CN110598754A - Online monitoring method, device and equipment based on image detection and storage medium - Google Patents
Online monitoring method, device and equipment based on image detection and storage medium Download PDFInfo
- Publication number
- CN110598754A CN110598754A CN201910759750.XA CN201910759750A CN110598754A CN 110598754 A CN110598754 A CN 110598754A CN 201910759750 A CN201910759750 A CN 201910759750A CN 110598754 A CN110598754 A CN 110598754A
- Authority
- CN
- China
- Prior art keywords
- image
- user
- value
- values
- hamming distance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000012544 monitoring process Methods 0.000 title description 14
- 238000000605 extraction Methods 0.000 claims abstract description 26
- 238000004590 computer program Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 15
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an on-line supervision method, device, equipment and storage medium based on image detection, wherein the method comprises the following steps: acquiring a user image from a user side at a preset time interval, and performing feature extraction on the user image to obtain an image feature value corresponding to the user image; if the number of the acquired user images reaches a preset value, randomly extracting N image characteristic values from a set formed by the image characteristic values, wherein N is a positive integer larger than 1; calculating Hamming distance values of the N image characteristic values, and taking an average value of the Hamming distance values as a check value; and if the check value is larger than a preset threshold value, confirming that the user side passes the image detection. The technical scheme of the invention improves the supervision capability on the data security on the online education network platform and reduces the false behavior of network falsification.
Description
Technical Field
The present invention relates to the field of information processing, and in particular, to an online monitoring method, apparatus, device, and storage medium based on image detection.
Background
Remote online education is becoming a new way for people to obtain information. People can use intelligent equipment such as cell-phone APP, panel computer can realize teaching activities such as remote training, study, communicate with mr and communicate in any place through the internet. The remote online education overcomes the defects of the traditional teaching mode, and provides a brand-new teaching mode for teaching participants such as students, teachers, institutions and the like.
Currently, there are more and more online education platforms, however, many of them have a vulnerability in reliability of use. For example, during the use of some educational training platforms, cheaters can cheat the servers of the online platforms in various ways to obtain enough online learning time, thereby achieving the purpose of obtaining training certification qualification. Therefore, a convenient and reliable supervision method is urgently needed for each online education platform to effectively supervise the participation process of the network trainees so as to ensure the reliability of online training.
Disclosure of Invention
The embodiment of the invention provides an image detection-based online monitoring method, device, equipment and storage medium, which aim to solve the problem of insufficient security monitoring of online data by the conventional online education network platform.
An online supervision method based on image detection comprises the following steps:
acquiring a user image from a user side at a preset time interval, and performing feature extraction on the user image to obtain an image feature value corresponding to the user image;
if the number of the acquired user images reaches a preset value, randomly extracting N image characteristic values from a set formed by the image characteristic values, wherein N is a positive integer larger than 1;
calculating Hamming distance values of the N image characteristic values, and taking an average value of the Hamming distance values as a check value;
and if the check value is larger than a preset threshold value, determining that the user side passes the image detection.
An image detection-based online supervision device, comprising:
the system comprises a characteristic extraction module, a feature extraction module and a feature extraction module, wherein the characteristic extraction module is used for acquiring a user image from a user side at a preset time interval and extracting the characteristics of the user image to obtain an image characteristic value corresponding to the user image;
the random sampling module is used for randomly extracting N image characteristic values from a set formed by the image characteristic values if the number of the acquired user images reaches a preset value, wherein N is a positive integer greater than 1;
the characteristic calculation module is used for calculating Hamming distance values of the N image characteristic values and taking the average value of the Hamming distance values as a check value;
and the characteristic comparison module is used for determining that the user side passes the image detection if the check value is greater than a preset threshold value.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the above-mentioned image detection-based online supervision method when executing the computer program.
A computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-described image detection-based online surveillance method.
