CN110363180A - A kind of method and apparatus and equipment that statistics stranger's face repeats - Google Patents
A kind of method and apparatus and equipment that statistics stranger's face repeats Download PDFInfo
- Publication number
- CN110363180A CN110363180A CN201910670902.9A CN201910670902A CN110363180A CN 110363180 A CN110363180 A CN 110363180A CN 201910670902 A CN201910670902 A CN 201910670902A CN 110363180 A CN110363180 A CN 110363180A
- Authority
- CN
- China
- Prior art keywords
- stranger
- face
- facial image
- acquisition
- situation
- 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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—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
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method and apparatus and equipment that statistics stranger's face repeats.Wherein, the described method includes: whether the stranger's facial image for detecting the acquisition meets the requirements, when the stranger's facial image for detecting the acquisition is undesirable, then stranger's facial image is considered as in vain, when the stranger's facial image for detecting the acquisition is to meet the requirements, then stranger's facial image is considered as effectively, it is considered as the feature of effective facial image with this is extracted, similarity value is obtained with the face characteristic library of the feature of stranger's facial image of the extraction and the foundation is carried out similarity comparison, with judge whether the similarity value is greater than preset threshold value, when judging that the similarity value is greater than preset threshold value, then judge that stranger's face is to repeat, what is judged to this is that the stranger's face repeated counts.By the above-mentioned means, can be realized the case where repeating to stranger's face carries out identification and statistics.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to a kind of method for repeating of statistics stranger's face and
Device and equipment.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.The technology
Including acquiring image or video flowing containing face, and automatic detection and tracking face in the picture with video camera or camera,
And then the feature information extraction of face, the identity etc. of the matching identification people based on facial feature information are carried out to the face detected
A series of the relevant technologies, usually also referred to as Identification of Images, face recognition.
Existing face statistical project usually disposes face snap equipment in front end to realize the detection of face and grab
It claps, recognition of face and statistics is carried out by the comparison in algorithm and customized list library.As public security department uses blacklist library
Identify concern personnel, service department identifies VIP (Very Important Person, honored guest) with white list library
Personnel etc., the premise of the application are all prior comparison and the systems for importing good known face i.e. black and white lists library and being just able to achieve face
Meter analysis.
In recent years, with the needs of the development of artificial intelligence and national economic development, safety guard, China's recognition of face
Market constantly expands, and has a kind of demand to be solved, i.e., to unknown face, that is, stranger's face comparison and analysis.Such as in public security
Bright as snow community on, the analysis repeated by stranger's face may recognize that and move in but unregistered strange in community
Everybody face;In bright as snow campus, a suspect often to hover on campus doorway and periphery can recognize;In shop, analyzed by this
It may recognize that the potential customers often bought;It may recognize that the doubtful " Huang often occurred in scenes such as traffic website, hospital's windows
Ox " personnel.The above scene is how to carry out weight to stranger's face of candid photograph under the premise of not known face list library
It appears again existing judgement, identifies that the stranger's face often entered and left comes out, carry out subsequent relevant application.
But at least there are the following problems in the prior art for inventor's discovery:
Existing face statistical project usually disposes face snap equipment in front end to realize the detection of face and grab
It claps, recognition of face and statistics is carried out by the comparison in algorithm and customized list library, such as public security department uses blacklist
Concern personnel are identified in library, and service department identifies honored guest personnel etc., existing face statistical project with white list library
Premise be all the prior identification and statistics for importing good known face i.e. black and white lists library and being just able to achieve face, cannot achieve pair
The case where stranger's face repeats carries out identification and statistics.
Summary of the invention
In view of this, it is an object of the invention to propose a kind of method and apparatus that repeat of statistics stranger's face with
And equipment, can be realized the case where repeating to stranger's face carries out identification and statistics.
According to an aspect of the present invention, a kind of method that statistics stranger's face repeats is provided, comprising:
Establish stranger's face characteristic library;
Obtain stranger's facial image;
Whether the stranger's facial image for detecting the acquisition meets the requirements, in the stranger's face for detecting the acquisition
When image is undesirable, then stranger's facial image of the acquisition is considered as in vain, on the footpath between fields for detecting the acquisition
Stranger's facial image is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements;
It is considered as the feature of effective stranger's facial image described in extraction;
The feature of stranger's facial image of the extraction is similar to the progress of stranger's face characteristic library of the foundation
Degree comparison obtains similarity value;
Whether the similarity value for judging that the comparison obtains is greater than preset threshold value, is judging the phase for comparing and obtaining
When being greater than preset threshold value like angle value, then judge that stranger's face is to repeat;
Judge is that the stranger's face repeated is counted to described.
Wherein, whether stranger's facial image of the detection acquisition meets the requirements, and is detecting the acquisition
When stranger's facial image is undesirable, then stranger's facial image of the acquisition is considered as in vain, detecting
The stranger's facial image for stating acquisition is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements, comprising:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side
Whether face situation or hindbrain situation or smudgy situation, the stranger's facial image for detecting the acquisition meet the requirements, are examining
The stranger's facial image for measuring the acquisition is the presence of bow situation or side face situation or hindbrain situation or smudgy situation
When, when detecting that stranger's facial image of the acquisition is undesirable, then by stranger's facial image of the acquisition
It is invalid to be considered as, and is that there is no bow situation or side face situations or hindbrain situation in the stranger's facial image for detecting the acquisition
Or when smudgy situation, detect that stranger's facial image of the acquisition is when meeting the requirements, then by the footpath between fields of the acquisition
Stranger's facial image is considered as effectively.
