CN110390290A - A kind of method, apparatus, electronic equipment and storage medium identifying target object - Google Patents
A kind of method, apparatus, electronic equipment and storage medium identifying target object Download PDFInfo
- Publication number
- CN110390290A CN110390290A CN201910647518.7A CN201910647518A CN110390290A CN 110390290 A CN110390290 A CN 110390290A CN 201910647518 A CN201910647518 A CN 201910647518A CN 110390290 A CN110390290 A CN 110390290A
- Authority
- CN
- China
- Prior art keywords
- characteristic information
- information
- target object
- library
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
Abstract
This application discloses a kind of method, apparatus, electronic equipment and storage mediums for identifying target object, are related to information identification field；Wherein, this method comprises: obtaining the characteristic information of current time node destination object；The temporal characteristics information model crossed by pre-training identifies characteristic information, and carries out similarity with the characteristic information of the target object prestored in characteristic information library and compare；When similarity exceeds preset threshold value, recongnition of objects success, and the characteristic information of current time node destination object is updated in characteristic information library automatically；The temporal characteristics information model that pre-training is crossed is optimized automatically according to updated characteristic information library and retraining.In the case where can be realized target object unaware using disclosed method, the continuous identification feature information of temporal characteristics information model crossed based on pre-training simultaneously updates characteristic information library, accuracy of identification is continuously improved simultaneously, and lower to the requirement of the fitness of user, usage experience is more preferably.
Description
Technical field
The present invention relates to information to identify field, and in particular to it is a kind of identify the method, apparatus of target object, electronic equipment and
Storage medium.
Background technique
This technology of target identification is commonly utilized in the fields such as identification, password unlock in the prior art, generallys use
Method be first extract target object feature and reliable model is established to target object, then model respectively；But these
Feature can over time and change (such as gradually aging, beard variation, hair covering, face decoration variation
Deng), and the target identification percent of pass that these variations will lead to declines the problems such as slack-off with recognition speed；In order to maintain target identification
Rate and recognition speed need it is continual carried out perception, purposive acquisition, updated correlated samples and model, this is just needed
A large amount of time and efforts is put into, higher cost is experienced bad.
Summary of the invention
The present invention is intended to provide it is a kind of identify target object method, apparatus, electronic equipment and storage medium, can gram
Take the defect of the prior art.Goal of the invention of the invention is achieved by the following technical programs:
The first aspect of the embodiment of the present application provides a kind of method for identifying target object, comprising:
Obtain the characteristic information of current time node destination object；
The temporal characteristics information model crossed by pre-training identifies the characteristic information, and in characteristic information library
The characteristic information of the target object prestored carries out similarity comparison；
When similarity exceeds preset threshold value, recongnition of objects success, and automatically by the current time node mesh
The characteristic information of mark object is updated in the characteristic information library；
The temporal characteristics information model that the pre-training is crossed optimizes automatically according to the updated characteristic information library
And retraining.
In some embodiments, the characteristic information is the information for referring to change with time change.
In some embodiments, the characteristic information includes: internal characteristics information and/or external feature information；
The internal characteristics information includes face characteristic information, motion characteristic information, at least one in sound characteristic information
Kind；
The external feature information includes aspectual character information, gait feature information, hair style characteristic information, garment ornament letter
At least one of breath, jewellery characteristic information.
In some embodiments, the face characteristic information, the motion characteristic information, the aspectual character information, institute
Gait feature information, the hair style characteristic information, the garment ornament information and the jewellery characteristic information are stated by least one
A local feature information composition.
In some embodiments, the temporal characteristics information model is also used to estimate while to recongnition of objects
Characteristic information of the target object in specific time.
In some embodiments, the method also includes: the identification model crossed by pre-training to the characteristic information into
Row identification, and the characteristic information and recognition result are stored in the characteristic information library.
The second aspect of the embodiment of the present application provides a kind of training method of temporal characteristics information model, comprising:
The characteristic information of target object, the type based on time series and the characteristic information are extracted from characteristic information library
Classify to the characteristic information；
Sorted characteristic information is trained based on the time series, at least generates a temporal characteristics information mould
Type.
The third aspect of the embodiment of the present application provides a kind of device for identifying target object, comprising:
Module is obtained, for obtaining the characteristic information of current time node destination object；
Identify comparison module, the spy that the temporal characteristics information model for crossing by pre-training obtains the acquisition module
Reference breath is identified, and is carried out similarity with the characteristic information of the target object prestored in characteristic information library and compared；
Update module is used for when similarity exceeds preset threshold value, automatically by the current time node destination object
Characteristic information be updated in the characteristic information library；
Optimization module, the temporal characteristics information model crossed for the pre-training is according to the updated characteristic information library
Automatically it optimizes and retraining.
The fourth aspect of the embodiment of the present application provides a kind of electronic equipment, comprising:
Memory and one or more processors；
Wherein, the memory is connect with one or more of processor communications, and being stored in the memory can quilt
The instruction that one or more of processors execute, when described instruction is executed by one or more of processors, the electronics
Equipment is for realizing the method as described in foregoing embodiments.
5th aspect of the embodiment of the present application provides a kind of computer readable storage medium, and being stored thereon with computer can
It executes instruction, when the computer executable instructions are executed by a computing apparatus, can be used to realize as described in foregoing embodiments
Method.
Advantageous effects of the invention: the invention discloses a kind of method for identifying target object, it can be in target
The continuous identification feature information of temporal characteristics information model crossed in the case where object unaware based on pre-training and more new feature letter
Library is ceased, while can be improved automatically with retraining temporal characteristics information model, accuracy of identification is continuously improved, and match to user
Right to require lower, usage experience is more preferably.
Detailed description of the invention
Illustrate the embodiment of the present invention or technical solution in the prior art in order to clearer, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of method flow schematic diagram for identifying target object according to shown in some embodiments of the present application；
Fig. 2 is a kind of apparatus module structural block diagram for identifying target object according to shown in some embodiments of the present application；
Fig. 3 is the structural schematic diagram of a kind of electronic equipment according to shown in some embodiments of the present application.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, disclosing a kind of method for identifying target object in one embodiment of the application, specifically include:
Step 101, the characteristic information for obtaining current time node destination object；
Step 102, the temporal characteristics information model crossed by pre-training identify the characteristic information, and and feature
The characteristic information of the target object prestored in information bank carries out similarity comparison；
Step 103, when similarity exceed preset threshold value when, recongnition of objects success, and automatically will be described current when
The characteristic information of intermediate node target object is updated in the characteristic information library；
The temporal characteristics information model that step 104, the pre-training are crossed is automatic according to the updated characteristic information library
It optimizes and retraining.
In some embodiments, the characteristic information is the information for referring to change with time change.
In some embodiments, the characteristic information includes: internal characteristics information and/or external feature information；
The internal characteristics information includes face characteristic information, motion characteristic information, at least one in sound characteristic information
Kind；
The external feature information includes aspectual character information, gait feature information, hair style characteristic information, garment ornament letter
At least one of breath, jewellery characteristic information.
In some embodiments, the face characteristic information, the motion characteristic information, the aspectual character information, institute
Gait feature information, the hair style characteristic information, the garment ornament information and the jewellery characteristic information are stated by least one
A local feature information composition.
In some embodiments, the temporal characteristics information model is also used to while recongnition of objects, estimates institute
Target object is stated in the characteristic information of specific time.
In some embodiments, the method also includes: the identification model crossed by pre-training to the characteristic information into
Row identification, and the characteristic information and recognition result are stored in the characteristic information library.
For example, for using Shopping Guide as target object sample, the characteristic information of multiple Shopping Guides is extracted, wherein special
Reference breath includes face characteristic, characteristics of human body, gait feature etc.；The identification model crossed by pre-training believes the feature of Shopping Guide
Breath identified, and will the characteristic information and recognition result deposit characteristic information library in；
The characteristic information of Shopping Guide, the type pair based on time series and the characteristic information are extracted from characteristic information library
The characteristic information is classified；
Sorted characteristic information is trained based on the time series, at least generates a temporal characteristics information mould
Type.
Occur again when the temporal characteristics information model that pre-training is crossed identifies once as the Shopping Guide A of target object sample
When, the face characteristic current to Shopping Guide A, characteristics of human body, gait feature carry out feature extraction, and in characteristic information library before
Face characteristic, characteristics of human body, the gait feature of storage are compared；When similarity be more than given threshold, decide that target pair
It is supplemented in characteristic information library as identifying successfully, and by the characteristic information of current time.
Under normal circumstances, the feature of target object can change with the variation of time, such as face characteristic
Variation, the variation of posture, Various Seasonal dress ornament and variation, daily hair style and the variation of length of decoration etc..Wherein face and body
The features such as state with the years passage, it may occur that more subtle variation, and the variation of the features such as dress ornament, decoration and hair style is general
It can be closely related with the change in season.The temporal characteristics information model crossed using pre-training, estimates target object in current time
Or the characteristic information of a certain specific time, the accuracy of identification of target object can be promoted in this way, while can also verify and estimate
Feature.Such as in the scene of shopping guide's reception, shopping guide, there are the variation of work clothes and decoration, passes through persistent collection when season
The characteristic information data of shopping guide carries out face, human body to shopping guide, and the difference local feature such as dress ornament distinguishes settling time characteristic information
Model.When season, the characteristic information of Shopping Guide B is estimated by temporal characteristics information model, can promote Shopping Guide B's
Accuracy of identification.
One embodiment of the application also discloses a kind of training method of temporal characteristics information model, comprising:
The characteristic information of target object, the type based on time series and the characteristic information are extracted from characteristic information library
Classify to the characteristic information；
Sorted characteristic information is trained based on the time series, at least generates a temporal characteristics information mould
Type.
As shown in Fig. 2, one embodiment of the application also discloses a kind of device 200 for identifying target object, comprising:
Module 201 is obtained, for obtaining the characteristic information of current time node destination object；
Identify comparison module 202, the temporal characteristics information model for crossing by pre-training obtains the acquisition module 201
The characteristic information taken is identified, and is carried out similarity with the characteristic information of the target object prestored in characteristic information library and compared；
Update module 203 is used for when 202 alignment similarity of identification comparison module exceeds preset threshold value, automatically
The characteristic information of the current time node destination object is updated in the characteristic information library；
Optimization module 204, the temporal characteristics information model crossed for the pre-training are believed according to the updated feature
Breath library optimizes automatically and retraining.
As shown in figure 3, the application one embodiment provides electronic equipment, which includes:
Memory 330 and one or more processors 310；
Wherein, the memory 330 is communicated to connect with one or more of processors 310, is deposited in the memory 330
The instruction 332 that can be executed by one or more of processors is contained, described instruction 332 is by one or more of processors
310 execute, so that one or more of processors 310 execute the method in the application previous embodiment.
Specifically, processor 310 can be connected with memory 330 by bus or other modes, by total in Fig. 3
For line 340 connects.Processor 310 can be central processing unit (Central Processing Unit, CPU).Processor
310 can also be other general processors, digital signal processor (Digital Signal Processor, DSP), dedicated collection
At circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 330 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
The progressive network of cascade in transient computer executable program and module, such as the embodiment of the present application.Processor 310 passes through fortune
Non-transient software program, instruction and the module 332 that row is stored in memory 330, thereby executing the various functions of processor
Using and data processing.
Memory 330 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the data etc. that are created of storage processor 310.In addition,
Memory 330 may include high-speed random access memory, can also include non-transient memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-transient solid-state memories.In some embodiments, it includes opposite that memory 330 is optional
In the remotely located memory of processor 310, these remote memories can be by network (for example passing through communication interface 320) even
It is connected to processor 310.The example of above-mentioned network include but is not limited to internet, intranet, local area network, mobile radio communication and
A combination thereof.
One embodiment of the application also provides a kind of computer readable storage medium, the computer readable storage medium
In be stored with computer executable instructions, the computer executable instructions execute in the application previous embodiment after being performed
Method.
Computer-readable storage medium above-mentioned includes to store such as computer readable instructions, data structure, program mould
Any mode or technology of the information such as block or other data are come the physics volatile and non-volatile, removable and not removable realized
Dynamic medium.Computer-readable storage medium specifically includes, but is not limited to, USB flash disk, mobile hard disk, read-only memory (ROM,
Read-OnlyMemory), random access memory (RAM, Random Access Memory), erasable programmable is read-only deposits
Reservoir (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other solid-state memory technologies, CD-ROM, number
Word versatile disc (DVD), HD-DVD, blue light (Blue-Ray) or other light storage devices, tape, disk storage or other magnetism
Storage equipment or any other medium that can be used to store information needed and can be accessed by computer.
Although subject matter described herein is held in the execution on the computer systems of binding operation system and application program
It is provided in capable general context, but it will be appreciated by the appropriately skilled person that may also be combined with other kinds of program module
To execute other realizations.In general, program module include routines performing specific tasks or implementing specific abstract data types,
Program, component, data structure and other kinds of structure.It will be understood by those skilled in the art that subject matter described herein can
It is practiced, including handheld device, multicomputer system, based on microprocessor or can compiled with using other computer system configurations
Journey consumption electronic product, minicomputer, mainframe computer etc., it is possible to use in wherein task by being connected by communication network
In the distributed computing environment that remote processing devices execute.In a distributed computing environment, program module can be located locally and far
In the two of journey memory storage device.
Those of ordinary skill in the art may be aware that being described in conjunction with institute's embodiments herein herein each exemplary
Unit and method and step can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are studied carefully
Unexpectedly it is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technique people
Member can use different methods to achieve the described function each specific application, but this realization is it is not considered that super
Scope of the present application out.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part or the technical solutions that contribute to original technology can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
In conclusion by embodiment disclosed herein, it can be in the case where target object unaware, based on pre-
The continuous identification feature information of the temporal characteristics information model trained simultaneously updates characteristic information library, while can improve automatically and again
Accuracy of identification is continuously improved in training time feature information model, and lower to the requirement of the fitness of user, and usage experience is more
It is good.
More than, it is merely preferred embodiments of the present invention, but scope of protection of the present invention is not limited thereto, it is any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. a kind of method for identifying target object characterized by comprising
Obtain the characteristic information of current time node destination object；
The temporal characteristics information model crossed by pre-training identifies the characteristic information, and with prestored in characteristic information library
Target object characteristic information carry out similarity comparison；
When similarity exceeds preset threshold value, recongnition of objects success, and automatically by the current time node destination pair
The characteristic information of elephant is updated in the characteristic information library；
The temporal characteristics information model that the pre-training is crossed optimizes and again automatically according to the updated characteristic information library
Training.
2. the method according to claim 1, wherein the characteristic information is to refer to become with time change
The information of change.
3. the method according to claim 1, wherein the characteristic information includes: internal characteristics information and/or outer
In characteristic information；
The internal characteristics information includes at least one of face characteristic information, motion characteristic information, sound characteristic information；
The external feature information include aspectual character information, gait feature information, hair style characteristic information, garment ornament information,
At least one of jewellery characteristic information.
4. the method according to claim 1, wherein the face characteristic information, the motion characteristic information, institute
It is special to state aspectual character information, the gait feature information, the hair style characteristic information, the garment ornament information and the jewellery
Reference breath is made of at least one local feature information.
5. the method according to claim 1, wherein the temporal characteristics information model is also used to target pair
While as identification, the target object is estimated in the characteristic information of specific time.
6. the method according to claim 1, wherein the method also includes: obtain target object sample spy
Reference breath, the identification model crossed by pre-training identifies the characteristic information of the target object sample, and by the spy
Reference breath and recognition result are stored in the characteristic information library.
7. a kind of training method of temporal characteristics information model characterized by comprising
The characteristic information of target object is extracted from characteristic information library, the type based on time series and the characteristic information is to institute
Characteristic information is stated to classify；
Sorted characteristic information is trained based on the time series, at least generates a temporal characteristics information model.
8. a kind of device for identifying target object characterized by comprising
Module is obtained, for obtaining the characteristic information of current time node destination object；
Identify comparison module, the feature that the temporal characteristics information model for crossing by pre-training obtains the acquisition module is believed
Breath is identified, and is carried out similarity with the characteristic information of the target object prestored in characteristic information library and compared；
Update module is used for when similarity exceeds preset threshold value, automatically by the spy of the current time node destination object
Reference breath is updated in the characteristic information library；
Optimization module, the temporal characteristics information model crossed for the pre-training are automatic according to the updated characteristic information library
It optimizes and retraining.
9. a kind of electronic equipment characterized by comprising
Memory and one or more processors；
Wherein, the memory is connect with one or more of processor communications, and being stored in the memory can be described
The instruction that one or more processors execute, when described instruction is executed by one or more of processors, the electronic equipment
For realizing the method according to claim 1 to 7.
10. a kind of computer readable storage medium, is stored thereon with computer executable instructions, refer to when the computer is executable
When order is executed by a computing apparatus, it can be used to realize the method according to claim 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910647518.7A CN110390290A (en) | 2019-07-17 | 2019-07-17 | A kind of method, apparatus, electronic equipment and storage medium identifying target object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910647518.7A CN110390290A (en) | 2019-07-17 | 2019-07-17 | A kind of method, apparatus, electronic equipment and storage medium identifying target object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110390290A true CN110390290A (en) | 2019-10-29 |
Family
ID=68286737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910647518.7A Pending CN110390290A (en) | 2019-07-17 | 2019-07-17 | A kind of method, apparatus, electronic equipment and storage medium identifying target object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110390290A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852305A (en) * | 2019-11-18 | 2020-02-28 | 哈尔滨工程大学 | Human gait feature extraction method |
| CN113781050A (en) * | 2021-09-03 | 2021-12-10 | 中国银行股份有限公司 | Biological password verification method and device, electronic equipment and storage medium |
| CN114187680A (en) * | 2020-08-25 | 2022-03-15 | 浙江宇视科技有限公司 | Unlocking information identification method, device, medium and equipment of intelligent lock |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537336A (en) * | 2014-12-17 | 2015-04-22 | 厦门立林科技有限公司 | Face identification method and system with self-learning function |
| CN105303998A (en) * | 2014-07-24 | 2016-02-03 | 北京三星通信技术研究有限公司 | Method, device and equipment for playing advertisements based on inter-audience relevance information |
| CN106250857A (en) * | 2016-08-04 | 2016-12-21 | 深圳先进技术研究院 | A kind of identity recognition device and method |
| CN106934364A (en) * | 2017-03-09 | 2017-07-07 | 腾讯科技（上海）有限公司 | The recognition methods of face picture and device |
| CN107480575A (en) * | 2016-06-07 | 2017-12-15 | 深圳市商汤科技有限公司 | The training method of model, across age face identification method and corresponding device |
| CN108846350A (en) * | 2018-06-08 | 2018-11-20 | 江苏大学 | Tolerate the face identification method of change of age |
| CN109034078A (en) * | 2018-08-01 | 2018-12-18 | 腾讯科技（深圳）有限公司 | Training method, age recognition methods and the relevant device of age identification model |
| CN109977887A (en) * | 2019-01-30 | 2019-07-05 | 四川电科维云信息技术有限公司 | A kind of face identification method of anti-age interference |
-
2019
- 2019-07-17 CN CN201910647518.7A patent/CN110390290A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303998A (en) * | 2014-07-24 | 2016-02-03 | 北京三星通信技术研究有限公司 | Method, device and equipment for playing advertisements based on inter-audience relevance information |
| CN104537336A (en) * | 2014-12-17 | 2015-04-22 | 厦门立林科技有限公司 | Face identification method and system with self-learning function |
| CN107480575A (en) * | 2016-06-07 | 2017-12-15 | 深圳市商汤科技有限公司 | The training method of model, across age face identification method and corresponding device |
| CN106250857A (en) * | 2016-08-04 | 2016-12-21 | 深圳先进技术研究院 | A kind of identity recognition device and method |
| CN106934364A (en) * | 2017-03-09 | 2017-07-07 | 腾讯科技（上海）有限公司 | The recognition methods of face picture and device |
| CN108846350A (en) * | 2018-06-08 | 2018-11-20 | 江苏大学 | Tolerate the face identification method of change of age |
| CN109034078A (en) * | 2018-08-01 | 2018-12-18 | 腾讯科技（深圳）有限公司 | Training method, age recognition methods and the relevant device of age identification model |
| CN109977887A (en) * | 2019-01-30 | 2019-07-05 | 四川电科维云信息技术有限公司 | A kind of face identification method of anti-age interference |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852305A (en) * | 2019-11-18 | 2020-02-28 | 哈尔滨工程大学 | Human gait feature extraction method |
| CN114187680A (en) * | 2020-08-25 | 2022-03-15 | 浙江宇视科技有限公司 | Unlocking information identification method, device, medium and equipment of intelligent lock |
| CN113781050A (en) * | 2021-09-03 | 2021-12-10 | 中国银行股份有限公司 | Biological password verification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390290A (en) | A kind of method, apparatus, electronic equipment and storage medium identifying target object | |
| Bhattacharya et al. | Recognition of complex events: Exploiting temporal dynamics between underlying concepts | |
| CN109064175A (en) | A kind of account takeover risk prevention system method and device | |
| CN109643448A (en) | Fine granularity object identification in robot system | |
| CN105095415B (en) | The determination method and apparatus of network mood | |
| CN110335115A (en) | A kind of service order processing method and processing device | |
| CN111784348A (en) | Account risk identification method and device | |
| CN106528613B (en) | Intelligent answer method and device | |
| CN104951807B (en) | The determination method and apparatus of stock market's mood | |
| CN111081257A (en) | Voice acquisition method, device, equipment and storage medium | |
| CN109472021A (en) | Critical sentence screening technique and device in medical literature based on deep learning | |
| CN111401507A (en) | Adaptive decision tree fall detection method and system | |
| CN111860101A (en) | Training method and device for face key point detection model | |
| KR102185979B1 (en) | Method and apparatus for determining type of movement of object in video | |
| CN112287228A (en) | Online learning recommendation method, online learning system and server | |
| CN103324949A (en) | Method and device for recognizing object in image | |
| CN113742580A (en) | Target type data recall method and device, electronic equipment and storage medium | |
| CN109285009A (en) | It brushes single recognition methods and brushes single identification device | |
| CN113205045A (en) | Pedestrian re-identification method and device, electronic equipment and readable storage medium | |
| CN103577543B (en) | The ranking fraud detection method and ranking fraud detection system of application program | |
| CN110019832A (en) | The acquisition methods and device of language model | |
| CN110427971A (en) | Recognition methods, device, server and the storage medium of user and IP | |
| CN111680514A (en) | Information processing and model training method, device, equipment and storage medium | |
| CN107003930B (en) | User information recording method and device and electronic equipment | |
| CN114627310A (en) | Clothing changing pedestrian weight recognition method, device, 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191210 Address after: 100080 Weigongcun Street, Haidian District, Beijing, 7-6-423, 4th floor, No. 7 Webhouse Home Building, No. 1 Weigongcun Street Applicant after: Beijing Tian Zheng Polymerization Technology Co., Ltd. Applicant after: Guangdong Tianzheng Computer Service Co., Ltd Address before: 100080 Weigongcun Street, Haidian District, Beijing, 7-6-423, 4th floor, No. 7 Webhouse Home Building, No. 1 Weigongcun Street Applicant before: Beijing Tian Zheng Polymerization Technology Co., Ltd. |