According to the image detection-based online monitoring method, device, equipment and storage medium, when a user performs online education, learning and training or online examination through a client, the user image is acquired from the client at a preset time interval, and the characteristic value of the user image is extracted; when the number of the acquired user images reaches a certain number, randomly extracting and sampling the acquired user images, obtaining a check value by calculating a Hamming characteristic value, determining whether the user passes through image detection according to the size relation between the check value and a preset threshold value, and further determining whether the user has a cheating behavior, so as to ensure fairness and justness of the user in the processes of online education, learning and training or online examination; therefore, the supervision capability of the data security on the online education network platform under the new application trend of the Internet is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of an image detection-based online monitoring method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an image detection-based online surveillance method according to an embodiment of the invention;
FIG. 3 is a flowchart of step S1 in the image detection-based online supervision method according to an embodiment of the present invention;
FIG. 4 is a flowchart of step S3 in the image detection-based online supervision method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an on-line monitoring apparatus based on image detection according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a computer device in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The online monitoring method based on image detection provided by the invention can be applied to the application environment as shown in fig. 1, wherein the server is a computer device providing online monitoring service based on image detection, and the server can be a server or a server cluster; the client is a mobile phone APP, a tablet computer, a PC or other intelligent terminal equipment used in application scenes of online learning, training, remote education and the like of a user; the client and the server are connected through a network, and the network can be a limited network or a wireless network. The image detection-based online supervision method provided by the embodiment of the invention is applied to a server.
In an embodiment, as shown in fig. 2, an online monitoring method based on image detection is provided, and a specific implementation flow thereof includes the following steps:
s1: and acquiring a user image from a user side at a preset time interval, and performing feature extraction on the user image to obtain an image feature value corresponding to the user image.
The user image refers to a user photo acquired by a server through a camera of a client in the process of online education, learning and training or online examination of a user.
The image feature value is data reflecting the characteristics of the user image. For example, the gray value distribution of the image, the time-space domain transformed array of the image, and the like can be obtained. The image time-space domain transformation includes, but is not limited to, digital fourier transformation, digital cosine transformation, and digital wavelet transformation.
And feature extraction, which is a process of processing the user image and obtaining an image feature value. Feature extraction is performed at the server.
The preset time interval is a time interval which is predetermined by the client and the server in advance and can be flexibly set. E.g., 3 minutes, 5 minutes, etc.
Specifically, taking a user as an example, the user uses a special APP for online training through a mobile phone to perform online training, and in the training process, the APP calls a mobile phone camera to take pictures of the face of the user every 5 minutes to obtain a user image. It will be appreciated that over time facial images of the user at different times during the training process will be captured.
Correspondingly, the server side obtains the user image from the APP side, and performs feature extraction on the user image to obtain an image feature value of each user image. The image characteristic values can be used for distinguishing different users, namely different users, and the image characteristic values of the user images are different; moreover, because the user images of each user are continuously acquired along with the time, different user images of the same user also have differences, and the server side can further perform identification according to the differences, so that whether the user cheats in the online training process is determined.
S2: and if the number of the acquired user images reaches a preset value, randomly extracting N image characteristic values from a set formed by the image characteristic values, wherein N is a positive integer greater than 1.
For a specific user, the server side obtains a certain number of user images of the user along with the time, and meanwhile, the image characteristic value of each user image can form a data set; and when the number of the user images is equal to a preset value, the server side randomly extracts N image characteristic values from the image characteristic values of the user images.
The preset value may be set by the server, for example, 10, and when the server continuously acquires 10 user images of the same user, the server randomly extracts at least 2 image feature values from the 10 image feature values, that is, N is greater than 1, and preferably, N is greater than 3.
S3: and calculating Hamming distance values of the N image characteristic values, and taking the average value of the Hamming distance values as a check value.
The hamming distance refers to the number of different characters of two equal-length character strings at corresponding positions in the information theory. The hamming distance value is the value of the hamming distance between two image characteristic values.
The check value is the average value of the Hamming distance values.
Specifically, if N is 2, the hamming distance between 2 image feature values is a hamming distance value, that is, a check value. If N is 4, in 4 image feature values, a hamming distance value is calculated for every two image feature values, so that 6 hamming distance values can be obtained, and the average value of the 6 hamming distance values is taken as a check value.
The Hamming distance value among the image characteristic values shows the change difference among the user images, can reflect whether the change condition of the face, the head and the background of the user in training or online examination is reasonable or not, and is beneficial to preventing the user from falsifying and faking by uploading tampered images or photos.
S4: and if the check value is larger than the preset threshold value, determining that the user side passes the image detection.
And the preset threshold value is used for comparing with the check value to judge whether the change of the check value exceeds the range or not, so as to determine whether the user has false behavior or not.
Specifically, the preset threshold is an empirical value set by the server. The preset threshold value can be obtained according to experiments of testers, for example, multiple testers normally use a mobile phone APP to perform online training, and the preset threshold value is determined according to the floating range of the check value. When the check value is larger than the preset threshold value, it can be determined that the user passes the image detection, and the user does not have behaviors such as falsification and the like. Otherwise, the user can be classified as a suspicious user, and the user's online behavior is monitored in a key manner through manual intervention.
In this embodiment, when a user performs an online education, learning training, or online examination process through a client, user images are acquired from the client at preset time intervals, and feature values of the user images are extracted; when the number of the acquired user images reaches a certain number, randomly extracting and sampling the acquired user images, obtaining a check value by calculating a Hamming characteristic value, determining whether the user passes through image detection according to the size relation between the check value and a preset threshold value, and further determining whether the user has a cheating behavior, so as to ensure fairness and justness of the user in the processes of online education, learning and training or online examination; therefore, the supervision capability of the data security on the online education network platform under the new application trend of the Internet is greatly improved.
Further, in an embodiment, after step S3, that is, after the step of calculating hamming distance values of the N image feature values and taking an average value of the hamming distance values as a check value, the online monitoring method based on image detection further includes the steps of:
and if the check value is less than or equal to the preset threshold value, acquiring the identification information of the user side, and listing the identification information into a blacklist.
The identification information of the user side refers to information for uniquely identifying the user, and includes, but is not limited to, a user name, browser information, IP address information, mobile phone model information, an operating system version, a device number, and the like.
The black list is a list for distinguishing normal users from abnormal users. The users in the blacklist can still be identified by the service end after the equipment is replaced or the IP is replaced.
Specifically, when the check value is less than or equal to the preset threshold, the server may send a data request to the mobile APP on the client, and the mobile APP sends the identification information of the user to the server, and the server lists the identification information in a blacklist. For example, if the identification information acquired by the server is the user name of the user, the user name cannot normally log in; if the identification information acquired by the server is the IP address of the user, even if the user re-registers the user name, normal login cannot be performed due to IP address restriction.
Preferably, each user terminal may be assigned a credit value with an initial value of 2. When the check value is less than or equal to the preset threshold value and the credit value is greater than 0, subtracting 1 from the credit value; when the check value is less than or equal to a preset threshold value and the credit value is less than or equal to 0, listing the identification information of the user side into a blacklist; that is, each ue is provided with at least 2 opportunities, and meanwhile, the server is prevented from being falsely detected.
In this embodiment, the server is configured to distinguish a normal user from an abnormal user by establishing a blacklist, so as to prevent the abnormal user from continuing to use the online service provided by the server.
Further, in an embodiment, for the step S1, the feature extraction for the user image specifically includes the following steps:
s11: and reducing the user image to a preset size by using a preset image difference algorithm to obtain an image to be processed.
The image difference algorithm is a compensation method for image pixels in the process of amplifying and reducing an image.
The preset size is the size of the image set for the convenience of the server side process. In the present embodiment, the predetermined size is 64 × 64 pixels.
Specifically, the image difference algorithm may be a nearest neighbor interpolation method, a bilinear interpolation method, or a bicubic interpolation method. Selecting a pixel point which is closest to the inserted pixel point, and replacing the inserted pixel point by the gray value of the pixel point; the bilinear interpolation method is to perform linear interpolation along x and y directions on a pixel matrix; bicubic interpolation is a method in which the pixel value of an insertion point can be obtained by weighted average of the nearest sixteen sampling points in a rectangular grid. And the server reduces the user image through a preset image difference algorithm to obtain the image to be processed.
S12: and converting the image to be processed into a gray picture.
Specifically, the server converts the image to be processed into a grayscale picture in various ways. For example, in the averaging method, the RGB values of 3 channels at the same pixel position in the image to be processed are averaged to obtain the gray value of the pixel.
S13: and carrying out discrete cosine transform on the gray level picture to obtain a two-dimensional matrix.
Discrete cosine transform is a kind of data orthogonal transform, which is used to perform lossy compression on original data in signal processing and/or image processing. The discrete cosine transform includes one-dimensional discrete cosine transform and two-dimensional discrete cosine transform
Specifically, the server performs two-dimensional discrete cosine transform on the grayscale image to obtain a two-dimensional matrix.
S14: converting the two-dimensional matrix into a one-dimensional array; and serializing the one-dimensional array into a character string, and taking the character string as an image characteristic value corresponding to the user image.
Specifically, the server side can sequentially take out all matrix elements in the two-dimensional matrix according to the sequence of rows and columns, and form a one-dimensional array; calculating the average value of all elements in the one-dimensional array, and then aiming at each element, if the value of the element is higher than or equal to the average value, the element corresponds to a binary value 1; if the value of an element is lower than the average value, the element corresponds to a binary value of 0, i.e., the one-dimensional array is converted into a binary string, which is used as the image feature value corresponding to the user image.
In this embodiment, the server zooms the user image through interpolation to obtain an image to be processed, which is convenient for the server to perform unified processing and extract a characteristic value; converting an image to be processed into a gray picture, and performing discrete cosine transform on the gray picture, namely compressing the image to be processed, so as to reduce interference information in the image to be processed; and converting the two-dimensional matrix after discrete cosine transformation to finally obtain a binary character string, namely, taking the data amount as little as possible as an image characteristic value, so that the storage space of a server can be saved.
Further, in an embodiment, before step S11, that is, before step S uses a preset image difference algorithm to reduce the user image to a preset size, and obtain an image to be processed, the online monitoring method based on image detection further includes the steps of:
EXIF information of the user image is detected, and the direction of the user image is adjusted according to the EXIF information.
Among them, EXIF information, i.e., Exchangeable image file format, may exchange attribute information in the image file format. The EXIF information can reflect relevant information in a user image file shot by the client, and the server can adjust the user image according to the EXIF information so as to ensure that the subsequently extracted image characteristic value is more accurate.
The EXIF information includes a manufacturer, a camera model, an image direction, an image resolution, a resolution unit, an exposure time, a photographing mode, an image photographing time, and the like. The server side mainly adjusts according to the value of the attribute 'image direction' in the EXIF information. For example, if the image direction Orientation value in the EXIF information is not equal to "upper-left", it represents that the image direction is not normal, and the server turns the user image by 90 °.
In this embodiment, the service end detects EXIF information of the user image, and adjusts the direction of the image according to the value of the EXIF information, so that the problem of inaccuracy of the extracted image feature value caused by incorrect image direction can be solved.
Further, in an embodiment, for step S3, that is, calculating hamming distance values of the N image feature values, and taking an average value of the hamming distance values as a check value, the method specifically includes the following steps:
s31: and randomly selecting one image characteristic value from the N image characteristic values as a scalar.
Specifically, taking N as 5 as an example, the server randomly selects one of 5 image feature values as a scalar.
S32: and calculating Hamming distances between the scalar and the N-1 image characteristic values to obtain N-1 Hamming distance values.
The server calculates hamming distances from the scalar selected in step S31 and the remaining 4 image feature values one by one to obtain 4 hamming distance values.
S33: and averaging the Hamming distance values obtained by removing at least M extreme values from the N-1 Hamming distance values to obtain a check value, wherein M is 2.
Where M extreme values, M being 2, are the maximum and minimum values from the 4 hamming distance values. After removing two extreme values in the 4 Hamming distances, the server calculates the average value of the remaining two Hamming distance values, and takes the check value as the check value. Preferably, if the number of N-1 Hamming distance values is too large, more Hamming distance values can be removed on the basis of the maximum and minimum two extreme values, thereby increasing the calculation speed.
In this embodiment, the server divides the N image feature values into two parts, where the number of one part is 1, that is, a scalar, calculates a hamming distance between the scalar and another part of the image feature values, and performs a step of removing an extremum and averaging on the hamming distance values obtained by calculation, thereby obtaining a check value. Compared with the method in the step S3, the method of the embodiment is simpler and more convenient, the number of hamming distance values is reduced, the calculation load of the server is reduced, and the obtained check value can reflect the characteristics of the user image.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, an image detection-based online monitoring device is provided, and the image detection-based online monitoring device corresponds to the image detection-based online monitoring method in the above embodiments one to one. As shown in fig. 5, the online supervision apparatus based on image detection includes a feature extraction module 51, a random sampling module 52, a feature calculation module 53, and a feature comparison module 54. The functional modules are explained in detail as follows:
the feature extraction module 51 is configured to obtain a user image from a user side at preset time intervals, and perform feature extraction on the user image to obtain an image feature value corresponding to the user image;
a random sampling module 52, configured to randomly extract N image feature values from a set of image feature values if the number of acquired user images reaches a preset value, where N is a positive integer greater than 1;
a feature calculating module 53, configured to calculate hamming distance values of the N image feature values, and take an average value of the hamming distance values as a check value;
and the feature comparison module 54 is configured to determine that the user side passes the image detection if the check value is greater than the preset threshold.
Further, the online supervision device based on image detection still includes:
and a blacklist setting module 55, configured to, if the check value is less than or equal to the preset threshold, obtain the identification information of the user side, and list the identification information in a blacklist.
Further, the feature extraction module 51 includes:
the image size adjusting submodule 511 is configured to reduce the user image to a preset size by using a preset image difference algorithm, so as to obtain an image to be processed;
the gray scale operator module 512 is used for converting the image to be processed into a gray scale picture;
the image transformation submodule 513 is configured to perform discrete cosine transformation on the grayscale image to obtain a two-dimensional matrix;
a hash value extraction submodule 514 for converting the two-dimensional matrix into a one-dimensional array; and serializing the one-dimensional array into a character string, and taking the character string as an image characteristic value corresponding to the user image.
Further, the feature extraction module 51 further includes:
and the direction detection sub-module 510 is configured to detect EXIF information of the user image, and adjust the direction of the user image according to the EXIF information.
Further, the feature calculating module 53 includes:
a scalar quantity extraction submodule 531 for randomly selecting an image feature value from the N image feature values as a scalar quantity;
the distance calculation submodule 532 is used for calculating Hamming distances between the scalar and the N-1 image characteristic values to obtain N-1 Hamming distance values;
the check value operator module 533 is configured to average hamming distance values obtained by removing at least M extreme values from the N-1 hamming distance values to obtain a check value, where M is 2.
For specific limitations of the image detection-based online supervision apparatus, reference may be made to the above limitations of the image detection-based online supervision method, which are not described herein again. The modules in the image detection-based online supervision device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an online supervision method based on image detection.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the image detection-based online supervision method in the foregoing embodiments, such as steps S1 to S4 shown in fig. 2. Alternatively, the processor, when executing the computer program, implements the functions of the modules/units of the online supervising device based on image detection in the above embodiments, such as the functions of the modules 51 to 54 shown in fig. 5. To avoid repetition, further description is omitted here.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when being executed by a processor implements the online supervision method based on image detection in the above method embodiment, or which when being executed by a processor implements the functions of the modules/units in the online supervision apparatus based on image detection in the above apparatus embodiment. To avoid repetition, further description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An image detection-based online supervision method is characterized by comprising the following steps:
acquiring a user image from a user side at a preset time interval, and performing feature extraction on the user image to obtain an image feature value corresponding to the user image;
if the number of the acquired user images reaches a preset value, randomly extracting N image characteristic values from a set formed by the image characteristic values, wherein N is a positive integer larger than 1;
calculating Hamming distance values of the N image characteristic values, and taking an average value of the Hamming distance values as a check value;
and if the check value is larger than a preset threshold value, determining that the user side passes the image detection.
2. The image-detection-based online supervision method according to claim 1, wherein after the computing hamming distance values of the N image feature values and taking an average value of the hamming distance values as a check value, the image-detection-based online supervision method further comprises:
and if the check value is less than or equal to a preset threshold value, acquiring the identification information of the user side, and listing the identification information into a blacklist.
3. The image detection-based online supervision method according to claim 1, wherein the performing feature extraction on the user image to obtain an image feature value corresponding to the user image comprises:
reducing the user image to a preset size by using a preset image difference algorithm to obtain an image to be processed;
converting the image to be processed into a gray picture;
performing discrete cosine transform on the gray level picture to obtain a two-dimensional matrix;
converting the two-dimensional matrix into a one-dimensional array; and serializing the one-dimensional array into a character string, and taking the character string as an image characteristic value corresponding to the user image.
4. The image-detection-based online supervision method according to claim 3, wherein before the image to be processed is obtained by reducing the user image to a preset size using a preset image difference algorithm, the image-detection-based online supervision method further comprises:
detecting EXIF information of the user image, and adjusting the direction of the user image according to the EXIF information.
5. The image detection-based online supervision method according to claim 1, wherein the calculating hamming distance values of the N image feature values and taking the average value of the hamming distance values as a check value comprises:
randomly selecting an image characteristic value from the N image characteristic values as a scalar;
calculating Hamming distances between the scalar and the N-1 image characteristic values to obtain N-1 Hamming distance values;
and averaging the Hamming distance values obtained by removing at least M extreme values from the N-1 Hamming distance values to obtain the check value, wherein M is 2.
6. An image detection-based online supervision device, which is characterized by comprising:
the system comprises a characteristic extraction module, a feature extraction module and a feature extraction module, wherein the characteristic extraction module is used for acquiring a user image from a user side at a preset time interval and extracting the characteristics of the user image to obtain an image characteristic value corresponding to the user image;
the random sampling module is used for randomly extracting N image characteristic values from a set formed by the image characteristic values if the number of the acquired user images reaches a preset value, wherein N is a positive integer greater than 1;
the characteristic calculation module is used for calculating Hamming distance values of the N image characteristic values and taking the average value of the Hamming distance values as a check value;
and the characteristic comparison module is used for determining that the user side passes the image detection if the check value is greater than a preset threshold value.
7. The image detection-based online surveillance apparatus of claim 6, further comprising:
and the blacklist setting module is used for acquiring the identification information of the user side and listing the identification information into a blacklist if the check value is less than or equal to a preset threshold value.
8. The image detection-based online supervision apparatus according to claim 7, wherein the feature extraction module comprises:
the image size adjusting submodule is used for reducing the user image to a preset size by using a preset image difference algorithm to obtain an image to be processed;
the gray level calculation submodule is used for converting the image to be processed into a gray level picture;
the image transformation submodule is used for carrying out discrete cosine transformation on the gray level picture to obtain a two-dimensional matrix;
the Hash value extraction submodule is used for converting the two-dimensional matrix into a one-dimensional array; and serializing the one-dimensional array into a character string, and taking the character string as an image characteristic value corresponding to the user image.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the image detection-based online supervision method according to any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements an online supervision method based on image detection according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910759750.XA CN110598754A (en) | 2019-08-16 | 2019-08-16 | Online monitoring method, device and equipment based on image detection and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910759750.XA CN110598754A (en) | 2019-08-16 | 2019-08-16 | Online monitoring method, device and equipment based on image detection and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110598754A true CN110598754A (en) | 2019-12-20 |
Family
ID=68854613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910759750.XA Pending CN110598754A (en) | 2019-08-16 | 2019-08-16 | Online monitoring method, device and equipment based on image detection and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598754A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651858A (en) * | 2020-09-23 | 2021-04-13 | 武汉铁路职业技术学院 | Online learning supervision auxiliary system |
| WO2022022493A1 (en) * | 2020-07-30 | 2022-02-03 | 北京嘀嘀无限科技发展有限公司 | Image authenticity determination method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105243378A (en) * | 2015-11-13 | 2016-01-13 | 清华大学 | Method and device of living body face detection on the basis of eyes information |
| CN107657629A (en) * | 2017-10-27 | 2018-02-02 | 广东工业大学 | The tracking and tracking system of a kind of target |
| CN108346191A (en) * | 2018-02-06 | 2018-07-31 | 中国平安人寿保险股份有限公司 | Work attendance method, device, computer equipment and storage medium |
| CN109344676A (en) * | 2018-11-22 | 2019-02-15 | 福州图腾易讯信息技术有限公司 | A kind of automatic sensing triggering method and its system based on hash algorithm |
-
2019
- 2019-08-16 CN CN201910759750.XA patent/CN110598754A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105243378A (en) * | 2015-11-13 | 2016-01-13 | 清华大学 | Method and device of living body face detection on the basis of eyes information |
| CN107657629A (en) * | 2017-10-27 | 2018-02-02 | 广东工业大学 | The tracking and tracking system of a kind of target |
| CN108346191A (en) * | 2018-02-06 | 2018-07-31 | 中国平安人寿保险股份有限公司 | Work attendance method, device, computer equipment and storage medium |
| CN109344676A (en) * | 2018-11-22 | 2019-02-15 | 福州图腾易讯信息技术有限公司 | A kind of automatic sensing triggering method and its system based on hash algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 黄秋儒: "《数字全景技术原理与应用》", 武汉大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022022493A1 (en) * | 2020-07-30 | 2022-02-03 | 北京嘀嘀无限科技发展有限公司 | Image authenticity determination method and system |
| CN112651858A (en) * | 2020-09-23 | 2021-04-13 | 武汉铁路职业技术学院 | Online learning supervision auxiliary system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232369B (en) | Face recognition method and electronic equipment | |
| CN110225299B (en) | Video monitoring method and device, computer equipment and storage medium | |
| CN110366001B (en) | Method and device for determining video definition, storage medium and electronic device | |
| CN1480902A (en) | Invalid registering preventer of personal authentication system | |
| CN110598754A (en) | Online monitoring method, device and equipment based on image detection and storage medium | |
| CN111814776B (en) | Image processing method, device, server and storage medium | |
| CN109996063B (en) | Video image screen splash detection method and device, computer equipment and storage medium | |
| CN108961209B (en) | Pedestrian image quality evaluation method, electronic device and computer readable medium | |
| CN110674834A (en) | Geo-fence identification method, device, equipment and computer-readable storage medium | |
| CN111091146A (en) | Image similarity obtaining method and device, computer equipment and storage medium | |
| CN112073713B (en) | Video leakage test method, device, equipment and storage medium | |
| CN114095722A (en) | Definition determining method, device and equipment | |
| CN111586427B (en) | Anchor identification method and device for live broadcast platform, electronic equipment and storage medium | |
| CN111310832A (en) | Picture duplicate checking method and system | |
| CN116645530A (en) | Construction detection method, device, equipment and storage medium based on image comparison | |
| CN109996062B (en) | Video image quality detection method and device, computer equipment and storage medium | |
| CN110896475A (en) | Display terminal channel switching detection method and device | |
| CN110213457B (en) | Image transmission method and device | |
| CN112738527A (en) | Video decoding detection method and device, electronic equipment and storage medium | |
| CN112257498A (en) | Construction and detection method and device of vehicle inspection code detection model | |
| Farinella et al. | On blind source camera identification | |
| CN111277724A (en) | Detection method and device for abnormal operation application, electronic equipment and storage medium | |
| CN113628089A (en) | Image processing method, image processing device, storage medium and computer equipment | |
| JPWO2006008992A1 (en) | Web site connection method using portable information communication terminal with camera | |
| CN111679988B (en) | Face recognition system testing method and device and related 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 |
Application publication date: 20191220 |