Wherein, it is described judge it is described compare whether obtained similarity value is greater than preset threshold value, judge it is described right
When similarity value than obtaining is greater than preset threshold value, then judge that stranger's face is to repeat, further includes:
Whether the similarity value for judging that the comparison obtains is greater than preset threshold value, is judging the phase for comparing and obtaining
When being no more than preset threshold value like angle value, then judge that stranger's face is to first appear, and described first appear
Face establishes archives in stranger's face characteristic library.
Wherein, described, judge is after the stranger's face repeated counts to described, further includes:
Stranger's face characteristic library of the foundation is periodically optimized, from stranger's face characteristic library of the foundation
It is middle to delete the stranger's face information for not repeating appearance within a preset time.
According to another aspect of the present invention, a kind of device that statistics stranger's face repeats is provided, comprising:
It establishes module, obtain module, detection module, extraction module, contrast module, judgment module and statistical module;
It is described to establish module, for establishing stranger's face characteristic library;
The acquisition module, for obtaining stranger's facial image;
The detection module, whether stranger's facial image for detecting the acquisition meets the requirements, detecting
When to state stranger's facial image of acquisition be undesirable, then by stranger's facial image of the acquisition be considered as in vain,
The stranger's facial image for detecting the acquisition is when meeting the requirements, then being considered as stranger's facial image of the acquisition has
Effect;
The extraction module, for extracting the feature for being considered as effective stranger's facial image;
The contrast module, for by the feature of stranger's facial image of the extraction and the foundation it is strange everybody
Face feature database carries out similarity comparison and obtains similarity value;
Whether the judgment module, the similarity value for judging that the comparison obtains are greater than preset threshold value, are judging
When the similarity value that the comparison obtains out is greater than preset threshold value, then judge that stranger's face is to repeat;
The statistical module, for judge to be that the stranger's face repeated is counted to described.
Wherein, the detection module, is specifically used for:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side
Whether face situation or hindbrain situation or smudgy situation, the stranger's facial image for detecting the acquisition meet the requirements, are examining
The stranger's facial image for measuring the acquisition is the presence of bow situation or side face situation or hindbrain situation or smudgy situation
When, when detecting that stranger's facial image of the acquisition is undesirable, then by stranger's facial image of the acquisition
It is invalid to be considered as, and is that there is no bow situation or side face situations or hindbrain situation in the stranger's facial image for detecting the acquisition
Or when smudgy situation, detect that stranger's facial image of the acquisition is when meeting the requirements, then by the footpath between fields of the acquisition
Stranger's facial image is considered as effectively.
Wherein, the judgment module, comprising:
First judgment module and the second judgment module;
Whether second judgment module, the similarity value for judging that the comparison obtains are greater than preset threshold value,
When the similarity value for judging that the comparison obtains is greater than preset threshold value, then judge that stranger's face is to repeat
It is existing;
Whether second judgment module, the similarity value for judging that the comparison obtains are greater than preset threshold value,
When the similarity value for judging that the comparison obtains is no more than preset threshold value, then judge that stranger's face is to go out for the first time
It is existing, and archives are established in stranger's face characteristic library for the face first appeared.
Wherein, the device that statistics stranger's face repeats, further includes:
Optimization module;
The optimization module, for periodically being optimized to stranger's face characteristic library of the foundation, from the foundation
Stranger's face characteristic library in delete the stranger's face information for not repeating appearance within a preset time.
According to a further aspect of the invention, a kind of equipment that statistics stranger's face repeats is provided, comprising:
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
A processor executes, so that at least one described processor is able to carry out statistics stranger's face described in any of the above embodiments and repeats
The method of appearance.
According to a further aspect of the invention, a kind of computer readable storage medium is provided, computer program is stored with, institute
State the method for realizing that statistics stranger's face described in any of the above embodiments repeats when computer program is executed by processor.
It can be found that above scheme, can establish stranger's face characteristic library and available stranger's facial image,
Whether meet the requirements with the stranger's facial image that can detecte the acquisition, is in the stranger's facial image for detecting the acquisition
When undesirable, then stranger's facial image of the acquisition is considered as in vain, in the stranger's face figure for detecting the acquisition
Seem then stranger's facial image of the acquisition is considered as effectively when meeting the requirements, and can extract this be considered as it is effective strange
The feature of everybody face image, and can be by stranger's face characteristic of the feature of stranger's facial image of the extraction and the foundation
Library carries out similarity comparison and obtains similarity value, and may determine that whether the similarity value that the comparison obtains is greater than preset threshold
Value then judges that stranger's face is to repeat when the similarity value for judging that the comparison obtains is greater than preset threshold value
It is existing, and what can be judged to this is that the stranger's face repeated counts, and be can be realized to stranger's face weight
The situation for appearing again existing carries out identification and statistics.
Further, above scheme can use facial features localization mode, detect stranger's facial image of the acquisition
With the presence or absence of situation or the side face situation or hindbrain situation or smudgy situation etc. of bowing, stranger's face figure of the acquisition is detected
Seem it is no meet the requirements, be to exist to bow situation or side face situation or hindbrain feelings in the stranger's facial image for detecting the acquisition
Whens condition or smudgy situation etc., when detecting that stranger's facial image of the acquisition is undesirable, then by the acquisition
Stranger's facial image is considered as in vain, is that there is no bow situation or side face feelings in the stranger's facial image for detecting the acquisition
Whens condition or hindbrain situation or smudgy situation etc., detect that stranger's facial image of the acquisition then will when meeting the requirements
Stranger's facial image of the acquisition is considered as effectively, and such benefit is that by by by stranger's face figure of the acquisition
The efficiency of the case where repeating to stranger's face progress identification and statistics is improved as being considered as invalid or effective mode.
Further, above scheme, it can be determined that whether the similarity value that the comparison obtains is greater than preset threshold value, is sentencing
It is disconnected go out the comparison obtained similarity value when being no more than preset threshold value, then judge stranger's face be first appear, and
Archives are established in stranger's face characteristic library for the face first appeared, and such benefit is that by going out for the first time
Existing face establishes archives in stranger's face characteristic library, convenient for identifying the case where repeating to stranger's face
And statistics.
Further, above scheme can periodically optimize stranger's face characteristic library of the foundation, from the foundation
Stranger's face characteristic library in delete the stranger's face information for not repeating appearance within a preset time, such benefit is
It can ensure that stranger's face characteristic library of the foundation has reasonable memory space to be the face that first appears always and builds at this
Archives are established in vertical stranger's face characteristic library, convenient for being managed to stranger's face.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, 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 the flow diagram for one embodiment of method that present invention statistics stranger's face repeats;
Fig. 2 is the flow diagram for another embodiment of method that present invention statistics stranger's face repeats;
Fig. 3 is the structural schematic diagram for one embodiment of device that present invention statistics stranger's face repeats;
Fig. 4 is the structural schematic diagram for another embodiment of device that present invention statistics stranger's face repeats;
Fig. 5 is the structural schematic diagram for one embodiment of equipment that present invention statistics stranger's face repeats.
Specific embodiment
With reference to the accompanying drawings and examples, the present invention is described in further detail.It is emphasized that following implement
Example is merely to illustrate the present invention, but is not defined to the scope of the present invention.Likewise, following embodiment is only portion of the invention
Point embodiment and not all embodiments, institute obtained by those of ordinary skill in the art without making creative efforts
There are other embodiments, shall fall within the protection scope of the present invention.
The present invention provides a kind of method that statistics stranger's face repeats, and can be realized and repeats to stranger's face
Existing situation carries out identification and statistics.
Referring to Figure 1, Fig. 1 is the process signal for one embodiment of method that present invention statistics stranger's face repeats
Figure.It is noted that if having substantially the same as a result, method of the invention is not limited with process sequence shown in FIG. 1.Such as
Shown in Fig. 1, this method comprises the following steps:
S101: stranger's face characteristic library is established.
In the present embodiment, each stranger's face in stranger's face characteristic library of the foundation can be arranged uniquely
ID (Identity Document, unique encodings) distinguish, the present invention is not limited.
S102: stranger's facial image is obtained.
In the present embodiment, the mode of acquisition stranger's facial image can be obtains in such a way that camera images
It takes, is also possible to obtain by way of mobile phone photograph, can also be in the video shot by monitor and extract stranger
The mode of facial image obtains, and the present invention is not limited.
S103: whether the stranger's facial image for detecting the acquisition meets the requirements, detect the acquisition it is strange everybody
When face image is undesirable, then stranger's facial image of the acquisition is considered as in vain, is detecting the strange of the acquisition
Everybody face image is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements.
Wherein, whether stranger's facial image of the detection acquisition meets the requirements, in the stranger for detecting the acquisition
When facial image is undesirable, then stranger's facial image of the acquisition is considered as in vain, on the footpath between fields for detecting the acquisition
Stranger's facial image is then to be considered as effectively stranger's facial image of the acquisition when meeting the requirements, may include:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side face
Whether situation or hindbrain situation or smudgy situation etc., the stranger's facial image for detecting the acquisition meet the requirements, are detecting
Out stranger's facial image of the acquisition be exist bow situation or side face situation or hindbrain situation or smudgy situation etc. whens,
When detecting that stranger's facial image of the acquisition is undesirable, then stranger's facial image of the acquisition is considered as nothing
Effect, the stranger's facial image for detecting the acquisition be there is no bow situation or side face situation or hindbrain situation or it is fuzzy not
Whens clear situation etc., detect that stranger's facial image of the acquisition is when meeting the requirements, then by stranger's face figure of the acquisition
As being considered as effectively, such benefit is that by by the way that stranger's facial image of the acquisition is considered as invalid or effective side
Formula come improve the case where stranger's face is repeated carry out identification and statistics efficiency.
S104: the feature for being considered as effective stranger's facial image is extracted.
In the present embodiment, recognition of face mode can be used, the spy for being considered as effective stranger's facial image is extracted
Sign can also use feature identification method, extract the feature for being considered as effective stranger's facial image, the present invention is not limited
It is fixed.
S105: the feature of stranger's facial image of the extraction is similar to the progress of stranger's face characteristic library of the foundation
Degree comparison obtains similarity value.
In the present embodiment, which can be a kind of measurement of close degree between two things of Comprehensive Assessment.
Two things are closer, their similarity measurement is also bigger, and two things are more become estranged, their similarity measurement is also
It is smaller.
S106: judging whether the similarity value that the comparison obtains is greater than preset threshold value, is judging what the comparison obtained
When similarity value is greater than preset threshold value, then judge that stranger's face is to repeat.
Wherein, this judges whether the similarity value that the comparison obtains is greater than preset threshold value, is judging that the comparison obtains
Similarity value when being greater than preset threshold value, then judge that stranger's face is to repeat, can also include:
Judge whether the similarity value that the comparison obtains is greater than preset threshold value, in the similarity for judging that the comparison obtains
When value is no more than preset threshold value, then judge stranger's face be first appear, and for the face first appeared at this
Archives are established in stranger's face characteristic library, such benefit is that by the face first appeared in stranger's face
Archives are established in feature database, convenient for repeating to stranger's face the case where carries out identification and statistics.
In the present embodiment, can be judged according to this be the corresponding unique encodings of stranger's face that repeat come
Record and update recording for the stranger's face repeated.
S107: what is judged to this is that the stranger's face repeated counts.
In the present embodiment, can using count this judge be the stranger's face repeated appearance number of days
Mode, what is judged to this is that the stranger's face repeated counts, and can also be weight using count that this judges
The mode of the frequency of occurrence for the stranger's face for appearing again existing, what is judged to this is that the stranger's face repeated is united
Meter, can also using statistics this judge be the stranger's face repeated time of occurrence by the way of, this is judged
Be that the stranger's face repeated counts, the present invention is not limited.
Wherein, what is judged at this to this is that after the stranger's face repeated counts, can also include:
Stranger's face characteristic library of the foundation is periodically optimized, is deleted from stranger's face characteristic library of the foundation
Except the stranger's face information for not repeating appearance within a preset time, such benefit is can to ensure the stranger of the foundation
It is the face that first appears in stranger's face characteristic library of the foundation that there is reasonable memory space in face characteristic library always
Archives are established, convenient for being managed to stranger's face.
It can be found that in the present embodiment, can establish stranger's face characteristic library and available stranger's face figure
Picture, and can detecte stranger's facial image of the acquisition and whether meet the requirements, in the stranger's face figure for detecting the acquisition
When seeming undesirable, then by stranger's facial image of the acquisition be considered as in vain, detect the acquisition it is strange everybody
Face image is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements, and can extract this and be considered as effectively
The feature of stranger's facial image, and can be by stranger's face of the feature of stranger's facial image of the extraction and the foundation
Feature database carries out similarity comparison and obtains similarity value, and to may determine that whether similarity value that the comparison obtains is greater than preset
Threshold value then judges that stranger's face is to repeat when the similarity value for judging that the comparison obtains is greater than preset threshold value
Occur, and what can be judged to this is that the stranger's face repeated counts, and be can be realized to stranger's face
The case where repeating carries out identification and statistics.
Further, in the present embodiment, facial features localization mode can be used, stranger's face of the acquisition is detected
Image with the presence or absence of bowing situation or side face situation or hindbrain situation or smudgy situation etc., detect the acquisition it is strange everybody
Whether face image meets the requirements, the stranger's facial image for detecting the acquisition be exist bow situation or side face situation or after
Whens brain situation or smudgy situation etc., when detecting that stranger's facial image of the acquisition is undesirable, then this is obtained
The stranger's facial image taken is considered as in vain, is that there is no bow situation or sides in the stranger's facial image for detecting the acquisition
Whens face situation or hindbrain situation or smudgy situation etc., detect that stranger's facial image of the acquisition is when meeting the requirements,
Then stranger's facial image of the acquisition is considered as effectively, such benefit be that by by by the acquisition it is strange everybody
Face image is considered as invalid or effective mode to improve the effect that the case where repeating to stranger's face carries out identification and statistics
Rate.
Further, in the present embodiment, it can be determined that whether the similarity value that the comparison obtains is greater than preset threshold value,
When the similarity value for judging that the comparison obtains is no more than preset threshold value, then judge that stranger's face is to go out for the first time
Existing, and establish archives in stranger's face characteristic library for the face first appeared, such benefit is that by pair
The face first appeared establishes archives in stranger's face characteristic library, the case where convenient for repeating to stranger's face into
Row identification and statistics.
Fig. 2 is referred to, Fig. 2 is the method and apparatus and another reality of equipment that present invention statistics stranger's face repeats
Apply the flow diagram of example.In the present embodiment, method includes the following steps:
S201: stranger's face characteristic library is established.
Can be as above described in S101, therefore not to repeat here.
S202: stranger's facial image is obtained.
Can be as above described in S102, therefore not to repeat here.
S203: whether the stranger's facial image for detecting the acquisition meets the requirements, detect the acquisition it is strange everybody
When face image is undesirable, then stranger's facial image of the acquisition is considered as in vain, is detecting the strange of the acquisition
Everybody face image is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements.
Can be as above described in S103, therefore not to repeat here.
S204: the feature for being considered as effective stranger's facial image is extracted.
Can be as above described in S104, therefore not to repeat here.
S205: the feature of stranger's facial image of the extraction is similar to the progress of stranger's face characteristic library of the foundation
Degree comparison obtains similarity value.
Can be as above described in S105, therefore not to repeat here.
S206: judging whether the similarity value that the comparison obtains is greater than preset threshold value, is judging what the comparison obtained
When similarity value is greater than preset threshold value, then judge that stranger's face is to repeat.
Can be as above described in S106, therefore not to repeat here.
S207: what is judged to this is that the stranger's face repeated counts.
In the present embodiment, can using count this judge be the stranger's face repeated appearance number of days
Mode, what is judged to this is that the stranger's face repeated counts, and can also be weight using count that this judges
The mode of the frequency of occurrence for the stranger's face for appearing again existing, what is judged to this is that the stranger's face repeated is united
Meter, can also using statistics this judge be the stranger's face repeated time of occurrence by the way of, this is judged
Be that the stranger's face repeated counts, the present invention is not limited.
Can be as above described in S107, therefore not to repeat here.
S208: periodically optimizing stranger's face characteristic library of the foundation, from stranger's face characteristic of the foundation
The stranger's face information for not repeating appearance within a preset time is deleted in library.
In the present embodiment, parameter setting can be carried out, including library maximum value: the maximum of face picture saves number in library
Amount;Day maximal increment: allow newly-increased face maximum quantity daily;Checkout time: start people in specified idle such as morning daily
The cleaning work in face library;Cleaning rule: number of days, number, nearest time of occurrence, descending, ascending order are pressed.
In the present embodiment, can be first in stranger's monitoring record, taking out is more than default month without the footpath between fields for capturing record
Stranger face ID, the strange face database for being issued to engine carry out the batch deletion of face picture;The monitoring note of the face is removed simultaneously
Record.
It in the present embodiment, can not be after if current face library quantity is less than reserved (library maximum value-daily increment)
It is continuous to delete.Such as larger than reserved then counts several X=current value-retentions to be deleted.
In the present embodiment, the strange face snap note before default day being greater than from entry time is taken out in historical record
Record for example face validity period protect, by capture number of days, number for example from small to large, recently time of occurrence for example arrive earliest recently according to
Minor sort.
In the present embodiment, default stranger face ID, is dealt into the strange of engine before being taken out according to number to be deleted
The batch that face database carries out face picture is deleted;The monitoring record of the face is removed simultaneously.
It can be found that in the present embodiment, can periodically be optimized to stranger's face characteristic library of the foundation, from this
The stranger's face information for not repeating appearance within a preset time is deleted in stranger's face characteristic library of foundation, it is such good
Place is that can to ensure that there is reasonable memory space in stranger's face characteristic library of the foundation always be that the face first appeared exists
Archives are established in stranger's face characteristic library of the foundation, convenient for being managed to stranger's face.
The present invention also provides a kind of devices that statistics stranger's face repeats, and can be realized and repeat to stranger's face
The case where appearance, carries out identification and statistics.
Fig. 3 is referred to, Fig. 3 is the structural representation for one embodiment of device that present invention statistics stranger's face repeats
Figure.In the present embodiment, the device 30 that statistics stranger's face repeats includes establishing module 31, obtaining module 32, detection
Module 33, extraction module 34, contrast module 35, judgment module 36 and statistical module 37.
This establishes module 31, for establishing stranger's face characteristic library.
The acquisition module 32, for obtaining stranger's facial image.
Whether the detection module 33, stranger's facial image for detecting the acquisition meet the requirements, and are detecting that this obtains
When the stranger's facial image taken is undesirable, then stranger's facial image of the acquisition is considered as in vain, is being detected
Stranger's facial image of the acquisition is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements.
The extraction module 34, for extracting the feature for being considered as effective stranger's facial image.
The contrast module 35, for the feature of stranger's facial image of the extraction and stranger's face of the foundation is special
Sign library carries out similarity comparison and obtains similarity value.
The judgment module 36 is being judged for judging whether the similarity value that the comparison obtains is greater than preset threshold value
When the similarity value that the comparison obtains is greater than preset threshold value, then judge that stranger's face is to repeat.
The statistical module 37 is that the stranger's face repeated counts for what is judged to this.
Optionally, the detection module 33, can be specifically used for:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side face
Whether situation or hindbrain situation or smudgy situation etc., the stranger's facial image for detecting the acquisition meet the requirements, are detecting
Out stranger's facial image of the acquisition be exist bow situation or side face situation or hindbrain situation or smudgy situation etc. whens,
When detecting that stranger's facial image of the acquisition is undesirable, then stranger's facial image of the acquisition is considered as nothing
Effect, the stranger's facial image for detecting the acquisition be there is no bow situation or side face situation or hindbrain situation or it is fuzzy not
Whens clear situation etc., detect that stranger's facial image of the acquisition is when meeting the requirements, then by stranger's face figure of the acquisition
As being considered as effectively.
Optionally, the judgment module 36 may include:
First judgment module (not indicated in figure) and the second judgment module (not indicated in figure);
Second judgment module is judging for judging whether the similarity value that the comparison obtains is greater than preset threshold value
When the similarity value that the comparison obtains out is greater than preset threshold value, then judge that stranger's face is to repeat;
Second judgment module is judging for judging whether the similarity value that the comparison obtains is greater than preset threshold value
When the similarity value that the comparison obtains out is no more than preset threshold value, then judge that stranger's face is to first appear, and be
The face first appeared establishes archives in stranger's face characteristic library.
Fig. 4 is referred to, Fig. 4 is the structural representation for another embodiment of device that present invention statistics stranger's face repeats
Figure.It is different from an embodiment, the device 40 that statistics stranger's face repeats described in the present embodiment further includes optimization module
41。
The optimization module 41, for periodically being optimized to stranger's face characteristic library of the foundation, from the footpath between fields of the foundation
The stranger's face information for not repeating appearance within a preset time is deleted in stranger's face characteristic library.
Each unit module for the device 30/40 that statistics stranger's face repeats can execute above method reality respectively
It applies and corresponds to step in example, therefore each unit module is not repeated herein, refer to the explanation of the above corresponding step.
The present invention provides a kind of equipment that statistics stranger's face repeats again, as shown in Figure 5, comprising: at least one
Processor 51;And the memory 52 with the communication connection of at least one processor 51;Wherein, be stored with can be by extremely for memory 52
The instruction that a few processor 51 executes, instruction is executed by least one processor 51, so that at least one processor 51 can
Execute the method that above-mentioned statistics stranger's face repeats.
Wherein, memory 52 is connected with processor 51 using bus mode, and bus may include any number of interconnection
Bus and bridge, bus is by one or more processors 51 together with the various circuit connections of memory 52.Bus can also incite somebody to action
Together with various other circuit connections of management circuit or the like, these are all abilities for such as peripheral equipment, voltage-stablizer
Well known to domain, therefore, it will not be further described herein.Bus interface is provided between bus and transceiver and is connect
Mouthful.Transceiver can be an element, is also possible to multiple element, such as multiple receivers and transmitter, provides for passing
The unit communicated on defeated medium with various other devices.The data handled through processor 51 are carried out on the radio medium by antenna
Transmission, further, antenna also receives data and transfers data to processor 51.
Processor 51 is responsible for management bus and common processing, can also provide various functions, including timing, periphery connects
Mouthful, voltage adjusting, power management and other control functions.And memory 52 can be used for storage processor 51 and execute behaviour
Used data when making.
The present invention provides a kind of computer readable storage medium again, is stored with computer program.Computer program is processed
Device realizes above method embodiment when executing.
It can be found that above scheme, can establish stranger's face characteristic library and available stranger's facial image,
Whether meet the requirements with the stranger's facial image that can detecte the acquisition, is in the stranger's facial image for detecting the acquisition
When undesirable, then stranger's facial image of the acquisition is considered as in vain, in the stranger's face figure for detecting the acquisition
Seem then stranger's facial image of the acquisition is considered as effectively when meeting the requirements, and can extract this be considered as it is effective strange
The feature of everybody face image, and can be by stranger's face characteristic of the feature of stranger's facial image of the extraction and the foundation
Library carries out similarity comparison and obtains similarity value, and may determine that whether the similarity value that the comparison obtains is greater than preset threshold
Value then judges that stranger's face is to repeat when the similarity value for judging that the comparison obtains is greater than preset threshold value
It is existing, and what can be judged to this is that the stranger's face repeated counts, and be can be realized to stranger's face weight
The situation for appearing again existing carries out identification and statistics.
Further, above scheme can use facial features localization mode, detect stranger's facial image of the acquisition
With the presence or absence of situation or the side face situation or hindbrain situation or smudgy situation etc. of bowing, stranger's face figure of the acquisition is detected
Seem it is no meet the requirements, be to exist to bow situation or side face situation or hindbrain feelings in the stranger's facial image for detecting the acquisition
Whens condition or smudgy situation etc., when detecting that stranger's facial image of the acquisition is undesirable, then by the acquisition
Stranger's facial image is considered as in vain, is that there is no bow situation or side face feelings in the stranger's facial image for detecting the acquisition
Whens condition or hindbrain situation or smudgy situation etc., detect that stranger's facial image of the acquisition then will when meeting the requirements
Stranger's facial image of the acquisition is considered as effectively, and such benefit is that by by by stranger's face figure of the acquisition
The efficiency of the case where repeating to stranger's face progress identification and statistics is improved as being considered as invalid or effective mode.
Further, above scheme, it can be determined that whether the similarity value that the comparison obtains is greater than preset threshold value, is sentencing
It is disconnected go out the comparison obtained similarity value when being no more than preset threshold value, then judge stranger's face be first appear, and
Archives are established in stranger's face characteristic library for the face first appeared, and such benefit is that by going out for the first time
Existing face establishes archives in stranger's face characteristic library, convenient for identifying the case where repeating to stranger's face
And statistics.
Further, above scheme can periodically optimize stranger's face characteristic library of the foundation, from the foundation
Stranger's face characteristic library in delete the stranger's face information for not repeating appearance within a preset time, such benefit is
It can ensure that stranger's face characteristic library of the foundation has reasonable memory space to be the face that first appears always and builds at this
Archives are established in vertical stranger's face characteristic library, convenient for being managed to stranger's face.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can
To realize by another way.For example, device embodiments described above are only schematical, for example, module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, institute
Display or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit
Indirect coupling or communication connection can be electrical property, mechanical or other forms.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of present embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) or processor (processor) execute each implementation of the present invention
The all or part of the steps of methods.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely section Examples of the invention, are not intended to limit protection scope of the present invention, all utilizations
Equivalent device made by description of the invention and accompanying drawing content or equivalent process transformation are applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of method that statistics stranger's face repeats characterized by comprising
Establish stranger's face characteristic library;
Obtain stranger's facial image;
Whether the stranger's facial image for detecting the acquisition meets the requirements, in the stranger's facial image for detecting the acquisition
When being undesirable, then stranger's facial image of the acquisition is considered as in vain, in the stranger for detecting the acquisition
Facial image is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements;
It is considered as the feature of effective stranger's facial image described in extraction;
Stranger's face characteristic library of the feature of stranger's facial image of the extraction and the foundation is subjected to similarity pair
Than obtaining similarity value;
Whether the similarity value for judging that the comparison obtains is greater than preset threshold value, is judging the similarity for comparing and obtaining
When value is greater than preset threshold value, then judge that stranger's face is to repeat;
Judge is that the stranger's face repeated is counted to described.
2. the method that statistics stranger's face repeats as described in claim 1, which is characterized in that obtained described in the detection
Whether the stranger's facial image taken meets the requirements, and is undesirable in the stranger's facial image for detecting the acquisition
When, then stranger's facial image of the acquisition is considered as in vain, is symbol in the stranger's facial image for detecting the acquisition
When conjunction requires, then stranger's facial image of the acquisition is considered as effectively, comprising:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side face feelings
Whether condition or hindbrain situation or smudgy situation, the stranger's facial image for detecting the acquisition meet the requirements, are detecting
Stranger's facial image of the acquisition is inspection when existing to bow situation or side face situation or hindbrain situation or smudgy situation
When to measure stranger's facial image of the acquisition be undesirable, then stranger's facial image of the acquisition is considered as nothing
Effect is that there is no bow situation or side face situations or hindbrain situation or fuzzy in the stranger's facial image for detecting the acquisition
When unclear situation, detect that stranger's facial image of the acquisition is when meeting the requirements, then by the acquisition it is strange everybody
Face image is considered as effectively.
3. the method that statistics stranger's face repeats as described in claim 1, which is characterized in that the judgement is described right
Whether the similarity value than obtaining is greater than preset threshold value, judge it is described compare obtained similarity value be greater than it is preset
When threshold value, then judge that stranger's face is to repeat, further includes:
Whether the similarity value for judging that the comparison obtains is greater than preset threshold value, is judging the similarity for comparing and obtaining
When value is no more than preset threshold value, then judge that stranger's face is the face for first appearing, and first appearing for described in
Archives are established in stranger's face characteristic library.
4. the method that statistics stranger's face repeats as described in claim 1, which is characterized in that sentence described to described
Breaking out is after the stranger's face repeated counts, further includes:
Stranger's face characteristic library of the foundation is periodically optimized, is deleted from stranger's face characteristic library of the foundation
Except the stranger's face information for not repeating appearance within a preset time.
5. a kind of device that statistics stranger's face repeats characterized by comprising
It establishes module, obtain module, detection module, extraction module, contrast module, judgment module and statistical module;
It is described to establish module, for establishing stranger's face characteristic library;
The acquisition module, for obtaining stranger's facial image;
Whether the detection module, stranger's facial image for detecting the acquisition meet the requirements, and are detecting described obtain
When the stranger's facial image taken is undesirable, then stranger's facial image of the acquisition is considered as in vain, is being detected
Stranger's facial image of the acquisition is then to be considered as stranger's facial image of the acquisition effectively when meeting the requirements out;
The extraction module, for extracting the feature for being considered as effective stranger's facial image;
The contrast module, for the feature of stranger's facial image of the extraction and stranger's face of the foundation is special
Sign library carries out similarity comparison and obtains similarity value;
The judgment module, whether the similarity value for judging that the comparison obtains is greater than preset threshold value, judging
When stating the obtained similarity value of comparison and being greater than preset threshold value, then judge that stranger's face is to repeat;
The statistical module, for judge to be that the stranger's face repeated is counted to described.
6. the device that statistics stranger's face repeats as claimed in claim 5, which is characterized in that the detection module,
It is specifically used for:
Using facial features localization mode, stranger's facial image of the acquisition is detected with the presence or absence of bow situation or side face feelings
Whether condition or hindbrain situation or smudgy situation, the stranger's facial image for detecting the acquisition meet the requirements, are detecting
Stranger's facial image of the acquisition is inspection when existing to bow situation or side face situation or hindbrain situation or smudgy situation
When to measure stranger's facial image of the acquisition be undesirable, then stranger's facial image of the acquisition is considered as nothing
Effect is that there is no bow situation or side face situations or hindbrain situation or fuzzy in the stranger's facial image for detecting the acquisition
When unclear situation, detect that stranger's facial image of the acquisition is when meeting the requirements, then by the acquisition it is strange everybody
Face image is considered as effectively.
7. the device that statistics stranger's face repeats as claimed in claim 5, which is characterized in that the judgment module,
Include:
First judgment module and the second judgment module;
Whether second judgment module, the similarity value for judging that the comparison obtains are greater than preset threshold value, are judging
When the similarity value that the comparison obtains out is greater than preset threshold value, then judge that stranger's face is to repeat;
Whether second judgment module, the similarity value for judging that the comparison obtains are greater than preset threshold value, are judging
When the similarity value that the comparison obtains out is no more than preset threshold value, then judge that stranger's face is to first appear,
And archives are established in stranger's face characteristic library for the face first appeared.
8. the device that statistics stranger's face repeats as claimed in claim 5, which is characterized in that the statistics stranger
The device that face repeats, further includes:
Optimization module;
The optimization module, for periodically being optimized to stranger's face characteristic library of the foundation, from the footpath between fields of the foundation
The stranger's face information for not repeating appearance within a preset time is deleted in stranger's face characteristic library.
9. a kind of equipment that statistics stranger's face repeats characterized by comprising
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
It manages device to execute, so that at least one described processor is able to carry out statistics stranger according to any one of claims 1 to 4
The method that face repeats.
10. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the computer program is located
Reason device realizes the method that statistics stranger's face described in any one of Claims 1-4 repeats when executing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910670902.9A CN110363180A (en) | 2019-07-24 | 2019-07-24 | A kind of method and apparatus and equipment that statistics stranger's face repeats |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910670902.9A CN110363180A (en) | 2019-07-24 | 2019-07-24 | A kind of method and apparatus and equipment that statistics stranger's face repeats |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110363180A true CN110363180A (en) | 2019-10-22 |
Family
ID=68220838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910670902.9A Pending CN110363180A (en) | 2019-07-24 | 2019-07-24 | A kind of method and apparatus and equipment that statistics stranger's face repeats |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110363180A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111428611A (en) * | 2020-03-19 | 2020-07-17 | 上海领感科技有限公司 | Big data based face recognition system and method for unregistered sports crowd |
CN112200034A (en) * | 2020-09-28 | 2021-01-08 | 武汉虹信技术服务有限责任公司 | Data clearing device and method and distributed face recognition system |
CN113221725A (en) * | 2021-05-08 | 2021-08-06 | 上海智蕙林医疗科技有限公司 | Risk processing method and system |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101609500A (en) * | 2008-12-01 | 2009-12-23 | 公安部第一研究所 | Quality estimation method of exit-entry digital portrait photos |
CN102024032A (en) * | 2010-11-29 | 2011-04-20 | 广州明朝网络科技有限公司 | Distributed data caching and persisting method and system based on Erlang |
CN104657714A (en) * | 2015-02-09 | 2015-05-27 | 重庆大学 | Illumination symmetry and global illumination intensity integrated no-reference face illumination evaluation method |
CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
CN105187771A (en) * | 2015-07-31 | 2015-12-23 | 山东创德软件技术有限公司 | Plant-level comprehensive supervision platform |
CN105354273A (en) * | 2015-10-29 | 2016-02-24 | 浙江高速信息工程技术有限公司 | Method for fast retrieving high-similarity image of highway fee evasion vehicle |
CN106803067A (en) * | 2016-12-28 | 2017-06-06 | 浙江大华技术股份有限公司 | A kind of quality of human face image appraisal procedure and device |
CN107067504A (en) * | 2016-12-25 | 2017-08-18 | 北京中海投资管理有限公司 | A kind of recognition of face safety-protection system and a suspect's detection and method for early warning |
CN107292228A (en) * | 2017-05-05 | 2017-10-24 | 珠海数字动力科技股份有限公司 | A kind of method for accelerating face recognition search speed |
CN108629305A (en) * | 2018-04-27 | 2018-10-09 | 朱旭辉 | A kind of face recognition method |
CN108932468A (en) * | 2018-04-27 | 2018-12-04 | 衡阳师范学院 | One kind being suitable for psychologic face recognition method |
US20190108404A1 (en) * | 2017-10-10 | 2019-04-11 | Weixin Xu | Consumer Camera System Design for Globally Optimized Recognition |
-
2019
- 2019-07-24 CN CN201910670902.9A patent/CN110363180A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101609500A (en) * | 2008-12-01 | 2009-12-23 | 公安部第一研究所 | Quality estimation method of exit-entry digital portrait photos |
CN102024032A (en) * | 2010-11-29 | 2011-04-20 | 广州明朝网络科技有限公司 | Distributed data caching and persisting method and system based on Erlang |
CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
CN104657714A (en) * | 2015-02-09 | 2015-05-27 | 重庆大学 | Illumination symmetry and global illumination intensity integrated no-reference face illumination evaluation method |
CN105187771A (en) * | 2015-07-31 | 2015-12-23 | 山东创德软件技术有限公司 | Plant-level comprehensive supervision platform |
CN105354273A (en) * | 2015-10-29 | 2016-02-24 | 浙江高速信息工程技术有限公司 | Method for fast retrieving high-similarity image of highway fee evasion vehicle |
CN107067504A (en) * | 2016-12-25 | 2017-08-18 | 北京中海投资管理有限公司 | A kind of recognition of face safety-protection system and a suspect's detection and method for early warning |
CN106803067A (en) * | 2016-12-28 | 2017-06-06 | 浙江大华技术股份有限公司 | A kind of quality of human face image appraisal procedure and device |
CN107292228A (en) * | 2017-05-05 | 2017-10-24 | 珠海数字动力科技股份有限公司 | A kind of method for accelerating face recognition search speed |
US20190108404A1 (en) * | 2017-10-10 | 2019-04-11 | Weixin Xu | Consumer Camera System Design for Globally Optimized Recognition |
CN108629305A (en) * | 2018-04-27 | 2018-10-09 | 朱旭辉 | A kind of face recognition method |
CN108932468A (en) * | 2018-04-27 | 2018-12-04 | 衡阳师范学院 | One kind being suitable for psychologic face recognition method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111428611A (en) * | 2020-03-19 | 2020-07-17 | 上海领感科技有限公司 | Big data based face recognition system and method for unregistered sports crowd |
CN111428611B (en) * | 2020-03-19 | 2022-07-12 | 上海领感科技有限公司 | Big data-based face recognition system and method for unregistered sports crowd |
CN112200034A (en) * | 2020-09-28 | 2021-01-08 | 武汉虹信技术服务有限责任公司 | Data clearing device and method and distributed face recognition system |
CN113221725A (en) * | 2021-05-08 | 2021-08-06 | 上海智蕙林医疗科技有限公司 | Risk processing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109858365B (en) | Special crowd gathering behavior analysis method and device and electronic equipment | |
CN106998444B (en) | Big data face monitoring system | |
CN110363180A (en) | A kind of method and apparatus and equipment that statistics stranger's face repeats | |
CN105631427A (en) | Suspicious personnel detection method and system | |
JP2008544705A (en) | Detect and track surveillance objects from overhead video streams | |
CN101556717A (en) | ATM intelligent security system and monitoring method | |
CN106027974A (en) | Image processing apparatus and image processing method | |
CN107403165B (en) | Data management architecture of intelligent face recognition system and use method | |
CN109858442B (en) | Stranger passing monitoring method and device based on entrance guard machine | |
CN110781735A (en) | Alarm method and system for identifying on-duty state of personnel | |
CN112699328A (en) | Network point service data processing method, device, system, equipment and storage medium | |
CN113343913A (en) | Target determination method, target determination device, storage medium and computer equipment | |
CN207233038U (en) | Face is called the roll and number system | |
CN112492383A (en) | Video frame generation method and device, storage medium and electronic equipment | |
CN110717428A (en) | Identity recognition method, device, system, medium and equipment fusing multiple features | |
CN107967743A (en) | A kind of personal identification method being applied in e-bidding and system | |
CN114898443A (en) | Face data acquisition method and device | |
CN110532929A (en) | A kind of same pedestrian's analysis method and device and equipment | |
CN110796014A (en) | Garbage throwing habit analysis method, system and device and storage medium | |
CN112580531A (en) | Method and system for identifying and detecting true and false license plates | |
CN110443187B (en) | Recording method and device of characteristic information | |
CN112258707A (en) | Intelligent access control system based on face recognition | |
CN109120896B (en) | Security video monitoring guard system | |
CN112689120A (en) | Monitoring method and device | |
CN109871456A (en) | A kind of detention house personnel relationship analysis method, device and electronic equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |