CN111639689B - Face data processing method and device and computer readable storage medium - Google Patents
Face data processing method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN111639689B CN111639689B CN202010431025.2A CN202010431025A CN111639689B CN 111639689 B CN111639689 B CN 111639689B CN 202010431025 A CN202010431025 A CN 202010431025A CN 111639689 B CN111639689 B CN 111639689B
- Authority
- CN
- China
- Prior art keywords
- face
- snapshot data
- abnormal
- snapshot
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a face data processing method, a device and a computer readable storage medium, wherein the method comprises the following steps: aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period, respectively determining the number of face snapshot data belonging to the same person; determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device; and determining the face image corresponding to the abnormal face snapshot data quantity as a suspected abnormal face image. According to the method, based on the statistical rule that the snapshot amount of the billboard is obviously higher than that of other non-billboard faces, the abnormal face image amount is determined from the face image amounts acquired by the same acquisition device, and the face image corresponding to the abnormal face image amount is determined to be the suspected abnormal face image, so that the preliminary identification of the suspected billboard is realized quickly and conveniently.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a face data processing method, a face data processing device, and a computer readable storage medium.
Background
With the rapid development of big data technology, face snapshot is the most direct and effective way for managing social security in security industry. The data contains certain social behaviors and social relations of human beings, and the effective and intelligent analysis of the face snapshot data can bring about extremely effective effects for the stability and public security of the society. However, the face-based snapshot machine has certain limitations in both the snapshot stage and the face recognition analysis stage, and cannot avoid the snapshot of two-dimensional planar face pictures and other suspected face images; therefore, waste of storage resources is caused, and accuracy of the analysis function based on the face data is affected.
Therefore, the limitation of the face snapshot machine and the face recognition stage is improved based on data analysis, the storage pressure of the face data can be reduced to a certain extent, and the waste of storage resources is avoided; meanwhile, the quality of the data can be improved, so that the accuracy of the analysis function based on the face data is improved, and the method has important research significance on the application and structural design of a face system.
In the prior art, face pictures are mainly acquired through snapshot equipment, face modeling analysis is carried out, and a human_id is given; and then, warehousing and persistent storage are carried out. However, due to the limitation of face recognition of the snapshot equipment, the modeling analysis is carried out on the front-end snapshot picture by the rear end, and the two-dimensional plane face picture cannot be accurately recognized. The prior art has the following defects:
At present, capturing face pictures through snapshot equipment, storing the pictures, identifying the faces through a face identification analysis algorithm, and labeling the faces with human_id; however, the condition that the two-dimensional plane face image is captured cannot be avoided because the picture is analyzed; the equipment for capturing also has certain limitation, and the captured pictures are not all face pictures, so that some things suspected to be faces can be captured.
Disclosure of Invention
The application aims to provide a face data processing method, a face data processing device and a computer readable storage medium. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of the embodiment of the present application, there is provided a face data processing method, including:
aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period, respectively determining the number of face snapshot data belonging to the same person;
Determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device;
and determining the face image corresponding to the abnormal face snapshot data quantity as a suspected abnormal face image.
According to another aspect of the embodiments of the present application, there is provided a face data processing apparatus, including:
the first module is used for respectively determining the number of face snapshot data belonging to the same person aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period;
the second module is used for determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device;
and the third module is used for determining that the face image corresponding to the abnormal face snapshot data quantity is a suspected abnormal face image.
According to another aspect of the embodiments of the present application, there is provided a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the above-described face data processing method.
According to another aspect of an embodiment of the present application, there is provided an electronic device including: the face data processing system comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the face data processing method.
One of the technical solutions provided in one aspect of the embodiments of the present application may include the following beneficial effects:
according to the face data processing method, based on the statistical rule that the snapshot amount of the billboard is obviously higher than that of other non-billboard faces, the number of abnormal face images is determined from the number of the plurality of face images acquired by the same acquisition device, and the face image corresponding to the number of the abnormal face images is determined to be the suspected abnormal face image, so that preliminary identification of the suspected billboard is rapidly and conveniently achieved.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a face data processing method of an embodiment of the present application;
FIG. 2 shows a flow chart of one implementation of step S10 of the embodiment shown in FIG. 1;
FIG. 3 shows a flow chart of another implementation of step S10 of the embodiment shown in FIG. 1;
FIG. 4 shows a block diagram of a face data processing apparatus of another embodiment of the present application;
FIG. 5 illustrates a block diagram of a face data processing system of one embodiment of the present application;
FIG. 6 shows a flow chart of a face data processing method of an embodiment of the present application;
fig. 7 shows a schematic diagram of a snapshot device according to an embodiment of the present application taking a picture of a face on a billboard.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As shown in fig. 1, a first embodiment of the present application provides a face data processing method, including:
s10, determining suspected abnormal face images from face images acquired by the same acquisition device.
In certain embodiments, as shown in fig. 2, step S10 includes:
s20, determining the number of face images belonging to the same person aiming at all face images acquired by the same acquisition device in a preset statistical period; for example, in all face images acquired by the acquisition Device1, the number of face images N1 of the person a, the number of face images N2 of the person B, the number of face images N3 of the person C, and the like are finally determined respectively by a face image clustering algorithm.
S21, determining the number of abnormal face images from the number of the face images corresponding to the same acquisition device; the above example is used to determine the number of abnormal face images from the number of face images belonging to the same person, such as N1, N2, N3; for example, when n1=500, n2=40, n3=50, since N1 is far greater than N2, N3, the number of face images where N1 is abnormal can be determined. Other ways of determining the number of abnormal face images may also be used, which is not limited in this embodiment.
S22, determining the face images corresponding to the abnormal face image number as suspected abnormal face images. In the above example, after determining the number of face images N1 is abnormal, the face images of the N1 persons a may be determined to be suspected abnormal face images.
The acquisition means may be a snapshot device, such as a face snapshot machine, for taking a photograph containing a face image. The snapshot device is generally arranged in public places with large people flow to conduct face snapshot, such as railway stations and the like, and non-real two-dimensional plane face images such as face photos on billboards often exist in the public areas. When the snapshot machine detects that the continuous change of the pictures exceeds a certain number (a preset threshold number), the snapshot is performed.
For example, the threshold number of frames is set to 96, when the snapshot machine detects that the number of frames of continuous variation exceeds 96 frames, the snapshot is performed, and when the number of frames of continuous variation does not exceed 96 frames, the snapshot is not performed. Therefore, when a moving object exists in front of the billboard, the snapshot machine can snapshot the billboard area when detecting that the continuous change of the pictures exceeds the preset threshold number. Because the area of the billboard is relatively large, and the billboard generally has figures, the snapshot amount of the billboard is obviously higher than that of other non-billboard faces. Based on such statistics rules, the number of abnormal face images is determined according to the number of the plurality of face images acquired by the same acquisition device, and the face image corresponding to the number of the abnormal face images is determined to be the suspected abnormal face image, so that the preliminary identification of the suspected advertising board is rapidly and conveniently realized.
In some embodiments, determining the abnormal number of face snapshot data from the plurality of face snapshot data numbers corresponding to the same acquisition device includes:
determining the total number of face snapshot data acquired by the same acquisition device in the preset statistical period;
Aiming at the face snapshot data quantity of any person, if the ratio of the face snapshot data quantity to the total number of the face snapshot data exceeds a first preset threshold, determining that the face snapshot data quantity is abnormal; or if the ratio of the number of the face snapshot data to the total number of the face snapshot data in the preset proportion exceeds a second preset threshold value, determining that the number of the face snapshot data is the abnormal number of the face images. Specifically, the face snapshot data may be a face image.
In some embodiments, determining the abnormal number of face images from the number of face images corresponding to the same acquisition device includes: in face images acquired by the same acquisition device in a preset statistical period, if the ratio of the number of face images of a certain person to the number of all face images acquired by the acquisition device in the preset statistical period exceeds a first preset threshold or the ratio of the number of face images of the certain person to the number of face images of a preset proportion of the number of all face images exceeds a second preset threshold, the number of face images of the certain person is an abnormal number of face images.
Namely: in face images acquired by the same acquisition device in a preset statistical period, if the ratio of the number A of face images of a certain person to the total number B of face images acquired by the acquisition device exceeds a first preset threshold D, or the ratio of the number A of face images of a certain person to the total number of face images acquired by the acquisition device in a preset proportion (the specific proportion can be set according to actual needs) is recorded as that the ratio in the number C exceeds a second preset threshold E, the face images of the certain person are suspected abnormal face images. I.e. if A/B > D or A/C > E, the face image of the person is a suspected abnormal face image. Because the snapshot amount of the billboard is obviously higher than that of other non-billboard faces, the ratio of the snapshot amount of the billboard in the total or partial face image amount collected by the collecting device is also larger, when the ratio exceeds a preset threshold, the number of the face images is determined to be abnormal, and the corresponding face images are suspected abnormal face images such as suspected billboard face images.
In some embodiments, determining the abnormal number of face images from the number of face images corresponding to the same acquisition device includes:
Selecting the front n face image numbers from the face image numbers corresponding to the same acquisition device according to the descending order of the face snapshot data numbers; the ratio of the sum of the front n face image numbers in all face image numbers acquired by the same acquisition device exceeds a third preset threshold;
and if the ratio of the number of the face images of a certain person in the sum of the number of the front n face images exceeds a fourth preset threshold, determining that the number of the face images is abnormal.
In some embodiments, a face image set corresponding to the acquisition device is formed by the face image acquired by the same acquisition device, the acquisition time of each face image and the acquisition device identification of the acquisition device, and then a suspected abnormal face image is screened out from the face image set.
In certain embodiments, as shown in fig. 3, step S10 includes:
S101、
and marking all face images belonging to the same face by using unique face identification aiming at all face images acquired by the same acquisition device in a preset statistical period, and calculating the number of face images corresponding to each face identification.
All face images of the same face are marked by the same face mark, and face images of different faces are respectively marked by different face marks. Each face corresponds to a face identification.
For example, the face identification may be human1, human2, human3 … …, and the like, and the number of face images identified as human1, the number of face images identified as human2, the number of face images identified as human3, and the like are calculated.
S102, selecting comparison marks from all the face marks, and forming a comparison set by using the face images marked by the comparison representation, wherein in some embodiments, the ratio of the sum of the number of the face images of all the comparison marks to the total number of all the face images acquired by the same acquisition device reaches or exceeds a first preset threshold; the comparison mark is that the number ranking of the marked face images belongs to the face mark with a plurality of preset values; the preset numerical value is determined according to the preset first threshold value and the total number of all face images.
When the ratio of the number of the face images in the comparison set to the number of the face images collected by the collection device reaches 100%, all the face images collected by the collection device need to be formed into the comparison set. In order to reduce the amount of calculation, the threshold is generally set to a value smaller than 100%.
S103, determining the ratio of the number of face images marked by each comparison mark to the total number of face images of the comparison set.
For example, as shown in table 1, the number of face images corresponding to 7 face identifications captured by four capturing devices.
Table 1 Snapshot statistics Top7 of the Snapshot device
| Snapshot equipment identifier | human1 | human2 | human3 | human4 | human5 | human6 | human7 |
| X33010853011210000150 | 776 | 52 | 9 | 6 | 6 | 6 | 4 |
| X33010351001210000022 | 339 | 51 | 10 | 6 | 6 | 6 | 6 |
| X33010462001210010427 | 2536 | 16 | 16 | 10 | 10 | 9 | 9 |
| X33010456001210010385 | 2306 | 19 | 5 | 4 | 4 | 3 | 3 |
human1, human2, human3, human4, human5, human6 and human7 are face identifications of 7 persons, and are respectively used for identifying corresponding face images. Each face identification uniquely identifies a face. The faces corresponding to the 7 face identifications are seven faces with the largest number of times of the capturing equipment. The corresponding image quantity ranks that face images of 7 people more than the front account for 90% of the quantity of face images collected by the same collecting device. The face images of the 7 top persons are selected in the embodiment, and the preset value is 7 in the embodiment.
X33010853011210000150, X33010351001210000022, X33010462001210010427 and X33010456001210010385 are all identifiers of the acquisition devices.
Setting:
n is the snapshot amount of the snapshot equipment device.
P is the snapshot amount of the billboard that is snapped by the device.
R is the snapshot amount of normal pedestrians which are snapshot by the device.
Then there is: P/N > > R/N.
Taking the human1 as an example, the number of face images of the human1 captured by X33010853011210000150 is 776, the number of face images of the human1 captured by X33010351001210000022 is 339, the number of face images of the human1 captured by X33010462001210010427 is 2536, and the number of face images of the human1 captured by X33010456001210010385 is 2306.
A duty cycle threshold is set, for example, to 30%, and so 30% because a billboard will not typically exceed 3 face pictures. Therefore, if the billboard is adopted, the snapshot rate is more than 30% in a high probability. When the ratio of the snap shot quantity of the same face mark acquired by the same acquisition device to the total number of the face images of the 7 persons acquired by the acquisition device exceeds the ratio threshold, the possibility that the face mark is the face of the billboard is high. All face images corresponding to the face identification are suspected abnormal face images meeting preset conditions, wherein the preset conditions are that the proportion of the number of face images corresponding to the face identification in the total number of face images of 7 persons collected by the collecting device exceeds a set proportion threshold (30% in this case).
According to the statistical rule, the number of face images of the human1 captured by X33010853011210000150 is 776, the number of face images of the human7 is 4, the number of face images of the 7 captured faces is 859, 776/859 (90.34), 4/859 (0.466), the occupation ratio of the human1 in the first 7 with the highest captured amount is more than 90%, and the face images of the human1 are suspected abnormal face images;
the number of face images of the human1 which is captured by X33010351001210000022 is 339, the number of face images of the 7 faces which are captured is 424, 339/424 is approximately equal to 79.95%, the ratio of the face images of the human1 in the first 7 persons with the highest capturing amount is more than 70%, and the face images of the human1 are suspected face images; the number of face images of the human1 which is snapped by X33010462001210010427 is 2536, the number of face images of the 7 faces which are snapped is 2606, 2536/2606 is approximately equal to 97.31%, and the ratio of the number of face images of the human1 is more than 90%, so that the human1 is identified as abnormal human_id (namely abnormal human face identification); the number of face images of the human1 which is captured by X33010456001210010385 is 2306, the number of face images of the 7 faces which are captured is 2344, 2306/2344 is approximately equal to 98.38%, the ratio of the human1 in the first 7 faces with the highest capturing amount is more than 90%, and then the face images of the human1 are suspected abnormal face images.
S104, determining a comparison mark corresponding to the ratio larger than a preset duty ratio threshold value as a suspected abnormal face mark, wherein the face image marked by the suspected abnormal face mark is a suspected abnormal face image.
In the face images collected by the four collecting devices, the number of face images of the face mark human1 is more than 30%, so that the face mark human1 is identified as suspected abnormal human_id (namely suspected abnormal face mark). By using the suspected abnormal face identification obtained by the steps as a reference, the suspected abnormal face identification can be used for judging whether the subsequently obtained face image is an abnormal face image or not under the condition of low requirement on the accuracy of the abnormal face identification. In the process of acquiring the face image in real time, the acquired face image can be filtered by using the suspected abnormal face image marked by the suspected abnormal face mark.
However, it cannot be determined that the face image corresponding to the human1 is the face image on the billboard, for example: this is a normal snapshot when a person stands under the snapshot machine and does not move. If the requirement on the recognition accuracy of the abnormal face image is high, the abnormal face image needs to be further analyzed according to a space-time rule. Thus, in another embodiment, the face data processing method further includes:
Determining a suspected abnormal face image set formed by face images belonging to the same person in the suspected abnormal face images acquired by the acquisition devices; for example, face images marked as the same face mark acquired by each acquisition device can be acquired, namely face images belonging to the same person can be acquired, and a suspected abnormal face image set is formed.
If the space-time information of at least two face images in the suspected abnormal face image set meets the abnormal condition, determining that the face images in the suspected abnormal face image set are abnormal face images; the time-space information comprises the acquisition time and the acquisition position of the face image.
The space-time information satisfies an abnormal condition such as that the acquisition time difference is smaller than a preset time interval, and the distance of the acquisition position is larger than a preset distance; alternatively, the ratio of the distance of the acquisition position to the acquisition time difference exceeds a preset speed threshold, etc., without limitation.
Specifically, as shown in fig. 1, in some embodiments, the face data processing method further includes the following steps:
s30, determining a suspected abnormal face snapshot data set formed by face snapshot data of the same person in the suspected abnormal face snapshot data acquired by each acquisition device in the preset statistical period; if the space-time information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image; the time-space information comprises the snapshot time and the snapshot device of the face snapshot data.
In some embodiments, before determining that the face image in the suspected abnormal face snapshot data set is the abnormal face image if the spatiotemporal information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set satisfies the abnormal condition, the method further includes:
sequencing all the snapshot devices according to earliest snapshot time;
and deleting the face snapshot data of each snapshot device between the earliest snapshot time of the snapshot device and the earliest snapshot time of the next snapshot device in the sequence.
In some embodiments, if the spatiotemporal information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set satisfies an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image includes:
determining at least two pieces of snapshot data with different snapshot devices, wherein the snapshot time difference is smaller than a preset time threshold value;
if the distance between the snapshot devices corresponding to the at least two pieces of snapshot data is larger than a preset distance threshold, determining that the space-time information of the snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition;
and determining the face image in the suspected abnormal face snapshot data set as an abnormal face image.
The face data processing method provided by the second embodiment of the application comprises the following steps:
1) And determining suspected abnormal face images from the face images acquired by the same acquisition device.
2) And forming a face image data set by using the suspected abnormal face images acquired by the acquisition devices, the acquisition time of each suspected abnormal face image, the identification of the acquisition device and the identification of the suspected abnormal face.
For example, a face image (suspected abnormal face image) corresponding to human1, a collection time of the face image collected to human1, and identifications X33010853011210000150, X33010351001210000022, X33010462001210010427 and four collection devices
X33010456001210010385 constitutes a face image dataset.
3) Determining the acquisition distance and the acquisition time difference corresponding to any two suspected abnormal face images marked by the same suspected abnormal face mark in the face image data set; the acquisition distance refers to the distance between acquisition devices for acquiring two suspected abnormal face images; the acquisition time difference refers to the time difference of the acquisition time of two suspected abnormal face images.
4) And judging whether the same suspected abnormal face mark is an abnormal face mark or not according to the acquisition distance and the acquisition time difference.
In some embodiments, determining whether the same suspected abnormal face identifier is an abnormal face identifier according to the acquisition distance and the acquisition time difference includes:
(1) Determining a ratio of the acquisition distance to the acquisition time difference;
(2) And judging whether the suspected abnormal face identification is an abnormal face identification or not according to the ratio.
Step (2) judging whether the suspected abnormal face mark is an abnormal face mark according to the ratio, comprising the following steps:
comparing each ratio with a preset threshold, and if the ratio is larger than the preset threshold, the suspected abnormal face identification corresponding to the ratio is an abnormal face identification; otherwise, not the abnormal face identification.
For example, assume that two face images of the same face are respectively at time point t 3 And time point t 4 Quilt device D 3 And device D 4 The snapshot is taken, and the acquisition time difference is deltat= |t 3 -t 4 I, acquisition distance D is device D 3 And D 4 The distance between them, the ratio v=Δt/d of the acquisition distance to the acquisition time difference. This ratio represents the speed of movement of the person. If this speed exceeds the attempted value, an anomaly is present. For example, the highest speed limit in all the snap shots is 70km/h, i.e. the preset threshold The value is 70km/h, if the calculated speed is 1000km/h,1000km/h>70km/h, then the face image on the billboard that was snap shot can be determined.
In some embodiments, determining whether the same suspected abnormal face identifier is an abnormal face identifier according to the acquisition distance and the acquisition time difference includes:
judging whether the acquisition distance and the acquisition time difference meet respective corresponding preset threshold conditions or not; if yes, the suspected abnormal face identification is an abnormal face identification, otherwise, the suspected abnormal face identification is not the abnormal face identification.
By spatio-temporal rules is meant rules that exist for longitudinal alignment in both the temporal and spatial dimensions. A time period threshold and a distance threshold are preset. If the interval between the snapping time points of the two snapping devices on the same billboard is smaller than a preset time period threshold, the snapping time points of the two snapping devices belong to the same snapping time sequence. If the distance between two snapshot devices for taking the same billboard is greater than a preset distance threshold, the two snapshot devices belong to the same snapshot space sequence. If two face images of a person belong to the same snapshot time sequence and belong to the same snapshot space sequence, the two face images can be considered to be abnormal face images.
Example 1: the same face picture a on the billboard is snapped to and stored in the database at adjacent times or at the same time by different devices 17km apart, as shown in fig. 7.
Table 2 some face identification humanld is snap shot to record TOP5
Table 2 shows the case where a certain humand is captured at different times; such as: at T 1 The time instant is simultaneously captured by X33011067001210001382, X33010454001210010372 and X33010456001210010385, and is denoted by a mark 1.
Setting:
t 1 ,t 2 ∈T 1 i.e. t 1 、t 2 Belonging to the same snapshot time sequence (set of time points with instant length less than a certain length, for example, T= [ T ] 1 ,t 2 ]T represents T 1 And t 2 A set of all moments in between);
D 1 and D 2 Numbering two snapshot devices respectively;
t 1 for D 1 The time from the snapshot to the billboard;
t 2 for D 2 The time from the snapshot to the billboard;
then there is:
acquisition time difference |t 1 -t 2 |<threshold (default 2 min)
And acquisition distance D (D 1 ,D 2 )>threshold (default 2 km).
For example, the preset threshold is set to 400km/h, if the ratio v of the acquisition distance to the acquisition time difference is more than 400km/h, the face in the face image can be determined to be an abnormal face, and the face image is a face image on a billboard; otherwise, the face is not abnormal. The judging method is actually carried out according to the speed which can be reached by a real person. For example, the highest speed of a person riding on a high-speed rail can reach 380km/h, and if the ratio v exceeds 400km/h, the possibility of being an abnormal face is high. The preset threshold value can be adjusted according to actual conditions and is generally set to be the highest speed limit of the snapshot coverage area.
And aiming at the abnormal face, obtaining face identification/identity information of an abnormal face image, and filtering the abnormal face data according to the face identification/identity information in the process of capturing data of the real-time face image.
For example, if the suspected abnormal face image corresponding to the same humanld corresponds to an abnormal face (for example, a face image on a billboard), the face image corresponding to the human1, the corresponding acquisition device identifier and the acquisition time are directly filtered in the process of acquiring the face image in real time.
In some embodiments, the abnormal face identifier, the abnormal face image and the acquisition device identifier and the acquisition time of the abnormal face image in the face image data set are additionally stored in other databases and used as comparison information, when a new face image is acquired, the new face image is compared with the abnormal face image, if the new face image is the face image of the same person, the face corresponding to the new face image is also the abnormal face, and the new face image is not stored in the database of normal face images.
The third embodiment of the present application provides a face data processing method, on the basis of the first embodiment, before step S10 of screening a suspected abnormal face image from face images acquired by the same acquisition device, the method further includes:
S00, extracting all face images from all photos captured by each acquisition device;
the snap shot photos are snap shot by a collecting device such as a snap shot device; performing face recognition on the snap shot photo, and recognizing the face from the photo;
comparing the extracted face images, assigning the same face identification to the face images belonging to the same person, for example, comparing the extracted face images, assigning the same face identification human_id to the identified face images belonging to the same person, namely, each face corresponds to a unique face identification, and all face images of the face are marked by the face identification;
s01, acquiring the identification and the acquisition time of an acquisition device for acquiring each face image.
And searching the equipment identification of the snapping equipment which captures each face image and the snapping time of the snapping equipment which captures the face image.
And marking the face image of the same person by using a face mark, and associating the mark of the corresponding snapshot equipment of each face image with the face image so as to facilitate searching.
On the basis of the second embodiment of the present application, as shown in fig. 2, before determining in step 3) that the collection distance and the collection time difference corresponding to any two suspected abnormal face images marked by the same suspected abnormal face identifier in the face image dataset, the method further includes: 2') cleaning the data of the suspected abnormal face images acquired by the acquisition devices to obtain a cleaned face image data set. In this embodiment, in step 3), a difference between the acquisition distance and the acquisition time corresponding to any two suspected abnormal face images marked by the same suspected abnormal face identifier in the cleaned face image dataset is determined. Through data cleaning, repeated face images captured in the same time period and the same place in the face image data set are removed, the data processing workload is reduced, the data processing efficiency is improved, and the data processing pressure is reduced. The data cleaning operation step is to delete the collection record of each collection device between the earliest collection time of the collection device and the earliest collection time of the next collection device.
In some embodiments, step 2') of performing data cleaning on the suspected abnormal face image acquired by each acquisition device to obtain a cleaned face image dataset, including:
s001, sequencing the identification of each acquisition device according to the sequence of the earliest acquisition time; the earliest acquisition time is the acquisition time when the acquisition device acquires the suspected abnormal face image earliest;
s002, removing suspected abnormal face images acquired by each acquisition device identifier in the sequencing in a corresponding adjacent time period to obtain a cleaned face image dataset consisting of the rest suspected abnormal face images; the contiguous time period is the time period between two earliest acquisition times that are adjacent in the ordering.
The range of the visual field of the snapshot device is limited, so that if the same person does not leave the visual field within a certain period of time, a plurality of photos can be captured, if all face images of the person in the photos are stored, a large amount of storage space is occupied, and the waste of the storage space is caused.
The use of the snap-shot face image is used for tracking a specific person, etc., and the snap-shot face image is processed for statistical analysis, so that the specific person can be found and the specific person can be determined to be at a certain place at a certain time. For example, if a specific person a is always located in the visual area of the capturing device a at 8 points 10 minutes 12 seconds to 8 points 40 minutes 22 seconds on a certain day, is captured by a to a plurality of photos, is captured by B to a plurality of photos in the visual area of the capturing device B at 8 points 41 minutes 41 seconds to 9 points 5 minutes 53 seconds, and then returns to the visual area of a at 9 points 6 minutes 17 seconds to 9 points 24 minutes 49 seconds, when the specific person a is sequenced according to the earliest capturing time, the specific person a is located before B and is adjacent to B, the earliest capturing time of a is 8 points 10 minutes 12 seconds, the earliest capturing time of B is 8 points 41 minutes 41 seconds, the adjacent time period corresponding to a is a time period between 8 points 10 minutes 12 seconds to 8 points 41 minutes 41 seconds, when data cleaning is performed, face images of the person a captured in the time period between 8 points 10 minutes 12 seconds to 8 points 41 minutes 41 seconds are deleted, only face images captured by 8 points 10 minutes 12 seconds are retained, or images captured by the face images captured by the earliest adjacent to the face can be retained in the earliest adjacent time periods, and if images captured by the face images are clear, the face images can be removed in the adjacent time periods. Therefore, the data to be stored is greatly reduced, the repeated storage of the face images is avoided, the storage space is saved, and the data processing efficiency is improved.
In some embodiments, step 2') of performing data cleaning on the suspected abnormal face image acquired by each acquisition device to obtain a cleaned face image dataset, including:
s1, searching a first acquisition time and a first acquisition device identifier from the suspected abnormal face image data set; the first acquisition time is the acquisition time of earliest acquiring a suspected abnormal face image; the first acquisition device identifier is an acquisition device identifier for acquiring the suspected abnormal face image at the first acquisition time;
s2, searching a second acquisition time and a second acquisition device from the suspected abnormal face image data set; the second acquisition time is the acquisition time when the acquisition device except the first acquisition device acquires the suspected abnormal face image earliest; the second acquisition device identifier is an acquisition device identifier for acquiring the suspected abnormal face image at the second acquisition time;
s3, removing suspected abnormal face images acquired by the first acquisition device in a first time period; the first time period is a time period between the first acquisition time and the second acquisition time;
S4, taking the second acquisition time as a new first acquisition time, taking the second acquisition device as a new first acquisition device, and turning to the step S2 until the second acquisition time is not found, and obtaining a cleaned face image data set.
In some embodiments, in order to read the factors of data speed, calculation speed, etc., the acquisition record of the snapshot device is selected as the calculation data structure:
i. the spatial point (i.e. the snapshot device) is used as a key.
Taking the time sequence of the human_id captured by the capturing device (key) as a value.
The number of snap devices that snap to a certain human_id within a day is limited and the length of the composed spatial sequence is much smaller than the length of the time sequence composed with snap times.
And a certain human_id is repeatedly and uninterruptedly shot by one shooting device, so that a single shooting device is caused to take a shot in a time sequence of 'bloated', and only one shooting record of a certain device is ensured to exist for a period of time through data cleaning until the shooting record is taken by different devices.
The data structure is set as follows:
[d 1 ,<t 11 ,t 12 ,t 13 ……t 1x1 >]
[d 2 ,<t 21 ,t 22 ,t 23 ……t 2x2 >]
……
[d m ,<t m1 ,t m2 ,t m3 ……t mxn >]
for example, the cleaning process includes the steps of:
1) Find the minimum time from all the snapshot time sequences (t min ) And record t min The device (device) key )；
2) From a non-device key Find out in other device sequences greater than t min Is (t) temp ) And records the device (device) temp )；
3) Removing device key More than t in the snapshot time sequence min Less than t temp Is a time point of all time points of (2);
4) Let t temp Assigning t to min ，device temp Assignment to device key The next cycle is performed.
5) Up to t temp If not, the cycle is ended.
The face data processing method provided by the embodiment can accurately identify and remove abnormal face images, improves the effective rate of collecting face data, avoids the waste of storage space, reduces storage pressure and improves the collection efficiency of effective face data.
In some embodiments, if the spatiotemporal information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set satisfies an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image includes:
determining at least two pieces of snapshot data with different snapshot devices, wherein the snapshot time difference is smaller than a preset time threshold value;
if the distance between the snapshot devices corresponding to the at least two pieces of snapshot data is larger than a preset distance threshold, determining that the space-time information of the snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition;
And determining the face image in the suspected abnormal face snapshot data set as an abnormal face image.
For example, the number of the cells to be processed,
1) The Key is taken as time, and items with the Key difference less than a snapshot time interval threshold (equivalent to the time interval threshold in the space-time law) are combined.
2) Finding the value of Key holds the items of different snapshot devices.
And calculating the distance between different snapshot devices in the single item, and judging that the suspected billboard is snapshot if the distance is greater than a threshold (equivalent to a distance interval threshold in a space-time law).
As shown in fig. 4, another embodiment of the present application further provides a face data processing apparatus, including:
the first module is used for respectively determining the number of face snapshot data belonging to the same person aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period;
the second module is used for determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device;
and the third module is used for determining that the face image corresponding to the abnormal face snapshot data quantity is a suspected abnormal face image.
In certain embodiments, the apparatus further comprises:
A fourth module, configured to determine a suspected abnormal face snapshot dataset formed by face snapshot data of the same person in the suspected abnormal face snapshot data collected by each collecting device in the preset statistics period; if the space-time information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image; the time-space information comprises the snapshot time and the snapshot device of the face snapshot data.
Another embodiment of the present application also provides a computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the above-mentioned face data processing method.
Another embodiment of the present application further provides an electronic device, including: the face data processing system comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the face data processing method.
In another embodiment of the present application, face data is collected and processed by a face data processing system. As shown in fig. 5, the face data processing system includes the following parts:
1) The acquisition device is used for capturing face images;
2) Static comparison server: comparing and modeling the data of the snapshot of the front-end snapshot equipment (namely the acquisition device) for consumption, and endowing unique face identification human_id for the identified face;
3) Face acquisition module: after the static comparison server completes face recognition, data are sent back to Kafka; the face acquisition module consumes data in Kafka, and filters the data by performing human_id comparison; kafka is a high throughput distributed publish-subscribe messaging system;
4) A suspected billboard analysis module: and (3) identifying the human_id of the suspected billboard by analyzing the historical data in the database and updating the human_id into the filtering cache of the face acquisition module.
Fig. 6 is a flowchart of a face data processing method according to the present embodiment. The suspected bill-board analysis module analyzes and processes the snapshot data, and comprises the following steps:
1. snapshot feature analysis
The face suspected billboard snapshot data have specific statistical rules and space-time rules, and whether the data of the billboard can be accurately identified through the rules.
a) Statistics law
The statistical rule is generated by the snapshot rule of the face snapshot machine. When the snapshot machine detects that the continuous change of the pictures exceeds a certain number (a preset threshold number), the snapshot is performed. For example, the threshold number of frames is set to 96, when the snapshot machine detects that the number of frames of continuous variation exceeds 96 frames, the snapshot is performed, and when the number of frames of continuous variation does not exceed 96 frames, the snapshot is not performed.
Therefore, when a moving object exists in front of the billboard, the snapshot machine can snapshot the billboard area when detecting that the continuous change of the pictures exceeds the preset threshold number. Because the area of the billboard is relatively large, and the billboard generally has a portrait, the snapshot amount of the billboard is relatively large in the occupation ratio of the snapshot amount of the snapshot equipment. Based on the statistical rule, the first step of snap shot analysis of the suspected advertising board is performed. Reference may be made to the data in table 1 above.
Setting a duty ratio threshold value, for example, may be set to 30%, and when the snap shot amount duty ratio of a face mark exceeds the duty ratio threshold value, the face mark is more likely to be the face of the billboard. Through the above statistical rules, the raman 1 can be identified as an abnormal raman_id, but it cannot be determined that the raman 1 is a billboard, for example: this is a normal snapshot when a person stands under the snapshot machine and does not move. Further analysis according to the space-time law is required.
b) Space-time law
The space-time law refers to a law which exists in the longitudinal comparison of two dimensions of time and space.
A time period threshold and a distance threshold are preset. If the interval between the snapping time points of the two snapping devices on the same billboard is smaller than a preset time period threshold, the snapping time points of the two snapping devices belong to the same snapping time sequence. If the distance between two snapshot devices for taking the same billboard is greater than a preset distance threshold, the two snapshot devices belong to the same snapshot space sequence. Reference may be made to the examples in table 2 above.
2. Construction of data structures
In order to read the factors such as data speed, calculation speed, etc., the device acquisition record is selected as a calculation data structure:
i. the spatial point (i.e. the snapshot device) is used as a key.
Taking the time sequence of the human_id captured by the capturing device (key) as a value.
The number of snap devices that snap to a certain human_id within a day is limited and the length of the composed spatial sequence is much smaller than the length of the time sequence composed with snap times.
And a certain human_id is repeatedly and uninterruptedly shot by one shooting device, so that a single shooting device is caused to take a shot time sequence to be 'bloated', and only one shooting record of a certain device is ensured to exist for a period of time through cleaning data until the shooting record is taken by different devices.
Data structure:
[d 1 ,<t 11 ,t 12 ,t 13 ……t 1x1 >]
[d 2 ,<t 21 ,t 22 ,t 23 ……t 2x2 >]
……
[d m ,<t m1 ,t m2 ,t m3 ……t mxn >]
cleaning rules:
1) Find the minimum time from all the snapshot time sequences (t min ) And record t min The device (device) key )；
2) From a non-device key Find out in other device sequences greater than t min Is (t) temp ) And records the device (device) temp )；
3) Removing device key More than t in the snapshot time sequence min Less than t temp Is a time point of all time points of (2);
4) Let t temp Assigning t to min ，device temp Assignment to device key The next cycle is performed.
5) Up to t temp If not, the cycle is ended.
Pseudo code example:
1)Begin
2)device key ,t min <-Function min(T<device>)
3)WHILE device temp ,t temp <-Function min(T<device other >and>t min )≠null
4)DO
5)remove(t min ,t temp ]from T<device min >
6)t min <-t temp
7)device key <-device temp
8)DONE
9)END
and (5) analyzing and calculating suspected billboards:
firstly, carrying out statistical probability analysis based on snapshot equipment, and screening abnormal human_id acquired by the snapshot equipment;
then, carrying out space-time analysis on the snapshot equipment corresponding to the abnormal human_id.
The distribution of the snapshot devices can have decisive influence on the characteristics of snapshot data, so that a unified calculation standard is not provided, and the threshold value can be set according to the situation of the scene.
Based on the above calculation data structure, a recognition algorithm for the suspected billboard of the face snapshot is provided.
The identification algorithm of the suspected billboard face image comprises the following steps:
1) Selecting a snapshot device to be analyzed, and carrying out grouping statistics on the human_id acquired by the snapshot device;
2) When the capture amount of the human_id exceeds a certain threshold value (default 30%) than the total capture amount of the equipment, marking the human_id as an abnormal human_id, and acquiring acquisition records of other capture equipment of the human_id to form a data structure to be analyzed;
3) Data cleaning is carried out on a data structure to be analyzed, transposition is carried out, the time is used as a key (key), and items with the key difference value smaller than a snapshot time interval threshold (equivalent to the time interval threshold in a space-time rule) are combined;
4) Finding out the items of which the value of Key has different snapshot devices;
5) And calculating the distance between different snapshot devices in the single item, and judging that the suspected billboard is snapshot if the distance is greater than a threshold (equivalent to a distance interval threshold in a space-time law).
In the method of the embodiment, in the process of face image acquisition, the data of the analyzed face image of the suspected advertisement board is accurately identified and removed, and the data of the suspected advertisement board is directly forbidden to be put in storage in the acquisition stage. The data acquisition efficiency can be improved while the pressure of the storage system is reduced.
According to the method, aiming at face snapshot suspected billboard analysis, suspected billboard snapshot records can be accurately identified, the pressure of a storage system of face data can be reduced, and meanwhile, the accuracy of the function of data analysis based on the face data is improved.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, modules may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same components. There may or may not be clear boundaries between different modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with the teachings herein. The required structure for the construction of such devices is apparent from the description above. In addition, the present application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and the above description of specific languages is provided for disclosure of preferred embodiments of the present application.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the present application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing examples merely represent embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (8)
1. A face data processing method, comprising:
aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period, respectively determining the number of face snapshot data belonging to the same person;
determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device;
determining the face images corresponding to the abnormal face snapshot data quantity as suspected abnormal face images;
determining a suspected abnormal face snapshot data set formed by face snapshot data of the same person in the suspected abnormal face snapshot data collected by each collecting device in the preset statistical period; if the space-time information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image; the time-space information comprises the snapshot time and the snapshot device of the face snapshot data.
2. The method according to claim 1, wherein determining the abnormal number of face snapshot data from the plurality of face snapshot data numbers corresponding to the same acquisition device includes:
determining the total number of face snapshot data acquired by the same acquisition device in the preset statistical period;
aiming at the face snapshot data quantity of any person, if the ratio of the face snapshot data quantity to the total number of the face snapshot data exceeds a first preset threshold, determining that the face snapshot data quantity is abnormal; or if the ratio of the number of the face snapshot data to the total number of the face snapshot data in the preset proportion exceeds a second preset threshold value, determining that the number of the face snapshot data is the abnormal number of the face images.
3. The method according to claim 1, wherein determining the abnormal number of face snapshot data from the plurality of face snapshot data numbers corresponding to the same acquisition device includes:
according to the descending order of the face snapshot data quantity, the front n face snapshot data quantity is selected from a plurality of face snapshot data quantities corresponding to the same acquisition device; the ratio of the sum of the front n face snapshot data amounts in the total number of face snapshot data acquired by the same acquisition device in the preset statistical period exceeds a third preset threshold;
And if the ratio of the face snapshot data quantity of a certain person to the sum of the front n face snapshot data quantities exceeds a fourth preset threshold value, determining that the face snapshot data quantity is abnormal.
4. The method according to claim 1, wherein if the spatiotemporal information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set satisfies an abnormal condition, before determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image, the method further comprises:
sequencing all the snapshot devices according to earliest snapshot time;
and deleting the face snapshot data of each snapshot device between the earliest snapshot time of the snapshot device and the earliest snapshot time of the next snapshot device in the sequence.
5. The method according to claim 1, wherein determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image if the spatiotemporal information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set satisfies an abnormal condition, comprises:
determining at least two pieces of snapshot data with different snapshot devices, wherein the snapshot time difference is smaller than a preset time threshold value;
If the distance between the snapshot devices corresponding to the at least two pieces of snapshot data is larger than a preset distance threshold, determining that the space-time information of the snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition;
and determining the face image in the suspected abnormal face snapshot data set as an abnormal face image.
6. A face data processing apparatus, comprising:
the first module is used for respectively determining the number of face snapshot data belonging to the same person aiming at all face snapshot data acquired by the same acquisition device in a preset statistical period;
the second module is used for determining abnormal face snapshot data quantity from a plurality of face snapshot data quantities corresponding to the same acquisition device;
a third module, configured to determine that a face image corresponding to the abnormal face snapshot data number is a suspected abnormal face image;
a fourth module, configured to determine a suspected abnormal face snapshot dataset formed by face snapshot data of the same person in the suspected abnormal face snapshot data collected by each collecting device in the preset statistics period; if the space-time information of at least two pieces of snapshot data in the suspected abnormal face snapshot data set meets an abnormal condition, determining that the face image in the suspected abnormal face snapshot data set is an abnormal face image; the time-space information comprises the snapshot time and the snapshot device of the face snapshot data.
7. A computer-readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the face data processing method according to any one of claims 1 to 5.
8. An electronic device, comprising: a memory, a processor, and a computer program stored in the memory, the processor running the computer program to perform the face data processing method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431025.2A CN111639689B (en) | 2020-05-20 | 2020-05-20 | Face data processing method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010431025.2A CN111639689B (en) | 2020-05-20 | 2020-05-20 | Face data processing method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111639689A CN111639689A (en) | 2020-09-08 |
| CN111639689B true CN111639689B (en) | 2023-07-25 |
Family
ID=72331483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010431025.2A Active CN111639689B (en) | 2020-05-20 | 2020-05-20 | Face data processing method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639689B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112885101B (en) * | 2021-03-30 | 2022-06-14 | 浙江大华技术股份有限公司 | Method and device for determining abnormal equipment, storage medium and electronic device |
| CN113255621B (en) * | 2021-07-13 | 2021-11-16 | 浙江大华技术股份有限公司 | Face image filtering method, electronic device and computer-readable storage medium |
| CN115297174B (en) * | 2022-10-10 | 2023-03-24 | 广州市易鸿智能装备有限公司 | Method and device for sequentially storing out-of-order data source, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016141641A1 (en) * | 2015-03-11 | 2016-09-15 | 中兴通讯股份有限公司 | Method and device for recognizing suspicious person |
| CN107016322A (en) * | 2016-01-28 | 2017-08-04 | 浙江宇视科技有限公司 | A kind of method and device of trailing personnel analysis |
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN107679613A (en) * | 2017-09-30 | 2018-02-09 | 同观科技（深圳）有限公司 | A kind of statistical method of personal information, device, terminal device and storage medium |
| CN107766797A (en) * | 2017-09-27 | 2018-03-06 | 汉柏科技有限公司 | A kind of stranger's recognition methods and system |
| CN108363947A (en) * | 2017-12-29 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Delay demographic method for early warning based on big data and device |
| CN108509657A (en) * | 2018-04-27 | 2018-09-07 | 深圳爱酷智能科技有限公司 | Data distribute store method, equipment and computer readable storage medium |
| CN110636258A (en) * | 2019-09-09 | 2019-12-31 | 四川东方网力科技有限公司 | Method, device, equipment and storage medium for analyzing peer personnel |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6248303B2 (en) * | 2013-08-14 | 2017-12-20 | 株式会社北電子 | Amusement park system |
| CN108229335A (en) * | 2017-12-12 | 2018-06-29 | 深圳市商汤科技有限公司 | It is associated with face identification method and device, electronic equipment, storage medium, program |
| CN109063582A (en) * | 2018-07-10 | 2018-12-21 | 武汉云易虹科技有限公司 | It is a kind of to determine the doubtful system and method bought and sold and divide personnel automatically |
| CN110472491A (en) * | 2019-07-05 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Abnormal face detecting method, abnormality recognition method, device, equipment and medium |
-
2020
- 2020-05-20 CN CN202010431025.2A patent/CN111639689B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016141641A1 (en) * | 2015-03-11 | 2016-09-15 | 中兴通讯股份有限公司 | Method and device for recognizing suspicious person |
| CN107016322A (en) * | 2016-01-28 | 2017-08-04 | 浙江宇视科技有限公司 | A kind of method and device of trailing personnel analysis |
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN107766797A (en) * | 2017-09-27 | 2018-03-06 | 汉柏科技有限公司 | A kind of stranger's recognition methods and system |
| CN107679613A (en) * | 2017-09-30 | 2018-02-09 | 同观科技（深圳）有限公司 | A kind of statistical method of personal information, device, terminal device and storage medium |
| CN108363947A (en) * | 2017-12-29 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Delay demographic method for early warning based on big data and device |
| CN108509657A (en) * | 2018-04-27 | 2018-09-07 | 深圳爱酷智能科技有限公司 | Data distribute store method, equipment and computer readable storage medium |
| CN110636258A (en) * | 2019-09-09 | 2019-12-31 | 四川东方网力科技有限公司 | Method, device, equipment and storage medium for analyzing peer personnel |
Non-Patent Citations (3)
| Title |
|---|
| FaceNet: A Unified Embedding for Face Recognition and Clustering;Florian Schroff等;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;全文 * |
| 人脸识别技术的研究;史姗姗;中国优秀硕士学位论文全文数据库;全文 * |
| 社区人脸识别的技术途径综述;秦程;;重庆工贸职业技术学院学报(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111639689A (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639689B (en) | Face data processing method and device and computer readable storage medium | |
| CN104303193B (en) | Target classification based on cluster | |
| CN107153817B (en) | Pedestrian re-identification data labeling method and device | |
| CN107016322B (en) | Method and device for analyzing followed person | |
| TWI416068B (en) | Object tracking method and apparatus for a non-overlapping-sensor network | |
| CN109190586B (en) | Customer's visiting analysis method, device and storage medium | |
| Parham et al. | Animal population censusing at scale with citizen science and photographic identification | |
| CN109784270B (en) | Processing method for improving face picture recognition integrity | |
| CN111291682A (en) | Method and device for determining target object, storage medium and electronic device | |
| WO2021043089A1 (en) | Customer traffic counting method and apparatus, device, and computer readable storage medium | |
| CN111625687B (en) | Method and system for quickly searching people in media asset video library through human faces | |
| WO2022156234A1 (en) | Target re-identification method and apparatus, and computer-readable storage medium | |
| US20130343618A1 (en) | Searching for Events by Attendants | |
| CN109117771B (en) | System and method for detecting violence events in image based on anchor nodes | |
| CN113269081A (en) | System and method for automatic personnel identification and video track query | |
| JP2023527239A (en) | Methods and devices for acquiring information and systems for detecting attention | |
| CN111209446A (en) | Method and device for presenting personnel retrieval information and electronic equipment | |
| CN112464850A (en) | Image processing method, image processing apparatus, computer device, and medium | |
| CN111027385B (en) | Clustering visitor statistics method, system, equipment and computer readable storage medium | |
| CN114078277A (en) | One-person-one-file face clustering method and device, computer equipment and storage medium | |
| Ahmed et al. | Temporal image forensic analysis for picture dating with deep learning | |
| CN110796014A (en) | Garbage throwing habit analysis method, system and device and storage medium | |
| US20210073515A1 (en) | Data processing apparatus, data processing method, and non-transitory storage medium | |
| CN111708907A (en) | Target person query method, device, equipment and storage medium | |
| CN115083004B (en) | Identity recognition method and device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |