information with the second behavior characteristic information in the identity characteristic database to obtain a behavior characteristic matching result;
the first determining module is used for determining target second behavior feature information with the matching rate with the first behavior feature information being larger than a first threshold value in the identity feature database if the behavior feature matching result meets a preset condition;
and the second determining module is used for determining the target identity associated with the target second behavior characteristic information as the identity recognition result of the target image.
In a third aspect, there is provided an apparatus for identity recognition, the apparatus comprising:
a processor and a memory storing computer program instructions;
the processor executes the computer program instructions to implement the method for identifying identity provided in the embodiment of the invention.
In a fourth aspect, a computer storage medium is provided, where computer program instructions are stored, where the computer program instructions, when executed by a processor, implement a method for identity recognition according to the embodiment of the present invention.
According to the method, the device, the equipment and the medium for identifying the identity, the electronic equipment sequentially performs matching through the first behavior characteristic in the target characteristic information of the acquired target image and the second behavior characteristic information in the identity characteristic database, and under the condition that the behavior matching result meets the preset condition, the target second behavior characteristic information is determined, and then the target identity associated with the target second behavior characteristic information is determined as the identity identification result of the target image, so that the accuracy of the identity identification result can be improved, and further a more accurate identity identification result can be obtained.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings that are needed to be used in the embodiments of the present invention will be briefly described, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identity recognition according to an embodiment of the present invention;
FIG. 2 is a diagram of an identity database according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method of identity recognition provided in another embodiment of the present invention;
FIG. 4 is a diagram of an identification system for a robot according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a sequencer according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an apparatus for identity recognition according to an embodiment of the present invention;
fig. 7 is a block diagram of an exemplary hardware architecture according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely configured to illustrate the invention and are not configured to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the invention by showing examples of the invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
With the rapid development of the current image recognition technology, the user information corresponding to the image can be recognized by collecting the image of the user through the electronic equipment, so that the image of the user can be sent to the corresponding user.
However, the current image recognition technology often generates deviation in the image recognition process, so that an accurate identity recognition result cannot be obtained frequently, and the accuracy of the identity recognition result is low.
Therefore, the embodiment of the invention provides a method, a device, equipment and a medium for identity identification, which can obtain a relatively accurate identity identification result.
The following describes a method, a device, equipment and a medium for identity recognition according to an embodiment of the present invention with reference to the accompanying drawings. It should be noted that these examples are not intended to limit the scope of the present disclosure.
The following describes in detail the identification method according to the embodiment of the present invention through fig. 1.
In order to better understand the technical solution of the present invention, a method for identifying identity according to an embodiment of the present invention will be described in detail below with reference to fig. 1 by taking a robot as an example, and fig. 1 is a flowchart of the method for identifying identity according to an embodiment of the present invention.
As shown in fig. 1, the method for identifying identity in the embodiment of the invention comprises the following steps:
s101, collecting target characteristic information of a target image.
Alternatively, in some embodiments of the present invention, the target feature information may include: first facial feature information, first behavior feature information, and first dressing feature information.
S102, sequentially matching the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database to obtain a behavior feature matching result.
Optionally, in some embodiments of the present invention, as shown in fig. 2, fig. 2 is a schematic diagram of an identity feature database according to an embodiment of the present invention. As can be seen in fig. 2, the identity feature database may include a facial information sub-database and a behavioral feature sub-database. The behavior characteristic sub-database further can be respectively a long-term behavior characteristic sub-database, a temporary characteristic resource sub-database and a strange characteristic resource sub-database, and the temporary characteristic resource sub-database further can be further divided into a temporary dressing characteristic sub-database and a temporary behavior characteristic sub-database.
For example, a long-term behavioral characteristics sub-database may be used to record long-term valid behavioral characteristics information, a temporary behavioral characteristics sub-database may be used to record short-term behavioral characteristics information, temporary dressing characteristics sub-data may be used to store first dressing characteristics information, and a strange characteristics resources sub-database may be used to record facial characteristics information without matching identity information.
The long-term behavior feature sub-database is used for storing the long-term features of the target image, the data size is small, the matching speed is high, and the computing speed can be improved by matching the feature information in the long-term behavior feature sub-database;
if the matching similarity with the characteristic information in the long-term behavior characteristic sub-database is low, the matching is carried out with the characteristic information in the temporary dressing characteristic sub-database, and the characteristic information in the temporary dressing characteristic sub-database is the behavior characteristic information collected recently, so that the matching success rate can be improved.
Optionally, in some embodiments of the present invention, since N (N is a positive integer) pieces of second behavior feature information are stored in the identity feature database, when the electronic device matches the first behavior feature information of the target image with the second behavior feature information in the identity feature database in sequence, N behavior feature matching results are finally obtained.
And S103, if the behavior feature matching result meets the preset condition, determining target second behavior feature information with the matching rate with the first behavior feature information being larger than a first threshold value in the identity feature database.
Alternatively, in some embodiments of the present invention, the preset condition may be that the number of matching rates greater than the second threshold in the behavior feature matching result is smaller than the third threshold, and the maximum matching rate in the behavior feature matching result is greater than the first threshold.
For example, when the electronic device sequentially matches the first behavior feature information of the target image with the second behavior feature information in the identity feature database, after N matching rates are finally obtained, if the number of more than 90% (the second threshold) of the N matching rates is less than 2 (the third threshold), and the maximum matching rate of the N matching rates is greater than the first threshold (95%), the obtained behavior feature matching result may be considered to satisfy the preset condition.
The electronic device may then determine target second behavior feature information in the identity feature database that has a matching rate with the first behavior feature information that is greater than a first threshold.
And S104, determining the target identity associated with the target second behavior characteristic information as an identity recognition result of the target image.
Optionally, in some embodiments of the present invention, after the electronic device determines, in the identity feature database, target second behavior feature information having a matching rate with the first behavior feature information greater than a first threshold, a target identity associated with the target second behavior feature information may be determined as an identity recognition result of the target image.
In the embodiment of the invention, the electronic equipment is matched with the second behavior feature in the identity feature database through the first behavior feature information of the acquired target image, and the target second behavior feature information is obtained under the condition that the behavior feature matching result meets the preset condition, so that the target identity associated with the target second behavior feature information is determined as the identity recognition result of the target image, the accuracy of the identity recognition result can be improved, and further, the more accurate identity recognition result is obtained.
Optionally, in some embodiments of the present invention, after S104, the electronic device may further output, in response to the image output request, a target image corresponding to the target identity after receiving the image output request of the target identity.
For example, the electronic device may output at least one image corresponding to the highlight after receiving the image output request to output the highlight.
Optionally, in some embodiments of the present invention, before S103, the electronic device may further match the first facial feature information in the target feature information with the second facial feature information in the identity feature database in sequence to obtain a facial feature matching result, and further match the first behavioral feature information in the target feature information with the second behavioral feature information in the identity feature database in sequence if the facial feature matching result does not meet a preset condition.
If the facial feature matching result obtained by the electronic device meets the preset condition, determining target second facial feature information with the matching rate of the first facial feature information being greater than a first threshold value in an identity feature database, and determining a target identity associated with the target second facial feature information as an identity recognition result of the target image.
In the embodiment of the invention, under the condition that the facial features cannot meet the preset conditions, the identity information of the target image can be identified through matching the behavior features of the target image, so that the identity identification is not limited to the facial features, the identifiable range of the identity identification is enlarged, and the accuracy of the identity identification is further improved. In addition, under the condition that no facial feature information exists in the target image, the behavior feature information can still be extracted through the image of the target and compared with the behavior feature information in the identity feature database to obtain the identity information of the target.
Optionally, in some embodiments of the present invention, if the electronic device determines that the matching rate of the facial feature does not meet the preset condition and the matching rate of the behavioral feature also does not meet the preset condition, the first dressing feature information in the target feature information and the second dressing feature information in the identity feature database may be further matched in sequence, so as to obtain a dressing feature matching result.
If the dressing feature matching result obtained by the electronic device meets the preset condition, determining target second dressing feature information with the matching rate of the first dressing feature information being greater than a first threshold value in the identity feature database, and determining a target identity associated with the target second dressing feature information as an identity recognition result of the target image.
In the embodiment of the invention, under the condition that the behavior characteristics can not meet the preset conditions, the identity information of the target image can be identified through matching the dressing characteristics of the target image, so that the identity identification is not limited to the facial characteristics and the behavior characteristics, the identifiable range of the identity identification is enlarged, and the accuracy of the identity identification is further improved.
Optionally, in some embodiments of the present invention, the electronic device may further update the target feature information of the target image to the identity feature database, so that the identity feature information in the identity feature database is more accurate, so that a more accurate matching result can be obtained when the matching is performed with the feature information in the identity feature data.
Alternatively, in some embodiments of the present invention, if the second dressing feature information in the identity feature database is updated, the first dressing feature information corresponding to the target image may be stored in a temporary dressing feature sub-database in the identity feature database, and the second dressing feature information before updating may be deleted.
Optionally, in some embodiments of the present invention, if the facial feature matching result, the behavioral feature matching result, and the dressing feature matching result obtained after sequentially matching the first facial feature information, the first behavioral feature information, and the first dressing feature information of the target image with the feature information in the identity feature database do not satisfy the preset conditions, the target feature information of the target image may be stored in a first sub-database in the identity feature database (in some embodiments of the present invention, the first sub-database may also be referred to as a strange feature resource sub-database).
Then, the electronic device may add the identity information corresponding to the target image in the identity feature database, establish an association between the identity information and the target feature information corresponding to the target image in the first sub-database, and store the association, the identity information corresponding to the target image, and the target feature information corresponding to the target image in the second sub-database in the identity feature information database. It should be appreciated that in some embodiments of the present invention, the second sub-database may also be a generic term for facial feature information sub-databases and behavioral feature sub-databases.
Optionally, in some embodiments of the present invention, the electronic device may further change an image capturing angle of the image capturing apparatus in order to re-capture the first facial feature information of the target image in a case that the facial feature matching result does not meet the preset condition.
Optionally, in some embodiments of the present invention, as shown in fig. 3, fig. 3 is a flowchart of a method for identity recognition according to another embodiment of the present invention.
S301, collecting target characteristic information.
Alternatively, in some embodiments of the invention,
s302, matching the first facial feature information in the target feature information with the second facial feature information in the identity feature database.
S303, determine that the facial feature matching result satisfies the preset condition? If the preset condition is satisfied, S304 is executed, and if the preset condition is not satisfied, S305 is executed.
S304, outputting the identification result of the target image.
S305, matching the first behavior characteristic information in the target characteristic information with the second behavior characteristic information in the identity characteristic database.
S306, judging whether the behavior feature matching result meets the preset condition? If the preset condition is satisfied, S307 is executed, and if the preset condition is not satisfied, S308 is executed.
S307, the identity recognition result of the target image is output.
S308, matching the first dressing characteristic information in the target characteristic information with the second dressing characteristic information in the identity characteristic data.
S309, judging whether the dressing feature matching result meets the preset condition? If the preset condition is satisfied, S310 is executed, and if the preset condition is not satisfied, S311 is executed.
S310, outputting the identification result of the target image.
S311, outputting query failure information.
In the embodiment of the invention, the facial features of the target image are preferentially matched, and the behavior features are matched under the condition that the facial features are not successfully matched, and if the behavior features are not matched, the dressing features are matched, so that the identification is not limited to the facial features, the identifiable range of the identification is enlarged, and the accuracy of the identification is improved.
Optionally, in some embodiments of the present invention, as shown in fig. 4, fig. 4 is an identification system applied to a robot according to an embodiment of the present invention.
As shown in fig. 4, the identification system includes a camera, a robot, and an identification device. The camera can be a fixed camera, after the camera collects the target image, the camera transmits the target image to an input interface of the identity recognition device through an output section, the obtained target characteristic information of the target image is matched with the characteristic information in the identity characteristic database through a program device in the identity recognition device, and a matching result is output through a query interface. In addition, the identity recognition device can control the image acquisition device arranged in the robot to change the image acquisition angle through the command output interface under the condition that the identity information corresponding to the target image cannot be determined through the facial features of the target image, and the target image is acquired again.
Optionally, in some embodiments of the present invention, as shown in fig. 5, fig. 5 is a schematic structural diagram of a program apparatus according to an embodiment of the present invention. The program device comprises: an information extraction unit, an information comparison unit and an information update unit.
Wherein the information extraction unit includes: a facial feature extraction unit, a behavioral feature extraction unit, and a dressing feature extraction unit; the information comparison unit includes: facial feature comparison unit, behavior feature comparison unit, and dressing feature comparison unit; the information updating unit includes: facial feature updating unit, behavioral feature updating unit, and dressing feature updating unit.
The function of the individual units in the program system is described in detail below by means of some embodiments:
facial feature extraction unit: the facial feature extraction unit is used for extracting facial feature information, and extracting the facial feature information according to the facial image of the target image.
Behavior feature extraction unit: the behavior feature extraction unit is used for extracting behavior features, and extracting behavior feature information according to the target image, wherein the behavior feature information comprises: personal behavior characteristic information such as gesture information during walking or running, step information during walking or running, and habitual action information.
Dressing feature extraction unit: the dressing feature extraction unit extracts dressing information of a target image, the dressing information including: color information, style information, etc. of the jacket, the lower garment, the shoe and boot.
Facial feature contrast unit: the facial feature comparison unit is used for comparing facial feature information, and comparing the facial feature information with second facial feature information in the identity feature database according to the first facial feature information of the target image.
Behavior feature comparison unit: and the behavior characteristic comparison unit compares the first behavior characteristic information of the target image with the second behavior characteristic information in the identity characteristic database.
Dressing feature contrast unit: the dressing feature comparison unit compares the first dressing feature information of the target image with the second dressing feature information in the identity feature database.
A facial feature updating unit: the facial feature updating unit is used for writing the first facial feature information corresponding to the target image into the facial feature sub-database for storage.
Behavior feature updating unit: the behavior feature updating unit is used for judging whether feature information in a temporary feature resource sub-database in the identity feature database belongs to feature information of short-term change or feature information of long-term change, and if the feature information belongs to the feature information of long-term change, the corresponding feature information is written into the long-term feature sub-database for storage.
Dressing feature updating unit: the dressing feature updating unit is used for writing the first dressing feature information corresponding to the target image into a temporary dressing feature resource sub-database in the identity feature database for storage, and deleting the dressing feature information before updating at regular time.
Optionally, in some embodiments of the present invention, the identity recognition system provided by the embodiment of the present invention may be applied to a preschool education scenario.
For example, in most cases, the child is in an active or running state, and the child is identified under the condition that the child does not actively cooperate with face recognition, and by the identification system provided by the embodiment of the invention, the corresponding relationship between the identity information of the child and the acquired behavior characteristics can be established in advance, and under the condition that the face recognition of the child cannot be carried out by acquiring the face image of the child later, the identification of the child is carried out by the behavior characteristics. In addition, if the matching result cannot be obtained through the behavior characteristics, the identity recognition can be continuously performed through the dressing characteristics, the recognizable range of the identity recognition is improved, and the recognition accuracy is further improved.
Optionally, in some embodiments of the present invention, when the behavior feature comparing unit compares, if the highest matching rate of the second behavior feature information in the long-term behavior feature sub-database is greater than or equal to 90% (the first threshold value), and only one (the third threshold value) of the results of the matching rate of the second behavior feature information in the long-term behavior feature sub-database is greater than or equal to 80% (the second threshold value), the behavior feature matching result of the target image satisfies the preset condition, and the process of extracting the behavior feature of the target image is terminated, so as to reduce the data processing capacity of the system, so as to improve the data processing efficiency of the system.
Optionally, in some embodiments of the present invention, when the behavioral characteristic comparison unit compares, if the highest matching rate of the behavioral characteristic information with the second behavioral characteristic information in the long-term behavioral characteristic sub-database is greater than or equal to 90% (the first threshold), and there are two (greater than the third threshold) results of the matching rate of the behavioral characteristic information with the second behavioral characteristic information in the long-term behavioral characteristic sub-database being greater than or equal to 80% (the second threshold), it indicates that the behavioral characteristic matching result of the target image does not meet the preset condition, and identity information of the target image cannot be output according to the matching result of the behavioral characteristic, so that dressing characteristic information of the target image can be further matched.
According to the identity recognition system provided by the embodiment of the invention, when the identity information of a certain target image is required to be obtained, the target image is sent to the identity recognition device, and the identity recognition device can perform identity recognition of the target image through the target characteristic information of the target image.
If the facial feature information exists in the target image, carrying out facial matching, and if the facial matching is successful, outputting the identity information of the target image to corresponding equipment; if the face matching fails, the characteristic information in the long-term behavior characteristic sub-database is matched, if the matching is successful, the identity information of the target image is output to the corresponding equipment, if the matching is failed, the characteristic information in the temporary characteristic resource sub-database is matched, and if the matching is successful, the identity information of the target is output to the corresponding equipment.
Optionally, in some embodiments of the present invention, the information updating unit may perform the updating operation periodically (may be performed once a month), and each time of updating, obtain feature information of each target identity in the temporary feature resource sub-database, calculate, according to natural months, average value information of each feature by using an algorithm, where each item of feature information is calculated.
For example, the characteristic value information of the first natural month before a certain characteristic of the target is C (Y-1) The characteristic value information of the first second natural month is C (Y-2) The characteristic value information of the first fourth natural month is C (Y-4) And C (Y-1) 、C (Y-2) And C (Y-4) Satisfying expression (1), the characteristic value information of the first natural month is C (Y-1) Updating into a long-term behavior characteristic sub-database.
And->
As can be seen from the expression (1), if the average characteristic value of the first month is compared with the average characteristic value of the first natural month, if the variation value is 5% or more, and the variation value of the average characteristic value of the first natural month and the average characteristic value of the second natural month is less than 1%; the target characteristic information is considered to be a long-term change, and there is no trend of continuing to change or recover in the near future, and the change is kept for a period of time in the future, and the characteristic information of the first natural month is stored in a long-term behavior characteristic sub-database. The characteristic information in the long-term behavior characteristic sub-database is preferentially matched in the characteristic value matching process of the subsequent information comparison unit, the long-term behavior characteristic sub-database is used for storing long-term characteristics of the target, the data size is small, the matching speed is high, and the computing speed can be improved through the matching of the long-term behavior characteristic sub-database.
Optionally, in some embodiments of the present invention, when the temporary dressing feature is updated by the information updating unit, dressing feature information (color information, style information, etc. of the upper garment, the lower garment, the shoes and boots) in the target feature information may be stored in the temporary feature resource acquisition sub-database, and when the target object in the target image is in a static state and is not easy to obtain its behavioral feature, identity recognition may be performed based on the dressing feature, where the temporary dressing feature is valid on the same day, and the information updating unit deletes temporary dressing features corresponding to all identity information before the end of the current natural day, so as to prevent erroneous recognition, and improve accuracy of performing identity recognition based on the dressing information.
The information more trust unit in the embodiment of the invention can transfer the characteristic information in the temporary characteristic resource sub-database to the long-term behavior characteristic sub-database, thereby improving the success rate of matching the long-term behavior characteristic sub-database and reducing the calculation amount of matching.
The following describes in detail, through fig. 6, an identification device according to an embodiment of the present invention, where the identification device corresponds to an identification method.
Fig. 6 is a schematic structural diagram of an apparatus for identity recognition according to an embodiment of the present invention.
As shown in fig. 6, the apparatus for identity recognition includes:
the acquisition module 610 is configured to acquire target feature information of a target image;
the first matching module 620 is configured to match the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database in sequence, so as to obtain a behavior feature matching result;
the first determining module 630 is configured to determine, in the identity feature database, target second behavior feature information having a matching rate with the first behavior feature information greater than a first threshold, if the behavior feature matching result meets a preset condition;
and a second determining module 640, configured to determine the identity of the target associated with the second behavior feature information of the target as an identity recognition result of the target image.
According to the identity recognition device provided by the embodiment of the invention, the electronic equipment sequentially performs matching through the first behavior characteristic in the acquired target characteristic information of the target image and the second behavior characteristic information in the identity characteristic database, and under the condition that the behavior matching result meets the preset condition, the target second behavior characteristic information is determined, and then the target identity associated with the target second behavior characteristic information is determined as the identity recognition result of the target image, so that the accuracy of the identity recognition result can be improved, and further a more accurate identity recognition result can be obtained.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
the first receiving module is used for receiving an image output request of the target identity after determining the target identity associated with the target second behavior characteristic information as the identity recognition result of the target image;
and the output module is used for responding to the image output request and outputting the target image.
Optionally, in some embodiments of the present invention, the preset condition is that the number of matching rates in the matching result that are greater than the second threshold is smaller than the third threshold, and the maximum matching rate in the matching result is greater than the first threshold.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
the second matching module is used for sequentially matching the first facial feature information in the target feature information with the second facial feature information in the identity feature database before sequentially matching the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database, so as to obtain a facial feature matching result;
the first matching module 620 is specifically configured to: and under the condition that the facial feature matching result does not meet the preset condition, sequentially matching the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
the third matching module is used for matching the first dressing characteristic information in the target characteristic information with the second dressing characteristic information in the identity database in sequence if the behavior characteristic matching result does not meet the preset condition, so as to obtain a dressing matching result;
the third determining module is used for determining target second dressing feature information with the matching rate with the first dressing feature information being larger than a first threshold value in the identity feature database if the dressing feature matching result meets the preset condition;
and the fourth determining module is used for determining the target identity associated with the target second dressing characteristic information as the identity recognition result of the target image.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
and the updating module is used for updating the identity characteristic database based on the target characteristic information of the target image after determining the target identity associated with the target second behavior characteristic information as the identity recognition result of the target image.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
and the deleting module is used for deleting the second dressing characteristic information before updating in the identity characteristic database under the condition of updating the identity characteristic database based on the first dressing characteristic information in the target characteristic information.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
and the first storage module is used for storing the target feature information of the target image into a first sub-database in the identity feature database if the dressing feature matching result does not meet the preset condition.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
the adding module is used for adding the identity information corresponding to the target image in the identity characteristic database;
the second storage module is used for establishing an association relation between the target feature information corresponding to the target image in the first sub-database and the identity information, and storing the association relation, the identity information corresponding to the target image and the target feature information corresponding to the target image into a second sub-database in the identity feature information database.
Optionally, in some embodiments of the present invention, the apparatus for identifying an identity further includes:
and the adjusting module is used for changing the image acquisition angle of the image acquisition device under the condition that the facial feature matching result does not meet the preset condition, so that the acquisition module 610 acquires the first facial feature information of the target image again.
Each module of the device for identifying identity provided in the embodiment of the present invention has a function of implementing the method/step of identifying identity in the embodiment shown in fig. 1 to 5, and can achieve the technical effects corresponding to the embodiment shown in fig. 1 to 5, and for brevity description, no further description is given here.
Fig. 7 is a block diagram of an exemplary hardware architecture according to an embodiment of the present invention.
As shown in fig. 7, computing device 700 includes an input device 701, an input interface 702, a central processor 703, a memory 704, an output interface 705, and an output device 706. The input interface 702, the central processor 703, the memory 704, and the output interface 705 are connected to each other through a bus 710, and the input device 701 and the output device 706 are connected to the bus 710 through the input interface 702 and the output interface 705, respectively, and further connected to other components of the computing device 700.
Specifically, the input device 701 receives input information from the outside, and transmits the input information to the central processor 703 through the input interface 702; the central processor 703 processes the input information based on computer executable instructions stored in the memory 704 to generate output information, temporarily or permanently stores the output information in the memory 704, and then transmits the output information to the output device 706 through the output interface 705; output device 706 outputs the output information to the outside of computing device 700 for use by a user.
That is, the computing device shown in FIG. 7 may also be an identification enabled device, which may include: a memory storing computer-executable instructions; and a processor that when executing computer-executable instructions can implement the method of identification described in connection with fig. 1-5.
Embodiments of the present invention also provide a computer readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by the processor, implement the method for identity recognition provided by the embodiment of the invention.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention. The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
The present invention may be embodied in other specific forms without departing from its spirit or essential characteristics. For example, the algorithms described in particular embodiments may be modified without departing from the basic spirit of the invention. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (10)
1. A method of identity recognition, comprising:
collecting target characteristic information of a target image;
sequentially matching the first behavior characteristic information in the target characteristic information with the second behavior characteristic information in the identity characteristic database to obtain a behavior characteristic matching result;
if the behavior feature matching result meets a preset condition, determining target second behavior feature information with the matching rate of the first behavior feature information being larger than a first threshold value in the identity feature database, determining a target identity associated with the target second behavior feature information as an identity recognition result of the target image, and updating the identity feature database based on the first behavior feature information when the first behavior feature information is feature information changing for a long time;
if the behavior feature matching result does not meet the preset condition, sequentially matching first dressing feature information in the target feature information with second dressing feature information in an identity database to obtain a dressing matching result, if the dressing feature matching result meets the preset condition, determining target second dressing feature information with the matching rate of the first dressing feature information being greater than a first threshold value in the identity feature database, determining a target identity associated with the target second dressing feature information as an identity recognition result of the target image, updating the identity feature database based on the first dressing feature information, and deleting the second dressing feature information before updating in the identity feature database;
acquiring a first average characteristic value of the target characteristic information in a first natural month of a plurality of natural months, a second average characteristic value of the target characteristic information in a second natural month of the plurality of natural months, and a third average characteristic value of the target characteristic information in a fourth natural month of the plurality of natural months;
updating the identity feature database based on the target feature information under the condition that the first average feature value, the second average feature value and the third average feature value meet preset conditions;
wherein, the preset conditions are:
and->
Wherein C is (Y-1) Representing a first average characteristic value, C (Y-2) Representing a second average characteristic value, C (Y-4) Representing a third average eigenvalue.
2. The method for identifying as in claim 1, further comprising, after determining the target identity associated with the target second behavior feature information as the identification result of the target image:
receiving an image output request of the target identity;
and outputting the target image in response to the image output request.
3. The method of claim 1, wherein the preset condition is that a number of matching results with a matching rate greater than a second threshold is smaller than a third threshold, and a maximum matching rate in the matching results is greater than the first threshold.
4. A method of identity recognition according to claim 3, wherein before the matching of the first behavioral characteristic information in the target characteristic information with the second behavioral characteristic information in the identity characteristic database in sequence, further comprises:
sequentially matching the first facial feature information in the target feature information with the second facial feature information in the identity feature database to obtain a facial feature matching result;
the sequentially matching the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database comprises the following steps:
and under the condition that the facial feature matching result does not meet the preset condition, sequentially matching the first behavior feature information in the target feature information with the second behavior feature information in the identity feature database.
5. The method as recited in claim 1, further comprising:
and if the dressing feature matching result does not meet the preset condition, storing the target feature information of the target image into a first sub-database in the identity feature database.
6. The method as recited in claim 5, further comprising:
adding identity information corresponding to the target image in the identity characteristic database;
and establishing an association relation between the target characteristic information corresponding to the target image in the first sub-database and the identity information, and storing the association relation, the identity information corresponding to the target image and the target characteristic information corresponding to the target image into a second sub-database in the identity characteristic information database.
7. The method according to claim 4, further comprising, in the case where the facial feature matching result does not satisfy the preset condition:
changing an image acquisition angle of an image acquisition device, and re-acquiring first facial feature information of the target image.
8. An apparatus for identification, comprising:
the acquisition module is used for acquiring target characteristic information of a target image;
the first matching module is used for sequentially matching the first behavior characteristic information in the target characteristic information with the second behavior characteristic information in the identity characteristic database to obtain a behavior characteristic matching result;
the first determining module is configured to determine, if the behavior feature matching result meets a preset condition, target second behavior feature information with a matching rate greater than a first threshold value with respect to the first behavior feature information in the identity feature database, determine a target identity associated with the target second behavior feature information as an identity recognition result of the target image, and update the identity feature database based on the first behavior feature information when the first behavior feature information is feature information that changes for a long time;
the second determining module is used for sequentially matching the first dressing feature information in the target feature information with the second dressing feature information in the identity database if the behavior feature matching result does not meet the preset condition to obtain a dressing matching result, determining target second dressing feature information with the matching rate of the first dressing feature information being greater than a first threshold value in the identity feature database if the dressing feature matching result meets the preset condition, determining a target identity associated with the target second dressing feature information as an identity recognition result of the target image, updating the identity feature database based on the first dressing feature information, and deleting the second dressing feature information before updating in the identity feature database;
the updating module is used for updating the first average characteristic value of the target characteristic information in a first natural month in a plurality of natural months, the second average characteristic value of the target characteristic information in a second natural month in the plurality of natural months and the third average characteristic value of the target characteristic information in a fourth natural month in the plurality of natural months;
the updating module is further configured to update the identity feature database based on the target feature information when the first average feature value, the second average feature value, and the third average feature value satisfy a preset condition;
wherein, the preset conditions are:
and->
Wherein C is (Y-1) Representing a first average characteristic value, C (Y-2) Representing a second average characteristic value, C (Y-4) Representing a third average eigenvalue.
9. An identification device, the device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of identity recognition as claimed in any one of claims 1-7.
10. A computer storage medium having stored thereon computer program instructions which when executed by a processor perform the method of identification as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911382814.5A CN113052197B (en) | 2019-12-28 | 2019-12-28 | Method, device, equipment and medium for identity recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911382814.5A CN113052197B (en) | 2019-12-28 | 2019-12-28 | Method, device, equipment and medium for identity recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052197A CN113052197A (en) | 2021-06-29 |
| CN113052197B true CN113052197B (en) | 2024-03-12 |
Family
ID=76507400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911382814.5A Active CN113052197B (en) | 2019-12-28 | 2019-12-28 | Method, device, equipment and medium for identity recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052197B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792603A (en) * | 2021-08-16 | 2021-12-14 | 北京神州慧达信息技术有限公司 | Livestock body identification system based on artificial intelligence and use method |
| CN116661975B (en) * | 2023-07-21 | 2023-10-13 | 天津卓朗昆仑云软件技术有限公司 | Process running control method and device, electronic equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079109A (en) * | 2007-06-26 | 2007-11-28 | 北京中星微电子有限公司 | Identity identification method and system based on uniform characteristic |
| CN102122354A (en) * | 2011-03-15 | 2011-07-13 | 上海交通大学 | Adaptive characteristic block selection-based gait identification method |
| KR20110129789A (en) * | 2010-05-26 | 2011-12-02 | 수원대학교산학협력단 | A security system and a method using multiplex biometrics of face and body |
| CN103049741A (en) * | 2012-12-21 | 2013-04-17 | 中国科学院合肥物质科学研究院 | Foot-to-ground acting force-based gait feature extraction method and gait identification system |
| CN103123690A (en) * | 2011-11-21 | 2013-05-29 | 中兴通讯股份有限公司 | Information acquisition device, information acquisition method, identification system and identification method |
| CN103942577A (en) * | 2014-04-29 | 2014-07-23 | 上海复控华龙微系统技术有限公司 | Identity identification method based on self-established sample library and composite characters in video monitoring |
| CN104133920A (en) * | 2014-07-18 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | User behavior collection method and device |
| CN105243357A (en) * | 2015-09-15 | 2016-01-13 | 深圳市环阳通信息技术有限公司 | Identity document-based face recognition method and face recognition device |
| CN105930832A (en) * | 2016-05-18 | 2016-09-07 | 成都芯软科技发展有限公司 | Identity recognition system and method |
| CN107967453A (en) * | 2017-11-24 | 2018-04-27 | 河北三川科技有限公司 | Hotel occupancy identity checking method and verifying system based on recognition of face |
| CN108038937A (en) * | 2017-11-22 | 2018-05-15 | 同观科技（深圳）有限公司 | A kind of methods of exhibiting, device, terminal device and the storage medium of welcome's information |
| WO2018133666A1 (en) * | 2017-01-17 | 2018-07-26 | 腾讯科技（深圳）有限公司 | Method and apparatus for tracking video target |
| CN108932419A (en) * | 2018-06-08 | 2018-12-04 | 成都第二记忆科技有限公司 | A kind of photography and vedio recording device identification matching process and system |
| CN110020617A (en) * | 2019-03-27 | 2019-07-16 | 五邑大学 | A kind of personal identification method based on biological characteristic, device and storage medium |
| CN110402840A (en) * | 2019-07-25 | 2019-11-05 | 深圳市阿龙电子有限公司 | Live pig monitoring terminal and live pig monitoring system based on image recognition |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7711145B2 (en) * | 2006-01-27 | 2010-05-04 | Eastman Kodak Company | Finding images with multiple people or objects |
| US11074495B2 (en) * | 2013-02-28 | 2021-07-27 | Z Advanced Computing, Inc. (Zac) | System and method for extremely efficient image and pattern recognition and artificial intelligence platform |
-
2019
- 2019-12-28 CN CN201911382814.5A patent/CN113052197B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079109A (en) * | 2007-06-26 | 2007-11-28 | 北京中星微电子有限公司 | Identity identification method and system based on uniform characteristic |
| KR20110129789A (en) * | 2010-05-26 | 2011-12-02 | 수원대학교산학협력단 | A security system and a method using multiplex biometrics of face and body |
| CN102122354A (en) * | 2011-03-15 | 2011-07-13 | 上海交通大学 | Adaptive characteristic block selection-based gait identification method |
| CN103123690A (en) * | 2011-11-21 | 2013-05-29 | 中兴通讯股份有限公司 | Information acquisition device, information acquisition method, identification system and identification method |
| CN103049741A (en) * | 2012-12-21 | 2013-04-17 | 中国科学院合肥物质科学研究院 | Foot-to-ground acting force-based gait feature extraction method and gait identification system |
| CN103942577A (en) * | 2014-04-29 | 2014-07-23 | 上海复控华龙微系统技术有限公司 | Identity identification method based on self-established sample library and composite characters in video monitoring |
| CN104133920A (en) * | 2014-07-18 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | User behavior collection method and device |
| CN105243357A (en) * | 2015-09-15 | 2016-01-13 | 深圳市环阳通信息技术有限公司 | Identity document-based face recognition method and face recognition device |
| CN105930832A (en) * | 2016-05-18 | 2016-09-07 | 成都芯软科技发展有限公司 | Identity recognition system and method |
| WO2018133666A1 (en) * | 2017-01-17 | 2018-07-26 | 腾讯科技（深圳）有限公司 | Method and apparatus for tracking video target |
| CN108038937A (en) * | 2017-11-22 | 2018-05-15 | 同观科技（深圳）有限公司 | A kind of methods of exhibiting, device, terminal device and the storage medium of welcome's information |
| CN107967453A (en) * | 2017-11-24 | 2018-04-27 | 河北三川科技有限公司 | Hotel occupancy identity checking method and verifying system based on recognition of face |
| CN108932419A (en) * | 2018-06-08 | 2018-12-04 | 成都第二记忆科技有限公司 | A kind of photography and vedio recording device identification matching process and system |
| CN110020617A (en) * | 2019-03-27 | 2019-07-16 | 五邑大学 | A kind of personal identification method based on biological characteristic, device and storage medium |
| CN110402840A (en) * | 2019-07-25 | 2019-11-05 | 深圳市阿龙电子有限公司 | Live pig monitoring terminal and live pig monitoring system based on image recognition |
Non-Patent Citations (1)
| Title |
|---|
| 基于卷积神经网络的身份识别技术研究与应用;王洋;《优秀硕士学位论文全文库信息科技辑》;1-56 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052197A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8792686B2 (en) | Biometric authentication device, method of controlling biometric authentication device and non-transitory, computer readable storage medium | |
| CN113382279B (en) | Live broadcast recommendation method, device, equipment, storage medium and computer program product | |
| CN113052197B (en) | Method, device, equipment and medium for identity recognition | |
| JP6798798B2 (en) | Method and device for updating data for user authentication | |
| US20210216617A1 (en) | Biometric authentication device, biometric authentication method, and computer-readable recording medium recording biometric authentication program | |
| KR102401194B1 (en) | Method and apparatus for authenticating a user using an electrocardiogram signal | |
| CN111695502A (en) | Feature updating method and device for face recognition and computer equipment | |
| JP5659777B2 (en) | Authentication processing apparatus, authentication processing method, and program | |
| CN105718920A (en) | Fingerprint identification method and fingerprint identification device | |
| WO2017156963A1 (en) | Method for fingerprint unlocking, and terminal | |
| US20220215292A1 (en) | Method to identify incorrect account numbers | |
| CN111985360A (en) | Face recognition method, device, equipment and medium | |
| WO2019223339A1 (en) | Method, device and apparatus for facial matching, and storage medium | |
| CN106446844B (en) | Posture estimation method and device and computer system | |
| KR101628602B1 (en) | Similarity judge method and appratus for judging similarity of program | |
| CN111783677B (en) | Face recognition method, device, server and computer readable medium | |
| EP3203415A1 (en) | Biometric authentication device, biometric authentication method and biometric authentication program | |
| KR20210018586A (en) | Method and apparatus for identifying video content using biometric features of characters | |
| CN111931148A (en) | Image processing method and device and electronic equipment | |
| CN110633647A (en) | Living body detection method and device | |
| CN111626173B (en) | Method for updating face feature vector in database | |
| CN115565222A (en) | Face recognition method, face recognition system, terminal device and storage medium | |
| CN115063858A (en) | Video facial expression recognition model training method, device, equipment and storage medium | |
| EP4152182A1 (en) | Authentication method, authentication program, and information processing device | |
| CN113869099A (en) | Image processing method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |