CN113221088B - User identity identification method and device - Google Patents
User identity identification method and device Download PDFInfo
- Publication number
- CN113221088B CN113221088B CN202110661848.9A CN202110661848A CN113221088B CN 113221088 B CN113221088 B CN 113221088B CN 202110661848 A CN202110661848 A CN 202110661848A CN 113221088 B CN113221088 B CN 113221088B
- Authority
- CN
- China
- Prior art keywords
- feature
- data
- user
- target
- gait
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/36—User authentication by graphic or iconic representation
-
- 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
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
Abstract
The invention provides a user identity identification method and a device, wherein the method comprises the following steps: acquiring characteristic information of a user to be identified; acquiring a first target gait feature based on the feature information; calculating the similarity between the target gait feature and each gait feature in the first database; setting the gait features with the similarity larger than a preset threshold as second target gait features; acquiring iris features associated with each second target gait feature; determining a data type for identifying the identity of the user as a target data type; storing feature data belonging to the target data type in each iris feature into a second database; when an identity recognition request is received, extracting target iris characteristics and target characteristic data corresponding to the type of the target data; and comparing the target characteristic data with each characteristic data in the second database so as to determine the user identity of the user to be identified. By applying the method, the time for user identity recognition can be shortened, and the success rate of user identity recognition can be improved.
Description
Technical Field
The invention relates to the technical field of biological feature recognition, in particular to a user identity recognition method and device.
Background
With the rapid development of computer technology and biometric identification technology, biometric identification technologies such as face identification, fingerprint identification, iris identification and the like have been widely applied to our daily lives.
In the actual biometric identification process, after the human body biometric characteristics are collected, the human body biometric characteristics are required to be matched with a large number of stored human body biometric characteristics in a database, so that the identity of the user is confirmed, and the subsequent business operation is completed. However, as the number of biometric features of the human body stored in the database increases, the time required for matching increases, and the user identification may easily time out or fail.
Disclosure of Invention
In view of this, the present invention provides a user identification method, by which the user identification time can be shortened and the success rate of user identification can be improved.
The invention also provides a user identity recognition device which is used for ensuring the realization and the application of the method in practice.
A user identity recognition method comprises the following steps:
acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, wherein the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area;
acquiring a first target gait feature of the user to be identified based on the feature information;
comparing the target gait features with each gait feature in a preset first database, and calculating the similarity between each gait feature in the first database and the first target gait feature;
setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature;
acquiring iris features associated with each second target gait feature, wherein the iris features comprise a plurality of feature data, and each feature data belongs to different data types;
determining a data type used for identifying the identity of the user to be identified as a target data type in each data type;
storing feature data belonging to the target data type in each iris feature into a preset second database;
when an identity recognition request corresponding to the user to be recognized and sent by a request end is received, extracting target iris characteristics of the user to be recognized in the identity recognition request and target characteristic data corresponding to the target data type in the target iris characteristics;
and comparing the target characteristic data with each characteristic data in the second database, and determining the user identity of the user to be identified based on the comparison result.
The above method, optionally, further includes:
extracting first face features of the user to be identified in the feature information;
generating a unique identification code corresponding to the user to be identified based on the first face feature;
and sending the first face feature and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face feature matched with the first face feature.
Optionally, in the method, after extracting the first facial feature of the user to be identified in the feature information, the method further includes:
setting the first facial features as target identification features of the second database;
when an identity recognition request sent by the request terminal is received, acquiring a second face feature contained in the identity recognition request;
searching for an identification feature matched with the second face feature;
and when the identification feature matched with the second face feature is found to be the target identification feature, determining the identity identification request to be the identity identification request corresponding to the user to be identified.
Optionally, in the method, the obtaining a first target gait feature of the user to be identified based on the feature information includes:
splitting the characteristic information into a plurality of human body posture pictures;
inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
wherein, the training process of the gait recognition model comprises the following steps: the method comprises the steps of obtaining preset sample data and a data label corresponding to each sample data, wherein the sample data are human body posture image groups of the same user, and the data label is the real gait feature of the user to which the corresponding sample data belong; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; and calculating a loss function corresponding to each sample data based on the training result and the data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model.
Optionally, in the foregoing method, the determining, in each data type, a data type used for identifying an identity of the user to be identified as a target data type includes:
extracting each feature data in each iris feature;
in each feature data of each iris feature, performing differentiation comparison on each feature data belonging to the same data type to obtain a differentiation value corresponding to each data type;
and determining the data type with the maximum difference value as a target data type for identifying the identity of the user to be identified.
A user identification apparatus comprising:
the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, and the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area;
the second acquisition unit is used for acquiring a first target gait feature of the user to be identified based on the feature information;
the first comparison unit is used for comparing the target gait features with each gait feature in a preset first database and calculating the similarity between each gait feature in the first database and the first target gait features;
the first setting unit is used for setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature;
a third obtaining unit, configured to obtain an iris feature associated with each second target gait feature, where the iris feature includes a plurality of feature data, and each feature data belongs to a different data type;
a first determining unit, configured to determine, in each data type, that a data type used for identifying an identity of the user to be identified is a target data type;
the storage unit is used for storing the feature data belonging to the target data type in each iris feature into a preset second database;
the first extraction unit is used for extracting the target iris characteristics of the user to be identified in the identity identification request and the target characteristic data corresponding to the target data type in the target iris characteristics when receiving the identity identification request corresponding to the user to be identified sent by a request end;
and the second comparison unit is used for comparing the target characteristic data with each characteristic data in the second database and determining the user identity of the user to be identified based on the comparison result.
The above apparatus, optionally, further comprises:
the second extraction unit is used for extracting the first face features of the user to be identified in the feature information;
the generating unit is used for generating a unique identification code corresponding to the user to be identified based on the first face feature;
and the sending unit is used for sending the first face feature and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face feature matched with the first face feature.
The above apparatus, optionally, further comprises:
a second setting unit configured to set the first facial feature as a target identification feature of the second database;
the fourth acquiring unit is used for acquiring a second face feature contained in the identity identification request when the identity identification request sent by the requesting terminal is received;
the searching unit is used for searching the identification characteristics matched with the second face characteristics;
and a second determining unit, configured to determine that the identity recognition request is an identity recognition request corresponding to the user to be recognized when the identification feature matched with the second face feature is found to be the target identification feature.
The above apparatus, optionally, the second obtaining unit includes:
the splitting subunit is used for splitting the characteristic information into a plurality of human body posture pictures;
the input subunit is used for inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
the gait recognition model training process comprises the following steps: acquiring preset sample data and a data tag corresponding to each sample data, wherein the sample data is a human body posture graph group of the same user, and the data tag is the real gait feature of the user to which the corresponding sample data belongs; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; and calculating a loss function corresponding to each sample data based on the training result and the data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model.
The above apparatus, optionally, the first determining unit includes:
an extraction subunit, configured to extract respective feature data in the respective iris features;
the comparison subunit is configured to perform differentiation comparison on each feature data belonging to the same data type in each feature data of each iris feature to obtain a differentiation value corresponding to each data type;
and the determining subunit is used for determining the data type with the maximum difference value as the target data type for identifying the identity of the user to be identified.
A storage medium, the storage medium including stored instructions, wherein when executed, the instructions control a device on which the storage medium is located to execute the above-mentioned user identification method.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the user identification method.
Compared with the prior art, the invention has the following advantages:
the invention provides a user identity identification method, which comprises the following steps: acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, wherein the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area; acquiring a first target gait feature of the user to be identified based on the feature information; comparing the target gait features with each gait feature in a preset first database, and calculating the similarity between each gait feature in the first database and the first target gait feature; setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature; acquiring iris features associated with each second target gait feature, wherein the iris features comprise a plurality of feature data, and each feature data belongs to different data types; determining the data type used for identifying the identity of the user to be identified as a target data type in each data type; storing feature data belonging to the target data type in each iris feature into a preset second database; when an identity recognition request corresponding to the user to be recognized and sent by a request end is received, extracting target iris characteristics of the user to be recognized in the identity recognition request and target characteristic data corresponding to the target data type in the target iris characteristics; and comparing the target characteristic data with each characteristic data in the second database, and determining the user identity of the user to be identified based on the comparison result. The method provided by the invention can shorten the time of user identity identification and improve the success rate of user identity identification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for identifying a user identity according to an embodiment of the present invention;
fig. 2 is a flowchart of another method of a user identity recognition method according to an embodiment of the present invention;
fig. 3 is a device structure diagram of a user identification device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In this application, relational terms such as first and second, and the like may be 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, and the terms "comprise", "comprises", 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 also other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The invention is operational with numerous general purpose or special purpose computing device environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multi-processor apparatus, distributed computing environments that include any of the above devices or equipment, and the like.
The embodiment of the invention provides a user identity identification method, which can be applied to various system platforms, wherein an execution subject of the method can be a computer terminal or a processor of various mobile devices, and a flow chart of the method is shown in fig. 1 and specifically comprises the following steps:
s101: and acquiring the characteristic information of the user to be identified, which is acquired by the data acquisition equipment.
The characteristic information is a dynamic picture or a video of the user to be identified walking in a preset identification area.
In the invention, the data acquisition equipment is used for acquiring the dynamic pictures or videos of the user in real time, and when the situation that the user passes through the identification area is detected, the dynamic pictures or videos of the user are acquired and uploaded to the server. The processor acquires characteristic information uploaded to the server by the data acquisition equipment.
It should be noted that the data acquisition device may be disposed at a store entrance, a bank entrance, a railway station ticket checking entrance, and other places where identification may be required.
S102: and acquiring a first target gait feature of the user to be identified based on the feature information.
In the invention, the first target gait characteristics comprise gait characteristic data such as walking posture, acting force magnitude and direction, step spacing and the like during walking. And analyzing the characteristic information to obtain a first target gait characteristic of the user to be identified.
S103: and comparing the target gait features with each gait feature in a preset first database, and calculating the similarity between each gait feature in the first database and the first target gait feature.
In the invention, a large number of biological characteristics of users are stored in a first database, wherein the biological characteristics specifically comprise gait characteristics, face characteristics, fingerprint characteristics, iris characteristics and the like, and the biological characteristics belonging to the same user are mutually associated in the first database. After the first target gait feature of the user to be identified is obtained, the first target gait feature is compared with each gait feature in the first database, and the similarity between each gait feature in the first database and the first target gait feature is calculated.
Specifically, the step of calculating the gait feature in the first database and the first target gait feature is to calculate the similarity between the gait feature data, for example, the similarity between walking postures, the similarity between acting force and direction, the similarity between step intervals, and the like, so as to obtain the total similarity between two gait features.
S104: and setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature.
According to the gait feature detection method and device, the gait features with similarity larger than the preset threshold value with the first target gait feature are screened from the first database to be used as second target gait features according to the preset threshold value. In each of the second target gait features, there may be any second target gait feature that is a previously-entered gait feature of the user to be identified.
S105: acquiring iris features associated with each of the second target gait features.
The iris features comprise a plurality of feature data, and each feature data belongs to different data types.
In the present invention, the first database contains a large number of biometric features of users, and the biometric features belonging to the same user are correlated with each other. After the second target gait features are screened out, the iris features associated with the second target gait features in the first database are obtained, and feature data of the iris features are extracted.
Specifically, the data types to which the feature data in the iris features belong include iris color, form, and wrinkle density. For example, characteristic data representing the data type as iris color is #0996633, #8B4513, or the like.
S106: and determining the data type used for identifying the identity of the user to be identified as a target data type in each data type.
In the invention, after each feature data in each iris feature is obtained, a target data type for identifying the identity of the user to be identified is screened out from each data type according to each feature data.
S107: and storing the feature data belonging to the target data type in each iris feature into a preset second database.
In the invention, the characteristic data belonging to the target data type in each iris characteristic is extracted, and each characteristic data is stored into a second database.
S108: when an identity recognition request corresponding to the user to be recognized and sent by a request end is received, extracting the target iris characteristics of the user to be recognized in the identity recognition request and target characteristic data corresponding to the target data type in the target iris characteristics.
In the invention, when a user to be identified needs to pay or is subjected to identity identification security check and other scenes, a request end can scan the target iris features of the user to be identified, generate an identity identification request carrying the target iris features and corresponding to the identity identification request, send the identity identification request to a server, and a processor in the server extracts the target iris features and target feature data corresponding to the target data type in the target iris features after receiving the identity identification request.
Specifically, the request end may be a terminal device such as a payment device and a ticket checking device, which can acquire iris features.
S109: and comparing the target characteristic data with each characteristic data in the second database, and determining the user identity of the user to be identified based on the comparison result.
It can be understood that before the user identification is needed, a small part of iris features are screened out through gait recognition to perform feature extraction, and one data type feature data is screened out from each iris feature. When the user identity is identified, only the target feature data corresponding to the target data type of the user to be identified is extracted, the target feature data is compared with each feature data in the second database, namely, the similarity between each feature data in the second database and the target feature data is calculated, the feature data with the highest similarity with the target feature data is determined, and the user identity of the user corresponding to the feature data with the highest similarity is determined as the user identity of the user to be identified.
In the user identity identification method provided by the embodiment of the invention, when the user to be identified walks into the designated identification area, the data acquisition equipment acquires the dynamic picture or video of the user to be identified when walking. The method comprises the steps of obtaining characteristic information of a user to be identified, which is collected by data collection equipment, and obtaining a first target gait characteristic of the user to be identified from the characteristic information. Comparing the first target gait feature with each gait feature in a first database, calculating the similarity, determining each gait feature with the first target gait feature, wherein the similarity between each gait feature and the first target gait feature is larger than a preset threshold value, as a second target gait feature, and acquiring each iris feature associated with the second target gait feature. And selecting a target data type for identity recognition from the data types corresponding to each characteristic data based on each characteristic data of the iris characteristics, extracting the characteristic data belonging to the target data type in each iris characteristic, and storing the characteristic data in a second database. When the request terminal sends an identity recognition request corresponding to the user to be recognized, extracting the target iris characteristics of the user to be recognized in the identity recognition request, and acquiring target characteristic data belonging to the type of target data from the target iris characteristics. And comparing the target characteristic data with each characteristic data in the second database, and determining the user corresponding to the characteristic data with the highest similarity as the user to be identified so as to determine the final identity of the user to be identified.
The method provided by the embodiment of the invention can shorten the time for identifying the user identity and improve the success rate of identifying the user identity.
In the method provided by the embodiment of the present invention, the feature information of the user to be identified is a dynamic picture or a video, and besides the first target gait feature of the user to be identified can be obtained from the feature information, the first facial feature of the user to be identified can also be obtained from the feature information, and the specific process may include:
extracting first face features of the user to be identified in the feature information;
generating a unique identification code corresponding to the user to be identified based on the first face feature;
and sending the first face features and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face features matched with the first face features.
It can be understood that, in order to extract the gait features of the user to be identified, the data acquisition devices are all arranged at a position far away from the identification area. Therefore, when the first face feature of the user to be identified is obtained, the feature information is firstly split into a plurality of human body posture images, a picture displaying the clearest face is selected from the human body posture images, and the first face feature of the user to be identified is extracted from the picture. Based on the first face feature, the first face feature is converted into a feature parameter, and the feature parameter is set to be a unique identification code corresponding to the user to be identified. And sending the first face feature and the unique identification code to a request end. When the request terminal scans the face features of any user, matching the scanned face features with the first face features, and if the matching is consistent, determining that the user is the user to be identified. The request terminal acquires the target iris characteristics of the user to be identified and sends an identity identification request carrying the target iris characteristics and the unique identification code to the processor. After receiving the identification request, the processor can determine that the identification request is the identification request corresponding to the user to be identified according to the unique identification code, so as to call each iris feature in the second database to be compared with the target iris feature in the identification request, and determine the user identity of the user to be identified.
It should be noted that a plurality of second databases storing iris features are arranged in the processor, and each database corresponds to one user to be identified. And when the unique identification code corresponding to each user to be identified is generated, associating the unique identification code with a second database corresponding to the user to be identified. And when an identity identification request sent by a request end is received, acquiring the unique identification code from the identity identification request, and acquiring a second database associated with the unique identification code. After the target iris feature of the user to be recognized included in the identification request is obtained, the processes from S106 to S109 are performed, which will not be described herein again.
Based on the method provided by the embodiment, the first face feature of the user to be identified can be extracted from the feature information, and the unique identification code corresponding to the user to be identified is generated. The requesting end can collect the face characteristics of the user when the iris characteristics of the user are collected, match the collected face characteristics with the stored first face characteristics, and send the unique identification code and the iris characteristics to the processor for further identity recognition after the matching is successful.
Specifically, after extracting the first face feature of the user to be identified in the feature information, the method may further include:
setting the first facial features as target identification features of the second database;
when an identity recognition request sent by the request terminal is received, acquiring a second face feature contained in the identity recognition request;
searching for an identification feature matched with the second face feature;
and when the identification feature matched with the second face feature is found to be the target identification feature, determining the identity identification request to be the identity identification request corresponding to the user to be identified.
It is to be understood that, after the first facial features of the user to be recognized in the feature information are extracted, the first facial features are set as the target identification features of the second database. Since a plurality of second databases storing iris features may be provided in the processor, the face features of the user to be recognized corresponding to each second database are set as the target identification features of the second database. When the request end collects the iris characteristics of any user, the request end collects the face characteristics of the user at the same time. And determining the face features acquired by the request end as second face features. And the request terminal sends an identity identification request carrying the second face characteristic and the iris characteristic. And after receiving the identification request, the processor acquires a second face feature. And matching the face features with each identification feature stored in the processor so as to search the identification features matched with the second face features in each identification feature. If the target identification feature of the second database is matched with the second face feature in a consistent manner, that is, the currently found identification feature matched with the second face feature is the target identification feature, it may be determined that the identity identification request sent by the request end is the identity identification request corresponding to the user to be identified in the above S101. And if the identification features matched with the currently searched second face features are identification features of other second databases, determining that the identification request sent by the request end is an identification request corresponding to the to-be-identified user corresponding to the other second databases.
It can be understood that, after determining that the identification request is an identification request corresponding to a user to be identified, the second database corresponding to the user to be identified may be directly obtained, so as to implement the identification process in S105 to S190.
By applying the method provided by the embodiment of the invention, the second database is marked by extracting the face features of the user to be identified, so that the second database of the user to be identified can be quickly positioned in the plurality of second databases when the user identity is identified, and the identity identification process is accelerated.
In the method provided in the embodiment of the present invention, based on the content of the foregoing S106, a process of determining, in each data type, that the data type used for identifying the identity of the user to be identified is a target data type is shown in fig. 2, and specifically may include:
s201: and extracting each characteristic data in each iris characteristic.
In the invention, each iris feature contains feature data of a plurality of data types, and the iris features of each iris are different because each iris is unique. The differences between the features of the respective irises are embodied between the respective feature data.
S202: and in each feature data of each iris feature, performing differentiation comparison on each feature data belonging to the same data type to obtain a differentiation value corresponding to each data type.
In the present invention, the respective feature data are differentially compared, for example, iris colors in the respective iris features are differentially compared, and differences between the respective iris colors are compared. And after comparing all characteristic parameters in all iris characteristics, obtaining a difference value corresponding to each data type.
Specifically, the larger the difference value is, the more obvious the difference between the feature data belonging to the data type corresponding to the difference value is.
S203: and determining the data type with the maximum difference value as a target data type for identifying the identity of the user to be identified.
In the invention, the data type with the largest difference value represents that the difference of each characteristic data belonging to the data type is most obvious, and the identity of the user to be identified can be quickly obtained only by comparing and identifying the characteristic data belonging to the data type during the subsequent identity identification.
In the user identity recognition method provided by the embodiment of the invention, after the features of each iris person are obtained, each feature data in each iris feature is extracted, the feature data are subjected to differentiation comparison, specifically, each feature data belonging to the same data type are subjected to differentiation comparison to obtain a difference value corresponding to each data type, and the data type with the largest difference value is taken as a target data type for finally carrying out user identity recognition.
It can be understood that after the data features are differentiated and compared according to the data types, only the feature data of the target data type needs to be identified during subsequent identification, and all feature data in the iris features need to be identified, so that the time for identifying the user identity is shortened.
In the method provided in the embodiment of the present invention, based on the content of S102, the obtaining a first target gait feature of the user to be identified based on the feature information includes:
splitting the characteristic information into a plurality of human body posture pictures;
inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
the gait recognition model training process comprises the following steps: acquiring preset sample data and a data tag corresponding to each sample data, wherein the sample data is a human body posture graph group of the same user, and the data tag is the real gait feature of the user to which the corresponding sample data belongs; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; and calculating a loss function corresponding to each sample data based on the training result and the data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model.
In the user identity identification method provided by the embodiment of the invention, the gait identification model can identify the walking posture of the human body, the direction and the size of the walking force, the walking change state of the human skeleton and other related information according to the input human posture graph. After the characteristic information is split into a plurality of human body posture images, the human body posture images are sequentially input into a gait recognition model according to a corresponding sequence, after the human body posture images are input, the gait recognition model sequentially recognizes the human body posture images, simulates walking gait of a user, performs related calculation, and finally outputs a first target gait characteristic of the user to be recognized.
It should be noted that the gait recognition model is trained through a large amount of training data to ensure the accuracy of the gait recognition model in gait recognition.
And in the process of applying the sample data to carry out model training, the gait recognition model needs to ensure that the output result corresponding to the currently recognized sample data is infinitely close to the data label corresponding to the sample data. And if the error precision between the output result and the data label is not less than the preset threshold value, calculating a corresponding loss function, adjusting the parameter adjustment of the model according to the loss function, then continuing training, and finishing the training when the error precision between the training result output by the gait recognition model and the data label is less than the preset threshold value.
Optionally, the gait recognition model is subjected to model parameter adjustment through a loss function, and in the training process, if the training result output by the gait recognition model is no longer convergent, the training is finished.
By applying the method provided by the embodiment of the invention, the gait characteristics of the user to be identified are identified through the gait identification model, so that the accuracy of the acquired gait characteristics is improved.
The specific implementation procedures and derivatives thereof of the above embodiments are within the scope of the present invention.
Corresponding to the method described in fig. 1, an embodiment of the present invention further provides a user identity recognition apparatus, which is used for implementing the method in fig. 1 specifically, the user identity recognition apparatus provided in the embodiment of the present invention may be applied to a computer terminal or various mobile devices, and a schematic structural diagram of the user identity recognition apparatus is shown in fig. 3, and specifically includes:
the first obtaining unit 301 is configured to obtain feature information of a user to be identified, which is collected by a data collection device, where the feature information is a dynamic picture or a video of the user to be identified walking in a preset identification area;
a second obtaining unit 302, configured to obtain a first target gait feature of the user to be identified based on the feature information;
a first comparison unit 303, configured to compare the target gait feature with each gait feature in a preset first database, and calculate a similarity between each gait feature in the first database and the first target gait feature;
a first setting unit 304, configured to set, as a second target gait feature, a gait feature with a similarity to the first target gait feature being greater than a preset threshold;
a third obtaining unit 305, configured to obtain an iris feature associated with each second target gait feature, where the iris feature includes a plurality of feature data, and each of the feature data belongs to a different data type;
a first determining unit 306, configured to determine, in each data type, that a data type used for identifying an identity of the user to be identified is a target data type;
a storage unit 307, configured to store, in a preset second database, feature data belonging to the target data type in each of the iris features;
a first extracting unit 308, configured to, when an identity identification request corresponding to the user to be identified and sent by a request end is received, extract a target iris feature of the user to be identified in the identity identification request and target feature data corresponding to the target data type in the target iris feature;
a second comparing unit 309, configured to compare the target feature data with each feature data in the second database, and determine, based on a comparison result, a user identity of the user to be identified.
According to the user identity recognition device provided by the embodiment of the invention, when a user to be recognized walks into the designated recognition area, the data acquisition equipment acquires the dynamic picture or video of the user to be recognized when the user walks. The method comprises the steps of obtaining characteristic information of a user to be identified, wherein the characteristic information is collected by data collection equipment, and obtaining a first target gait characteristic of the user to be identified from the characteristic information. Comparing the first target gait feature with each gait feature in a first database, calculating the similarity, determining each gait feature with the first target gait feature, wherein the similarity between each gait feature and the first target gait feature is larger than a preset threshold value, as a second target gait feature, and acquiring each iris feature associated with the second target gait feature. And selecting a target data type for identity recognition from the data types corresponding to each feature data based on each feature data of the iris features, extracting the feature data belonging to the target data type from each iris feature, and storing the feature data in a second database. When the request terminal sends an identity recognition request corresponding to the user to be recognized, extracting the target iris characteristics of the user to be recognized in the identity recognition request, and acquiring target characteristic data belonging to the type of target data from the target iris characteristics. And comparing the target characteristic data with each characteristic data in the second database, and determining the user corresponding to the characteristic data with the highest similarity as the user to be identified so as to determine the final identity of the user to be identified.
By applying the device provided by the embodiment of the invention, the time for identifying the user identity can be shortened, and the success rate of identifying the user identity is improved.
The device provided by the embodiment of the invention further comprises:
the second extraction unit is used for extracting the first face features of the user to be identified in the feature information;
the generating unit is used for generating a unique identification code corresponding to the user to be identified based on the first face feature;
and the sending unit is used for sending the first face feature and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face feature matched with the first face feature.
The device provided by the embodiment of the invention also comprises:
a second setting unit configured to set the first facial feature as a target identification feature of the second database;
the fourth acquiring unit is used for acquiring a second face feature contained in the identity identification request when the identity identification request sent by the requesting terminal is received;
the searching unit is used for searching the identification characteristics matched with the second face characteristics;
and the second determining unit is used for determining that the identity recognition request is the identity recognition request corresponding to the user to be recognized when the identification feature matched with the second face feature is found to be the target identification feature.
In the apparatus provided in the embodiment of the present invention, the second obtaining unit 302 includes:
the splitting subunit is used for splitting the characteristic information into a plurality of human body posture pictures;
the input subunit is used for inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
wherein, the training process of the gait recognition model comprises the following steps: the method comprises the steps of obtaining preset sample data and a data label corresponding to each sample data, wherein the sample data are human body posture image groups of the same user, and the data label is the real gait feature of the user to which the corresponding sample data belong; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; and calculating a loss function corresponding to each sample data based on the training result and the data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model.
In the apparatus provided in the embodiment of the present invention, the first determining unit 306 includes:
an extraction subunit, configured to extract each feature data in each iris feature;
a comparison subunit, configured to perform difference comparison on each feature data belonging to the same data type in each feature data of each iris feature, so as to obtain a difference value corresponding to each data type;
and the determining subunit is used for determining the data type with the maximum difference value as the target data type for identifying the identity of the user to be identified.
The specific working processes of each unit and sub-unit in the user identity recognition apparatus disclosed in the above embodiment of the present invention can refer to the corresponding contents in the user identity recognition method disclosed in the above embodiment of the present invention, and are not described herein again.
The embodiment of the invention also provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the equipment where the storage medium is located is controlled to execute the user identity identification method.
An electronic device is provided in an embodiment of the present invention, and a schematic structural diagram of the electronic device is shown in fig. 4, which specifically includes a memory 401 and one or more instructions 402, where the one or more instructions 402 are stored in the memory 401 and configured to be executed by one or more processors 403 to execute the one or more instructions 402 to:
acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, wherein the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area;
acquiring a first target gait feature of the user to be identified based on the feature information;
comparing the target gait features with each gait feature in a preset first database, and calculating the similarity between each gait feature in the first database and the first target gait feature;
setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature;
acquiring iris features associated with each second target gait feature, wherein the iris features comprise a plurality of feature data, and each feature data belongs to different data types;
determining a data type used for identifying the identity of the user to be identified as a target data type in each data type;
storing feature data belonging to the target data type in each iris feature into a preset second database;
when an identity recognition request corresponding to the user to be recognized and sent by a request end is received, extracting target iris characteristics of the user to be recognized in the identity recognition request and target characteristic data corresponding to the target data type in the target iris characteristics;
and comparing the target characteristic data with each characteristic data in the second database, and determining the user identity of the user to be identified based on the comparison result.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments, which are substantially similar to the method embodiments, are described in a relatively simple manner, and reference may be made to some descriptions of the method embodiments for relevant points. The above-described system and system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
To clearly illustrate this interchangeability of hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A user identity recognition method is characterized by comprising the following steps:
acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, wherein the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area;
splitting the characteristic information into a plurality of human body posture pictures;
inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
wherein, the training process of the gait recognition model comprises the following steps: acquiring preset sample data and a data tag corresponding to each sample data, wherein the sample data is a human body posture graph group of the same user, and the data tag is the real gait feature of the user to which the corresponding sample data belongs; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; calculating a loss function corresponding to each sample data based on a training result and a data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model;
comparing the target gait features with each gait feature in a preset first database, and calculating the similarity between each gait feature in the first database and the first target gait feature;
setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature;
acquiring iris features associated with each second target gait feature, wherein the iris features comprise a plurality of feature data, and each feature data belongs to different data types;
determining the data type used for identifying the identity of the user to be identified as a target data type in each data type;
storing feature data belonging to the target data type in each iris feature into a preset second database;
when an identity recognition request corresponding to the user to be recognized and sent by a request end is received, extracting target iris characteristics of the user to be recognized in the identity recognition request and target characteristic data corresponding to the target data type in the target iris characteristics;
and comparing the target characteristic data with each characteristic data in the second database, and determining the user identity of the user to be identified based on the comparison result.
2. The method of claim 1, further comprising:
extracting first face features of the user to be identified in the feature information;
generating a unique identification code corresponding to the user to be identified based on the first face feature;
and sending the first face features and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face features matched with the first face features.
3. The method according to claim 2, wherein after extracting the first facial feature of the user to be identified in the feature information, the method further comprises:
setting the first face features as target identification features of the second database;
when an identity recognition request sent by the request terminal is received, acquiring a second face feature contained in the identity recognition request;
searching for an identification feature matched with the second face feature;
and when the identification feature matched with the second face feature is found to be the target identification feature, determining the identity identification request to be the identity identification request corresponding to the user to be identified.
4. The method according to claim 1, wherein the determining, in each of the data types, a data type for identifying the identity of the user to be identified as a target data type includes:
extracting each feature data in each iris feature;
in each feature data of each iris feature, performing differentiation comparison on each feature data belonging to the same data type to obtain a differentiation value corresponding to each data type;
and determining the data type with the maximum difference value as a target data type for identifying the identity of the user to be identified.
5. A user identification device, comprising:
the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring characteristic information of a user to be identified, which is acquired by data acquisition equipment, and the characteristic information is a dynamic picture or video of the user to be identified walking in a preset identification area;
the second acquisition unit is used for acquiring a first target gait feature of the user to be identified based on the feature information;
the first comparison unit is used for comparing the target gait features with each gait feature in a preset first database and calculating the similarity between each gait feature in the first database and the first target gait features;
the first setting unit is used for setting the gait feature with the similarity degree larger than a preset threshold value with the first target gait feature as a second target gait feature;
a third obtaining unit, configured to obtain an iris feature associated with each second target gait feature, where the iris feature includes a plurality of feature data, and each feature data belongs to a different data type;
the first determining unit is used for determining the data type used for identifying the identity of the user to be identified as a target data type in each data type;
the storage unit is used for storing the feature data which belong to the target data type in each iris feature into a preset second database;
the first extraction unit is used for extracting the target iris characteristics of the user to be identified in the identity identification request and the target characteristic data corresponding to the target data type in the target iris characteristics when the identity identification request corresponding to the user to be identified, which is sent by a request end, is received;
the second comparison unit is used for comparing the target characteristic data with each characteristic data in the second database and determining the user identity of the user to be identified based on the comparison result;
the second acquisition unit includes:
the splitting subunit is used for splitting the characteristic information into a plurality of human body posture pictures;
the input subunit is used for inputting each human body posture picture into a pre-trained gait recognition model, and triggering the gait recognition model to output a first target gait feature of the user to be recognized;
the gait recognition model training process comprises the following steps: the method comprises the steps of obtaining preset sample data and a data label corresponding to each sample data, wherein the sample data are human body posture image groups of the same user, and the data label is the real gait feature of the user to which the corresponding sample data belong; inputting each sample data into the gait recognition model, and obtaining a training result corresponding to each sample data output by the gait recognition model; and calculating a loss function corresponding to each sample data based on the training result and the data label corresponding to each sample data, and adjusting the gait recognition model based on each loss function until the error precision between the training result corresponding to the current sample data output by the gait recognition model and the data label corresponding to the current sample data is less than a preset threshold value, and finishing the training of the gait recognition model.
6. The apparatus of claim 5, further comprising:
the second extraction unit is used for extracting the first face features of the user to be identified in the feature information;
the generating unit is used for generating a unique identification code corresponding to the user to be identified based on the first face feature;
and the sending unit is used for sending the first face feature and the unique identification code to the request end so that the request end sends an identity identification request carrying the unique identification code after capturing the face feature matched with the first face feature.
7. The apparatus of claim 6, further comprising:
a second setting unit configured to set the first facial feature as a target identification feature of the second database;
the fourth acquiring unit is used for acquiring a second face feature contained in the identity recognition request when the identity recognition request sent by the requesting terminal is received;
the searching unit is used for searching the identification characteristics matched with the second face characteristics;
and a second determining unit, configured to determine that the identity recognition request is an identity recognition request corresponding to the user to be recognized when the identification feature matched with the second face feature is found to be the target identification feature.
8. The apparatus of claim 5, wherein the first determining unit comprises:
an extraction subunit, configured to extract each feature data in each iris feature;
the comparison subunit is configured to perform differentiation comparison on each feature data belonging to the same data type in each feature data of each iris feature to obtain a differentiation value corresponding to each data type;
and the determining subunit is used for determining the data type with the maximum difference value as the target data type for identifying the identity of the user to be identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110661848.9A CN113221088B (en) | 2021-06-15 | 2021-06-15 | User identity identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110661848.9A CN113221088B (en) | 2021-06-15 | 2021-06-15 | User identity identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113221088A CN113221088A (en) | 2021-08-06 |
| CN113221088B true CN113221088B (en) | 2022-08-19 |
Family
ID=77080306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110661848.9A Active CN113221088B (en) | 2021-06-15 | 2021-06-15 | User identity identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113221088B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117801A (en) * | 2018-08-20 | 2019-01-01 | 深圳壹账通智能科技有限公司 | Method, apparatus, terminal and the computer readable storage medium of recognition of face |
| CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901351B (en) * | 2010-07-28 | 2012-09-05 | 中国科学院自动化研究所 | Face and iris image fusion and recognition method based on hierarchical structure |
| US9875398B1 (en) * | 2016-06-30 | 2018-01-23 | The United States Of America As Represented By The Secretary Of The Army | System and method for face recognition with two-dimensional sensing modality |
| WO2020041728A1 (en) * | 2018-08-23 | 2020-02-27 | Averon Us, Inc. | Methods, apparatuses, and computer program products for frictionless custody chain management |
| CN110210444B (en) * | 2019-06-12 | 2020-08-25 | 湖北东方星海科技实业有限公司 | Application method of iris recognition technology |
| CN112528706A (en) * | 2019-09-17 | 2021-03-19 | 清华大学 | Personnel identification system and method thereof |
| CN111554055A (en) * | 2020-04-27 | 2020-08-18 | 中国银行股份有限公司 | Full-automatic safety device |
| CN112036894B (en) * | 2020-09-01 | 2023-08-18 | 中国银行股份有限公司 | Method and system for identity confirmation by utilizing iris characteristics and action characteristics |
-
2021
- 2021-06-15 CN CN202110661848.9A patent/CN113221088B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117801A (en) * | 2018-08-20 | 2019-01-01 | 深圳壹账通智能科技有限公司 | Method, apparatus, terminal and the computer readable storage medium of recognition of face |
| CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113221088A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105844206A (en) | Identity authentication method and identity authentication device | |
| CN105913507B (en) | A kind of Work attendance method and system | |
| JP2006293644A (en) | Information processing device and information processing method | |
| CN109903474A (en) | A kind of intelligence based on recognition of face opens cabinet method and device | |
| CN109376604B (en) | Age identification method and device based on human body posture | |
| CN109472247B (en) | Face recognition method based on deep learning non-fit type | |
| CN110633004B (en) | Interaction method, device and system based on human body posture estimation | |
| CN112132099A (en) | Identity recognition method, palm print key point detection model training method and device | |
| CN111626371A (en) | Image classification method, device and equipment and readable storage medium | |
| CN111401105B (en) | Video expression recognition method, device and equipment | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| CN113221086A (en) | Offline face authentication method and device, electronic equipment and storage medium | |
| EP3617993B1 (en) | Collation device, collation method and collation program | |
| CN113221088B (en) | User identity identification method and device | |
| CN116311400A (en) | Palm print image processing method, electronic device and storage medium | |
| CN112183167A (en) | Attendance checking method, authentication method, living body detection method, device and equipment | |
| CN111507124A (en) | Non-contact video lie detection method and system based on deep learning | |
| JP5279007B2 (en) | Verification system, verification method, program, and recording medium | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| Moshayedi et al. | Fingerprint Identification Banking (FIB); Affordable and Secure Biometric IOT Design | |
| Logronio et al. | Age Range Classification Through Facial Recognition Using Keras Model | |
| CN114359646A (en) | Video analysis method, device, system, electronic equipment and medium | |
| Mishra et al. | Integrating State-of-the-Art Face Recognition and Anti-Spoofing Techniques into Enterprise Information Systems | |
| Altun et al. | Face Verification System In Mobile Devices By Using Cognitive Services | |
| Bratoszewski et al. | Pilot testing of developed multimodal biometric identity verification system |
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 |