CN110751500A - Processing method and device for sharing pictures, computer equipment and storage medium - Google Patents
Processing method and device for sharing pictures, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110751500A CN110751500A CN201910841756.1A CN201910841756A CN110751500A CN 110751500 A CN110751500 A CN 110751500A CN 201910841756 A CN201910841756 A CN 201910841756A CN 110751500 A CN110751500 A CN 110751500A
- Authority
- CN
- China
- Prior art keywords
- image
- poster
- target
- activity
- sharing
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims description 17
- 230000000694 effects Effects 0.000 claims abstract description 170
- 238000012795 verification Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 26
- 238000003708 edge detection Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 229910052704 radon Inorganic materials 0.000 claims description 3
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 12
- 238000001514 detection method Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 235000013618 yogurt Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for processing a shared picture, computer equipment and a readable storage medium. The method comprises the steps of receiving a shared image to be audited, and extracting an effective area in the shared image to be audited to obtain a basic image; if the poster image is identified from the basic image, extracting a target sharer identifier, a target sharing duration and the poster image from the basic image; extracting a target verification image with the similarity meeting a preset threshold value with the poster image from a activity database, and acquiring target activity information corresponding to the target poster image; acquiring a sharer account corresponding to the target sharer identification, and judging whether the activity reward of the activity is issued to the sharer account or not; and if the target sharing time length is not less than the preset activity time length, the activity reward is issued to the sharer account according to the preset reward mode. By adopting the method, the purpose of accurately positioning the real sharer sharing the poster is realized, and the reward is issued to the account of the real sharer.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a method and an apparatus for processing a shared picture, a computer device, and a storage medium.
Background
Social platforms such as WeChat and microblog are used by more and more users, product or activity promotion is carried out through social platforms such as WeChat or microblog, the current mainstream trend is reached, the users click sharing links to automatically generate activity posters, and then the activity posters are shared with social platforms such as WeChat friend circles or microblog, so that more users can know about the promotion activity through the activity posters.
In order to encourage users to share and popularize, sharing rewards are generally set, namely, after the users share successfully according to the specified requirements, the users can obtain the rewards provided by a marketing party so as to increase the popularization enthusiasm of the users, after the users share, the users capture the sharing pages, send the captured images to the marketing party for auditing, and send the rewards to the account of the users after the audits are passed.
In the traditional technology, after a server receives a sharing screenshot sent by a user, the server identifies the sharing screenshot to obtain an incentive mode in the information of the sharing activity, then awards of the activity are issued to an account of a sharer, the identification mode of the sharing screenshot is too single, the identification accuracy of a real sharer is not high, the situation that the sharing screenshot of the sharer is stolen to obtain the incentive is easy to occur, whether the sharing behavior is effective or not cannot be accurately identified, sharing is performed for obtaining the incentive, the situation that the sharing information is immediately deleted after the incentive is obtained is caused, and the situation that effective sharing in the true sense cannot be achieved.
Disclosure of Invention
The embodiment of the invention provides a processing method and device for sharing pictures, computer equipment and a storage medium, and aims to solve the technical problem that in the prior art, the reward is falsely claimed due to low identification accuracy of real sharers.
A processing method of a shared picture comprises the following steps:
receiving a shared image to be audited, and extracting an effective area in the shared image to be audited to obtain a basic image;
if the poster image is identified from the basic image, extracting a target sharer identifier, a target sharing duration and the poster image from the basic image, wherein the sharing duration is the duration from the sharing activity to the uploading of the screenshot of the user;
extracting verification images with the similarity meeting a preset threshold value with the poster image from a activity database, taking the verification images as target poster images, and acquiring target activity information corresponding to the target poster images, wherein the target activity information comprises a preset sharing time length and a preset rewarding mode, and each verification image corresponds to one activity;
acquiring a sharer account corresponding to the target sharer identification, and judging whether the activity reward of the activity is issued to the sharer account or not;
and if the activity reward is not issued to the sharer account and the target sharing time length is not less than the preset activity time length, the activity reward is issued to the sharer account according to the preset reward mode. A processing apparatus for sharing pictures, comprising:
the image extraction module is used for receiving the shared image to be audited and extracting the effective area in the shared image to be audited to obtain a basic image;
the target information extraction module is used for extracting a target sharer identifier, a target sharing duration and a poster image from the basic image if the poster image is identified from the basic image, wherein the sharing duration is the duration from the sharing activity to the uploading of the screenshot of the user;
the activity matching module is used for extracting verification images with similarity meeting a preset threshold value with the poster image from an activity database, taking the verification images as target poster images, and acquiring target activity information corresponding to the target poster images, wherein the target activity information comprises preset sharing duration and a preset rewarding mode, and each verification image corresponds to one activity;
the sharer information identification module is used for acquiring a sharer account corresponding to the target sharer identification and judging whether the activity reward of the activity is issued to the sharer account or not;
and the sharing duration judging module is used for issuing the activity reward to the sharer account according to the preset reward mode if the activity reward is not issued to the sharer account and the target sharing duration is not less than the preset activity duration.
A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the above processing method for sharing pictures when executing the computer program.
A computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the above processing method for sharing pictures are realized.
According to the processing method and device for the sharing pictures, the computer equipment and the readable storage medium, whether the sharer meets the condition of activity reward is judged by judging the sharing time of the sharer sharing the activity, and the situation that the sharer uses the sharing poster with insufficient sharing condition to receive the reward is avoided; in addition, rewards are issued according to sharer accounts corresponding to sharer identifications, so that real sharers sharing posters can be accurately positioned, and the condition that interests of the real sharers are damaged due to the fact that other persons are embezzled to share the posters to obtain more sharing rewards to take screenshot pretend rewards is avoided; finally, whether the activity reward is issued to the account of the sharer is determined by judging whether the reward is issued to the account of the sharer or not, so that the situation that the sharer repeatedly obtains the reward by using the used sharing screenshot can be avoided; therefore, besides identifying the sharer identification to ensure that the reward is issued to the account of the actual sharer, the sharer is ensured to obtain the reward according to the sharing screenshot, and the purpose of rewarding the sharer for one time according to the preset reward rule is achieved.
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 a processing method for sharing pictures according to an embodiment;
FIG. 2 is a flowchart illustrating a method for processing a shared picture according to an embodiment;
FIG. 3 is a flowchart illustrating step 202 of the method for processing a shared picture according to an embodiment;
fig. 4 is a flowchart illustrating step 204 of the method for processing a shared picture according to an embodiment;
FIG. 5 is another flowchart illustrating step 204 of the method for processing a shared picture according to an embodiment;
FIG. 6 is a flowchart illustrating step 404 of the method for processing a shared picture according to an embodiment;
FIG. 7 is a flowchart illustrating step 206 of the method for processing a shared picture according to an embodiment;
FIG. 8 is a flowchart illustrating a method for processing a shared picture according to another embodiment;
FIG. 9 is a diagram illustrating a processing device for sharing pictures according to an embodiment;
fig. 10 is a schematic diagram illustrating a shared image to be checked in the method for sharing a picture according to an embodiment;
FIG. 11 is a diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. 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 processing method for sharing pictures provided by the embodiment of the invention can be applied to the application environment shown in fig. 1. Wherein, the terminal 102 communicates with the server 104 through the network. The server 104 receives the shared image to be audited sent by the terminal 102, processes and analyzes the image to be audited to obtain a target sharer identifier, a target sharing duration and a poster image contained in the image, and then obtains a check image with similarity to the poster image meeting a preset threshold value in a movable database as a target poster image; and after the information of the activity is acquired from the target poster image, judging whether the sharer account corresponding to the target sharer mark meets the condition of reward issuing or not according to the comparison between the acquired target sharer mark and the information of the activity, and if so, issuing the reward to the sharer account. Therefore, the real sharer who shares the screenshot can be accurately positioned, and the condition that the sharing screenshot of the sharer is embezzled to falsely receive the reward is avoided. The terminal 102 and the server 104 are connected through a network, the network may be a wired network or a wireless network, the terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a method for processing a shared picture is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The to-be-audited shared image is generally a screenshot of a activity sharing interface sent by a user to a server through a terminal or an automatically stored picture, as shown in fig. 10, the to-be-audited shared image 002 includes activity content, an activity poster image 004, a sharer identifier 006, and plaintext information or encrypted information such as sharing time 008 when the user uploads the activity to the server after sharing the activity.
Specifically, after the user shares the active poster, screenshot is performed on the shared page or a key on the shared page is clicked to automatically save the shared page, and the shared page is sent to a verification window of the server. And the verification window of the server receives the screenshot through a network transmission protocol, and the screenshot is used as an image to be checked.
It should be understood that the share screen shot contains the active poster and the time of the share or the time interval between the time of the share and the time of the screen shot.
For example, in this embodiment, the verification window of the server is a wechat public number window, after the user captures the shared page, the user opens the public number window and sends the captured image to the server from the window, and the server receives the captured image and obtains the wechat identifier of the user.
The effective area refers to characters and images related to the activity in the image to be audited, and the effective area can be judged by identifying whether sharer identification areas which can be obtained on different images on the shared screenshot exist.
And 204, if the poster image is identified from the basic image, extracting the target sharer identification, the target sharing duration and the poster image from the basic image, wherein the sharing duration is the duration from the sharing activity to the uploading of the screenshot of the user.
After a general user shares a campaign, the client automatically generates a campaign poster, the campaign poster comprises a poster image and information of a sharer, then the user clicks to share the campaign poster to an application, and after a certain time, the sharing information is captured and uploaded, and the server takes the received captured image as a sharing image to be audited. However, there are cases where a user does not have a poster image in a event poster generated after sharing an event, and there are cases where the user may have a line character, a picture of a picture publicity phrase unrelated to the event, or the like. At this time, the obtained basic image needs to be preliminarily recognized, and if the poster image exists in the basic image, the target sharer identifier, the target sharing duration and the poster image are extracted from the basic image.
The target sharer identification may be an identity identification of the user in the social platform corresponding to the identity of the real sharer, such as a WeChat identification, a microblog identification, a bean identification, and the like of the user, and may be a string of characters or a string of identification codes. Specifically, through the activity shared by different social platforms, the social platform identifier has different embodiments, which may be a two-dimensional code, a barcode, a share list number, and the like. In different sharing modes, the font, the position information, the sharing duration/the position of the sharing time of the sharer identifier on the basic image are different. Determining a region corresponding to a sharer identifier and a region corresponding to sharing duration in a basic image, identifying characters, numbers or symbols in the regions to obtain the sharer identifier and the sharing duration, taking the sharer identifier as a target sharer identifier, and taking the sharing duration as the target sharing duration; meanwhile, whether the basic image contains the poster area or not can be determined in an OCR recognition mode, and the poster image of the sharing activity is recognized from the poster area.
And step 206, extracting verification images with similarity meeting a preset threshold value with the poster image from the activity database to serve as target poster images, and acquiring target activity information corresponding to the target poster images, wherein the target activity information comprises preset sharing time and a preset rewarding mode, and each verification image corresponds to one activity.
In the same time period, the server may have a plurality of sharing activities, each sharing activity corresponds to one activity poster, and therefore, if activity information of the poster image is to be acquired from the server according to the poster image, the activity information corresponding to the poster needs to be indexed.
And the server side directly searches a check image with the similarity meeting a preset threshold value with the poster image from the activity database through a Hash algorithm to serve as the target poster image.
Further, in this embodiment, the server may also search the activity database for a check image whose similarity with the poster image satisfies a preset threshold, and then use a set of check images whose similarity satisfies the preset threshold as the comparison image set. It should be noted that each verification graph corresponds to one piece of activity information in the activity database.
Preferably, the manner of obtaining the comparison image set may be a hash algorithm, and if the hamming distance between the verification image and the poster image in the activity database meets a preset threshold, the verification image is considered to be in accordance with the requirement, and the verification image in accordance with the requirement may be classified into the comparison image set.
Of course, the comparison image set of the poster image may also be obtained by obtaining a preset number of verification images from the activity database that are closer to the current time. Specifically, how long the current time is, may be preset according to the type of the activity and the activity time, for example, if the activity is a certain yogurt promotional activity, the latest time may be set to be within one week, and the verification image in the latest week or two weeks is obtained from the activity database to obtain the comparison image set.
Preferably, for a preset number of verification images, the present embodiment determines the sequence of the verification images according to the time difference from the current time, that is, when the verification image corresponding to the activity closest to the current time is located at the first position of the comparison image set.
After the comparison image set is obtained, a check image with the matching degree meeting the preset value with the poster image can be searched from the comparison image set in a picture approximate searching mode to serve as a target check image.
In this embodiment, if a verification image whose hamming distance from the poster image meets a preset threshold exists in the comparison image set, the verification image is considered as a target poster image, target activity information corresponding to the target poster image is indexed from an activity database according to the target poster image, and a preset sharer identifier and a preset sharing duration of the poster image are obtained from the target activity information.
Similar verification of poster images with verification images takes place in ways including, but not limited to: perceptual Hash Algorithm (PHA), Structural Similarity (SSIM) histogram method and grayscale-based template matching algorithm, feature-based matching algorithm and relationship-based matching algorithm, etc.
Preferably, the present embodiment employs a perceptual hashing algorithm to perform a similar comparison of two images, i.e., by generating a "fingerprint" string for each image and then comparing the fingerprints of the different images. The closer the result is, the more similar the images are, and if the value of the similarity exceeds a preset threshold, the two images can be determined to be similar.
The method comprises the steps of firstly obtaining a comparison image set of the poster images, searching a check image which is most matched with the poster images from the comparison image set to serve as a target poster image, increasing the searching speed of the target poster image, obtaining the comparison image set through a Hash algorithm, and matching the most similar check image through a template matching degree algorithm based on gray scale, so that the search of the check image is more accurate.
Specifically, the specific time obtained in the base image may be only the specific time when the sharer shares the activity, for example, the specific time for sharing is: 12 o' clock 05 points in 2019, 4, 16 and then the server cannot directly know the specific data of the sharing time length, and the server can obtain the difference between the time of uploading the sharing screenshot by the sharer and the specific time of sharing the activity to obtain the sharing time length, and then the sharing time length is used as the preset sharing time length.
However, the time for uploading the shared image is not necessarily the time for the sharer to capture the image, so the sharing time obtained by the method is not accurate. In order to solve the above problem, in this embodiment, the screenshot time of the shared screenshot obtained from the image to be audited or the generation time of the shared picture may be obtained, and then the difference between the screenshot time and the sharing time (generation time) of the shared poster may be used as the sharing duration.
Specifically, the generation time of the image to be audited may be obtained by a getItemType () method in Python or an ExifInterface in Java.
And step 208, acquiring a sharer account corresponding to the target sharer identification, and judging whether the activity rewards of the activities are issued to the sharer account.
And obtaining a sharer account corresponding to the target sharer identifier by taking the target sharer identifier as an index, wherein the sharer account can be a payment purse, a WeChat purse, a microblog purse and the like of the user, retrieving the sharer account or the identifier information of the sharer account from an account database according to the obtained sharer account information, and if the sharer account is not searched from the account database, determining that the activity reward is not issued to the sharer account. And if the sharer account is searched from the account database, the activity reward is considered to be released to the sharer account, the activity reward is not released to the sharer account any more, and a prompt of releasing the reward is sent to the user.
If the sharer account is not searched from the account database and the target sharing time length is not less than the preset activity time length, the activity reward of the activity is not issued to the sharer account, and the activity reward is issued to the sharer account according to the preset reward mode.
Further, after the activity reward is issued to the sharer account, the sharer identification is stored in the account database for marking, wherein the mark is that the reward of the activity is issued to the sharer account corresponding to the sharer identification (if the preset reward rule of the activity is that only one reward is given to each sharer account), or the nth reward (for example, the preset reward rule is divided into multiple rewards according to different time periods), the technical problem that the reward is falsely led can be further solved through the step. The sharer identifications corresponding to different sharing platforms are different, and the sharer accounts corresponding to the sharer identifications are also different.
In the embodiment, whether the sharer meets the condition of activity reward is judged by judging the sharing time of the sharer sharing the activity, so that the situation that the sharer uses the sharing poster with insufficient sharing condition to draw the reward is avoided; in addition, rewards are issued according to sharer accounts corresponding to sharer identifications, so that real sharers sharing posters can be accurately positioned, and the condition that interests of the real sharers are damaged due to the fact that other persons are embezzled to share the posters to obtain more sharing rewards to take screenshot pretend rewards is avoided; finally, whether the activity reward is issued to the account of the sharer is determined by judging whether the reward is issued to the account of the sharer or not, so that the situation that the sharer repeatedly obtains the reward by using the used sharing screenshot can be avoided; therefore, besides identifying the sharer identification to ensure that the reward is issued to the account of the actual sharer, the sharer is ensured to obtain the reward according to the sharing screenshot, and the purpose of rewarding the sharer for one time according to the preset reward rule is achieved.
In one embodiment, as shown in FIG. 3, step 202, comprises:
and 302, preprocessing the image to be audited to obtain a characteristic image to be audited.
Specifically, before extracting the effective region from the shared image to be audited, image preprocessing may be performed on the shared image to be audited to obtain a feature image to be audited.
The image preprocessing includes, but is not limited to, a sharpening process, a graying process, a perspective transformation process, a binarization process, and the like. Since the content image may contain a plurality of colors, the colors themselves are very susceptible to the influence of factors such as illumination, and the colors of similar objects are changed, the colors themselves are difficult to provide key information, and thus, the content image needs to be grayed to obtain a grayscale map so as to eliminate interference and reduce the complexity of the image and the information processing amount.
The gray processing is a process of converting a color picture into a gray picture, and aims to improve the image quality and make the display effect of the picture clearer. Grayscale processing includes, but is not limited to: component, maximum, average, weighted average, and the like.
The sharpening process is to compensate the outline of the picture, enhance the edge and the gray level jump part of the picture, make the picture clear, and is divided into a spatial domain process and a frequency domain process, and the sharpening process is to highlight the edge and the outline of the ground object on the picture or the characteristics of some linear target elements.
And 304, acquiring an effective area in the characteristic image to be audited according to a preset template as a basic image, wherein the preset template is a condition for extracting the effective area in the characteristic image to be audited.
Extracting an effective area from an image obtained after image preprocessing according to a preset template, and taking the obtained effective area as a basic image, wherein the preset template is preset and is used for screenshot files of each sharing message through two ends of a boundary mark between the sharing messages, dividing different messages contained in the shared image to be audited, taking the part containing the complete sharing message as an identification area, taking other parts as non-identification areas, and removing the non-identification areas in the preprocessed shared image to be audited to obtain the basic image.
Specifically, the preset template includes two lines with preset lengths and thicknesses as boundary lines between different shared messages, the image to be audited shown in fig. 10 is divided by a line segment between two shared messages, an identification area from which a top title bar and a bottom irrelevant message are removed is obtained, the identification area is used as a base image, and the removed portion is a non-identification area.
According to the method and the device, the shared image to be audited is preprocessed before the non-identification area is eliminated, so that the characteristics of the shared image to be audited are more obvious, and the identification accuracy of the effective area is improved.
In one embodiment, as shown in FIG. 4, step 204 comprises:
and 402, positioning characters in the basic image to obtain a character area and a poster area, identifying sharing information in the character area, and obtaining a target sharer identifier and a target sharing duration.
And performing character positioning on the standard image through a scene text detection algorithm, confirming character areas in the basic image, and determining a sharer identification area, a sharing duration area and a poster area from the character areas according to a preset template.
Specifically, because the text region in the base image obtained by the shared screenshot shared in the same sharing manner has a certain frame, but each text region is not fixed, for example, the lower left corner of the base image is the sharer identifier, the sharing time is below the sharer identifier, and the character length of the sharer identifier and the character length of the sharing time are not fixed, so that the positions of the centers of the text regions on the base image are not the same, and therefore, after the image is preprocessed to obtain the base image, the text region of the sharer identifier and the text region of the sharing time duration in the base image need to be determined, so as to perform text recognition.
The text area determination method includes, but is not limited to: hough Transform (Hough Transform) algorithm, Hidden Markov Model (HMM) based character recognition algorithm, region feature extraction (MSER) algorithm, and scene text detection (Connectionist textforward Network) algorithm.
Preferably, the present embodiment adopts a scene text detection algorithm to determine the text region in the base image, and the implementation manner is as follows: training a basic image by using a Convolutional Neural Network (CNN) model to obtain a depth feature of the image; predicting character edges according to the depth features and a text line construction algorithm (Side reference), and putting characters with the character edges in the same line into the same rectangular frame according to the rectangular frame with a preset size; the rectangular frames are stringed into a sequence and input into a Recurrent Neural Networks (RNN) model for training, and finally, the training result is regressed by using a full connection layer to obtain a correct character edge, and the correct character edge is connected into a line, so that a character area in the basic image is obtained.
Understandably, when the scene text detection algorithm performs character positioning, the positioning is performed based on line level, that is, the position information of the rectangular box corresponding to each line is returned.
It should be noted that, in the present embodiment, there may be one or more target text regions, which may be determined according to actual detection results, and the present invention is not limited thereto.
Further, a pre-trained long-and-short-term memory neural network model is adopted to identify the sharer identification area and the sharing duration area, so that text information corresponding to the sharer identification area is obtained and is used as a sharer identification, and text information corresponding to the sharing duration area is obtained and is used as sharing duration;
specifically, the pre-trained long-and-short time memory neural network model is adopted to identify the obtained images of the sharer identification area and the sharing time length area, and text information contained in the images of the sharer identification area and the sharing time length area is obtained.
Among them, the long-short term memory (LSTM) network is a time recursive neural network, and is suitable for processing and predicting important events with time series and relatively long time series intervals and delays.
It should be noted that, when the number of the text regions obtained by the scene text detection algorithm in step S32 is n, it is necessary to sequentially identify each text region to obtain n pieces of text information, where n is a positive integer greater than 1. Preferably, in this embodiment, the value of n is 2, that is, a text region corresponding to one sharer identifier and a text region corresponding to one sharing duration may also be identified by adding other text regions according to actual requirements, which is not limited herein.
Specifically, when text recognition is performed through the long-term memory neural network model, the long-term memory neural network model needs to be trained in advance. The specific training steps of the long-time memory neural network model are as follows:
sequentially labeling training sample images in a training set, inputting the labeled training sample images into a convolutional neural network-long-and-short-term memory neural network for training, and updating network parameters of the convolutional neural network-long-and-short-term memory neural network by adopting a time sequence classification algorithm and an Adam optimizer so as to obtain the long-and-short-term memory neural network model.
The time sequence classification algorithm (CTC) is used for solving the problem of a time sequence with uncertain alignment relation between input features and output labels, and is an algorithm capable of optimizing model parameters and aligning a segmentation boundary end to end.
The shared image to be audited obtained by screenshot can also include an area with a recommendation reason and other blank areas besides the poster area, and these non-poster images can interfere with subsequent poster identification, so that in order to improve the accuracy of subsequent poster identification, an edge inspection algorithm is required to find out the upper boundary of the poster and the lower boundary of the poster in the poster area, so as to determine the poster range in the poster area and obtain the poster image.
Where edge detection algorithms are algorithms used to perform edge detection, which is a fundamental problem in image processing and computer vision, in embodiments of the present invention the purpose of edge detection is to identify points in the poster image where changes in brightness are significant, i.e. points at the poster boundary, where significant changes in image properties typically reflect significant events and changes in properties, including but not limited to: discontinuities in depth, surface orientation discontinuities, material property changes, scene lighting changes, and the like.
The edge of the image refers to a region in which the gray scale of the image changes rapidly, and the change of the gray scale of the image can be reflected by the gradient of the gray scale distribution.
Commonly used edge detection algorithms include, but are not limited to: a Sobel operator (Sobel operator) edge detection algorithm, a laplacian operator edge detection algorithm, a Roberts Cross edge detection (Roberts Cross operator) algorithm, a Canny multi-level edge detection algorithm, and the like.
Preferably, the edge detection algorithm employed by the embodiments of the present invention is a Canny multi-stage edge detection algorithm.
It is worth mentioning that the upper boundary of the poster and the lower boundary of the poster are two line segments according to the edge detection algorithm. That is, the upper boundary of the resulting poster includes two vertices, left and right, and the lower boundary of the resulting poster includes two vertices, left and right.
The embodiment can improve the recognition precision of the text and the poster image and improve the recognition efficiency through the steps.
In one embodiment, as shown in fig. 5, step 204 further includes:
and 502, positioning characters in the basic image to obtain a poster area, and acquiring the poster image from the poster area in an edge detection mode.
The character positioning can be performed through a scene text detection algorithm, and when the scene text detection algorithm performs the character positioning, the positioning is performed based on line levels, that is, the position information of the rectangular box corresponding to each line is returned.
And step 504, identifying the two-dimensional code in the poster image to obtain the link information. The two-dimensional Code in the embodiment can be a two-dimensional bar Code, and the two-dimensional Code can be divided into a stacked two-dimensional bar Code, a row-type two-dimensional bar Code and a matrix two-dimensional bar Code; the two-dimensional code may also be a QR code. When the two-dimensional code in the poster is identified, the information in the two-dimensional code can be identified through the existing two-dimensional code identification technology.
Step 508, inquiring sharing information corresponding to the sharing identification information from a preset database, extracting sharer identifications and sharing time in the sharing information, determining sharing duration according to the sharing time, taking the sharer identifications as target sharer identifications, and taking the sharing duration as the target sharing duration.
The preset database comprises activity information corresponding to the poster images, and can be an activity database or other databases which store the activity information like the activity database.
The sharing time (sharing duration) in the basic image is directly the two-dimensional code as the carrier, and the server can directly acquire the sharing time of the sharing person identifier and the sharing person in the two-dimensional code through the two-dimensional code recognition technology, so that the recognition efficiency is improved.
In one embodiment, as shown in FIG. 6, step 404 includes:
and step 602, determining the upper boundary of the poster area and the lower boundary of the poster area through an edge detection algorithm, and obtaining the poster image to be determined according to the upper boundary of the poster area and the lower boundary of the poster area.
Specifically, noise removal is carried out on the image in the poster area through Gaussian blur, and a noise-removed poster image is obtained; calculating gradient values of the denoised poster image in the horizontal direction and the vertical direction by using a preset gradient operator to obtain an initial gradient value set; performing edge refinement processing on the initial gradient value set by adopting a non-maximum value suppression mode to obtain a gradient edge with one pixel width; filtering weak edge points in the gradient edge by using a preset double threshold value to obtain strong edge points in the gradient edge; from the strong edge points, an upper boundary of the poster area and a lower boundary of the poster area are determined.
Then, the obtained upper boundary of the poster area and the lower boundary of the poster area are connected, that is, the left vertex of the upper boundary of the poster area is connected with the left vertex of the lower boundary of the poster area, the right vertex of the upper boundary of the poster area is connected with the right vertex of the lower boundary of the poster area, so that a quadrangle is obtained, and the image in the quadrangle range is used as the range image of the poster.
And step 604, performing inclination correction on the poster image to be determined by adopting Radon transformation to obtain the corrected poster image.
Specifically, due to the influence of some factors, the acquired initial poster image has a certain offset inclination, and the acquired range image also has an inclination.
The embodiment highlights the edge characteristics of the picture by denoising the poster area, and improves the identification precision of the poster image.
In one embodiment, as shown in FIG. 7, step 206, comprises:
and step 702, normalizing the poster image to obtain a reduced image of the poster image in the same ratio.
Specifically, the poster image is normalized to 8 × 8 size to obtain a reduced image of 64 pixels, and through the step, the details of the image can be removed, only basic information such as structure/brightness and the like is retained, and image differences caused by different sizes/proportions are abandoned.
And converting the scaled-down image into 64-level gray scale to obtain a simplified image with 64 colors in total for all pixel points.
And step 706, calculating a gray level average value of the simplified image, comparing the gray level value of each pixel of the simplified image with the gray level average value to obtain a pixel identifier of each pixel of the simplified image, and using the obtained pixel identifier as the target image fingerprint of the poster image.
Specifically, the gray-scale average value of the simplified image is calculated, the gray-scale value of each pixel is compared with the gray-scale average value, the pixel with the gray-scale value greater than or equal to the average value is identified as 1, the pixel with the gray-scale value less than the gray-scale average value is identified as 0, a 64-bit integer is formed, and the 64-bit integer is used as the target image fingerprint of the poster image.
At step 708, an image fingerprint of each verification image is obtained from the activity database as a verification image fingerprint.
The image fingerprint of the verification image is stored in a database, and the image fingerprint is the unique identifier of the image obtained by performing hash processing on the image, detecting the content of the image and obtaining the unique identifier of the image.
In this embodiment, the image fingerprint of the poster image is obtained through a hash algorithm, the hamming distance between the image fingerprint of the poster image and the image fingerprint of the verification image is calculated, and if the hamming distance does not exceed a preset threshold value, it is determined that the poster image and the verification image have similarity, so that the purpose of accurately matching the verification image from the activity database as the target verification image for the poster image is achieved.
In an embodiment, as shown in fig. 8, after step 202 and before step 208, the method for processing a shared picture further includes:
After a general user shares a campaign, the client automatically generates a campaign poster, the campaign poster comprises a poster image and information of a sharer, then the user clicks to share the campaign poster to an application, and after a certain time, the sharing information is captured and uploaded, and the server takes the received captured image as a sharing image to be audited. However, there are cases where a user does not have a poster image in a event poster generated after sharing an event, and there are cases where the user may have a line character, a picture of a picture publicity phrase unrelated to the event, or the like. At this time, the obtained basic image needs to be preliminarily recognized, and if the poster image exists in the basic image, the target sharer identifier, the target sharing duration and the poster image are extracted from the basic image.
If the activity poster does not have a poster image, the client generally generates an image unique identification code according to information such as a sharer identifier of the user, activity information corresponding to the activity, a specific time point of the activity sharing and the like. The image unique identification code can be embodied in the form of a two-dimensional code, and can also be a character string consisting of characters, numbers and other symbols. Each image unique identification code corresponds to a movable poster shared by sharers and is generally not repeated.
And step 804, identifying the target sharer identification and the index number of the activity in the image unique identification code, and acquiring the activity information of the activity from the activity database according to the index number to serve as the target activity information.
The activity information of the activity in the activity database corresponding to the index number is stored in the image unique identification code in the form of the index number, so that the complexity of the image unique identification code can be reduced.
According to the method and the device, the picture identification rate is improved by directly identifying the image unique identification code of the sharing poster in the sharing picture, whether the sharer meets the condition of activity reward is judged by judging the sharing duration of the sharing activity of the sharer, and the condition that the sharer uses the sharing poster which is not enough in sharing condition to receive the reward is avoided; in addition, rewards are issued according to sharer accounts corresponding to sharer identifications, so that real sharers sharing posters can be accurately positioned, and the condition that interests of the real sharers are damaged due to the fact that other persons are embezzled to share the posters to obtain more sharing rewards to take screenshot pretend rewards is avoided; finally, whether the activity reward is issued to the account of the sharer is determined by judging whether the reward is issued to the account of the sharer or not, so that the situation that the sharer repeatedly obtains the reward by using the used sharing screenshot can be avoided; therefore, besides identifying the sharer identification to ensure that the reward is issued to the account of the actual sharer, the sharer is ensured to obtain the reward according to the sharing screenshot, and the purpose of rewarding the sharer for one time according to the preset reward rule is achieved.
It should be understood that although the various steps in the flowcharts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
In an embodiment, as shown in fig. 9, a processing device for sharing pictures is provided, where the processing device for sharing pictures corresponds to the processing method for sharing pictures in the foregoing embodiments one to one. The processing device for sharing pictures comprises an image extraction module 902, a target information extraction module 904, an activity matching module 906 and a sharer information identification module 906, wherein:
the image extraction module 902 is configured to receive the shared image to be audited, and extract an effective area in the shared image to be audited to obtain a basic image;
and the target information extraction module 904 is configured to, if the poster image is identified from the base image, extract a target sharer identifier, a target sharing duration and the poster image from the base image, where the sharing duration is a duration from a sharing activity to uploading a screenshot of a user.
And the activity matching module 906 is configured to extract, from the activity database, check images whose similarity to the poster image meets a preset threshold value, serve as target poster images, and acquire target activity information corresponding to the target poster images, where the target activity information includes a preset sharing duration and a preset rewarding mode, and each check image corresponds to one activity.
The sharer information identifying module 908 is configured to obtain a sharer account corresponding to the target sharer identifier, and determine whether the active activity reward is issued to the sharer account.
The sharing duration determining module 910 is configured to, if the activity reward is not issued to the sharer account and the target sharing duration is not less than the preset activity duration, issue the activity reward to the sharer account according to a preset reward mode.
Further, the image extraction module 902 includes:
the image preprocessing submodule 9022 is configured to preprocess the image to be checked to obtain a feature image to be checked;
and the basic image obtaining submodule 9024 is configured to obtain an effective region in the feature image to be audited according to a preset template, where the preset template is a condition for extracting the effective region in the feature image to be audited.
Further, the target information extraction module 904 includes:
the sharing identifier obtaining sub-module 9042 is configured to position characters in the basic image to obtain a character area and a poster area, identify sharing information in the character area, and obtain a target sharer identifier and a target sharing duration;
and the poster image acquisition sub-module 9044 is used for acquiring poster images from the poster area in an edge detection mode.
Further, the poster image acquisition sub-module 9044 further includes:
the image edge detection unit 9044a is used for determining an upper boundary of the poster area and a lower boundary of the poster area through an edge detection algorithm, and obtaining a poster image to be determined according to the upper boundary of the poster area and the lower boundary of the poster area;
and the inclination correction unit 9044b is configured to perform inclination correction on the poster image to be determined by adopting radon transform, so as to obtain a corrected poster image.
Further, the target information extracting module 904 further includes:
the character positioning sub-module 9046 is configured to position characters in the basic image to obtain a poster area, and acquire the poster image from the poster area in an edge detection manner;
and the link acquisition sub-module 9048 is used for identifying the two-dimensional code in the poster image to obtain link information.
And the link analysis submodule 9050 is used for analyzing the link information to obtain the shared identification information in the link information.
The information identifying sub-module 9052 is configured to query sharing information corresponding to the sharing identification information from a preset database, extract a sharer identifier and sharing time in the sharing information, determine sharing duration according to the sharing time, use the sharer identifier as a target sharer identifier, and use the sharing duration as a target sharing duration.
Further, the activity matching module 906 includes:
and the normalization processing sub-module 9062 is used for performing normalization processing on the poster image to obtain a scaled-down image of the poster image.
And the gray processing submodule 9064 is used for performing gray processing on the reduced image with the same ratio to obtain a simplified image.
And the image fingerprint acquisition sub-module 9066 is configured to calculate a gray-scale average value of the simplified image, compare the gray-scale value of each pixel of the simplified image with the gray-scale average value, obtain a pixel identifier of each pixel of the simplified image, and use the obtained pixel identifier as a target image fingerprint of the poster image.
A verification image fingerprint obtaining sub-module 9068 is configured to obtain an image fingerprint of each verification image from the active database as a verification image fingerprint.
And the target image acquisition sub-module 9070 is configured to acquire, as a target verification image, a verification image corresponding to a verification image fingerprint of which the hamming distance from the target image fingerprint does not exceed a preset threshold.
Further, the target information extraction module 904 is further configured to, if the poster image is not identified from the base image, obtain a target sharing duration and an image unique identification code of the base image from the base image, where the image unique identification code is a unique identification number of the user-shared activity poster generated by the client according to the target activity information and the target sharer identifier.
Further, the activity matching module 906 is further configured to identify a target sharer identifier in the image unique identifier and an index number of the activity, and acquire activity information of the activity from the activity database according to the index number, as the target activity information.
According to the embodiment, the identity identification and the sharing duration of the sharer contained in the image to be audited are obtained by processing the image to be audited sent by the sharer, then the activity information corresponding to the activity is obtained from the activity database according to the extracted sharer identification, the activity information is verified with the target sharing duration and the sharer account to obtain the real sharer, whether the real sharer is rewarded with the sharer account of the real sharer or not is judged, corresponding processing is carried out according to the judged result, and the situations that the sharing screenshot of the sharer is embezzled to lead the reward and the reward is mistaken are avoided.
For specific limitations of the processing apparatus for sharing pictures, reference may be made to the above limitations on the processing method for sharing pictures, which are not described herein again. All or part of the modules in the processing device for sharing pictures can be 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. 11. 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 database of the computer device is used for storing the data of the verification image and the sharing image. 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 a processing method for sharing pictures.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the processing method for sharing pictures in the foregoing embodiments, such as the steps 202 to 210 shown in fig. 2, or when the processor executes the computer program, the processor implements the functions of the modules/units of the processing apparatus for sharing pictures in the foregoing embodiments, such as the functions of the modules 902 to 910 shown in fig. 9. To avoid repetition, further description is omitted here.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the processing method for sharing pictures in the foregoing embodiments, such as steps 202 to 210 shown in fig. 2, or the processor, when executing the computer program, implements the functions of the modules/units of the processing apparatus for sharing pictures in the foregoing embodiments, such as the functions of modules 902 to 910 shown in fig. 9. 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, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. 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 technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, without departing from the spirit and scope of the present invention, several changes, modifications and equivalent substitutions of some technical features may be made, and these changes or substitutions do not make the essence of the same technical solution depart from the spirit and scope of the technical solution of the embodiments of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. The processing method of the shared picture is characterized by comprising the following steps:
receiving a shared image to be audited, and extracting an effective area in the shared image to be audited to obtain a basic image;
if the poster image is identified from the basic image, extracting a target sharer identifier, a target sharing duration and the poster image from the basic image, wherein the target sharing duration is the duration uploaded by a user from a sharing activity to a screenshot;
extracting verification images with the similarity meeting a preset threshold value with the poster image from a activity database, taking the verification images as target poster images, and acquiring target activity information corresponding to the target poster images, wherein the target activity information comprises a preset sharing time length and a preset rewarding mode, and each verification image corresponds to one activity;
acquiring a sharer account corresponding to the target sharer identification, and judging whether the activity reward of the activity is issued to the sharer account or not;
and if the activity reward is not issued to the sharer account and the target sharing time length is not less than the preset activity time length, the activity reward is issued to the sharer account according to the preset reward mode.
2. The method for processing the shared picture according to claim 1, wherein the extracting the effective area in the shared picture to be audited to obtain a basic picture includes:
preprocessing the image to be audited to obtain a characteristic image to be audited;
and acquiring an effective area in the characteristic image to be audited according to a preset template to be used as a basic image, wherein the preset template is a condition for extracting the effective area in the characteristic image to be audited.
3. The method for processing the shared picture according to claim 1, wherein the extracting a target sharer identifier, a target sharing duration and a poster image from the base image comprises:
positioning characters in the basic image to obtain a character area and a poster area, and identifying sharing information in the character area to obtain a target sharer identifier and a target sharing duration;
and acquiring the poster image from the poster area in an edge detection mode.
4. The method for processing the shared picture according to claim 1, wherein the extracting a target sharer identifier, a target sharing duration and a poster image from the base image further comprises:
positioning characters in the basic image to obtain a poster area, and acquiring a poster image from the poster area in an edge detection mode;
identifying the two-dimensional code in the poster image to obtain link information;
analyzing the link information to obtain the sharing identification information in the link information;
the sharing information corresponding to the sharing identification information is inquired from a preset database, the sharer identification and the sharing time in the sharing information are extracted, the sharing duration is determined according to the sharing time, the sharer identification is used as a target sharer identification, and the sharing duration is used as a target sharing duration.
5. The method for processing a shared picture according to claim 3 or 4, wherein the obtaining of the poster image from the poster area through an edge detection method comprises:
determining an upper boundary of the poster area and a lower boundary of the poster area through an edge detection algorithm, and obtaining a poster image to be determined according to the upper boundary of the poster area and the lower boundary of the poster area;
and adopting Radon transformation to perform inclination correction on the poster image to be determined to obtain the corrected poster image.
6. The method for sharing pictures according to claim 1, wherein the extracting, from a campaign database, a check image whose similarity with the poster image satisfies a preset threshold as a target poster image comprises:
normalizing the poster image to obtain a reduced image of the poster image in the same ratio;
carrying out gray level processing on the reduced images in the same ratio to obtain simplified images;
calculating a gray level average value of the simplified image, comparing the gray level value of each pixel of the simplified image with the gray level average value to obtain a pixel identifier of each pixel of the simplified image, and taking the obtained pixel identifier as a target image fingerprint of the poster image;
acquiring an image fingerprint of each check image from the activity database to serve as a check image fingerprint;
and acquiring the verification image corresponding to the verification image fingerprint of which the Hamming distance with the target image fingerprint does not exceed the preset threshold value as a target verification image.
7. The method for processing the shared picture according to claim 1, wherein after the receiving the shared image to be audited and extracting the effective area in the shared image to be audited to obtain a basic image, before the obtaining of the sharer account corresponding to the target sharer identifier and the determining of whether the activity reward of the activity has been issued to the sharer account, the method further comprises:
if the poster image is not identified from the basic image, acquiring the target sharing duration and an image unique identification code of the basic image from the basic image, wherein the image unique identification code is a unique identification number of the user-shared activity poster generated by the client according to the target activity information and the target sharer identification;
and identifying a target sharer identification in the image unique identification code and the index number of the activity, and acquiring activity information of the activity from the activity database according to the index number to serve as the target activity information.
8. The processing device for sharing pictures is characterized by comprising:
the image extraction module is used for receiving the shared image to be audited and extracting the effective area in the shared image to be audited to obtain a basic image;
the target information extraction module is used for extracting a target sharer identifier, a target sharing duration and a poster image from the basic image if the poster image is identified from the basic image, wherein the sharing duration is the duration from the sharing activity to the uploading of the screenshot of the user;
the activity matching module is used for extracting verification images with similarity meeting a preset threshold value with the poster image from an activity database, taking the verification images as target poster images, and acquiring target activity information corresponding to the target poster images, wherein the target activity information comprises preset sharing duration and a preset rewarding mode, and each verification image corresponds to one activity;
the sharer information identification module is used for acquiring a sharer account corresponding to the target sharer identification and judging whether the activity reward of the activity is issued to the sharer account or not;
and the sharing duration judging module is used for issuing the activity reward to the sharer account according to the preset reward mode if the activity reward is not issued to the sharer account and the target sharing duration is not less than the preset activity duration.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the processing method for sharing pictures according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the processing method for sharing pictures according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910841756.1A CN110751500B (en) | 2019-09-06 | 2019-09-06 | Processing method and device for sharing pictures, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910841756.1A CN110751500B (en) | 2019-09-06 | 2019-09-06 | Processing method and device for sharing pictures, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110751500A true CN110751500A (en) | 2020-02-04 |
| CN110751500B CN110751500B (en) | 2023-06-27 |
Family
ID=69276079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910841756.1A Active CN110751500B (en) | 2019-09-06 | 2019-09-06 | Processing method and device for sharing pictures, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751500B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785353A (en) * | 2021-03-04 | 2021-05-11 | 深圳大智软件技术有限公司 | Method for guiding vermicelli to be added to sales WeChat |
| CN112988688A (en) * | 2021-03-24 | 2021-06-18 | 百度在线网络技术（北京）有限公司 | Picture sharing method and device, electronic equipment and storage medium |
| CN113420205A (en) * | 2021-05-28 | 2021-09-21 | 北京达佳互联信息技术有限公司 | Method and device for determining sharing source account, terminal equipment and server |
| CN114996766A (en) * | 2022-08-01 | 2022-09-02 | 江西财经大学 | Image sharing method and system based on two-dimension code social network and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108494947A (en) * | 2018-02-09 | 2018-09-04 | 维沃移动通信有限公司 | A kind of images share method and mobile terminal |
| CN109636127A (en) * | 2018-11-19 | 2019-04-16 | 贵州创汇众投科技信息咨询有限公司 | A kind of network based on positioning puts mutual assistance platform and its application method on someone's head |
| CN109871497A (en) * | 2019-02-28 | 2019-06-11 | 广州酷狗计算机科技有限公司 | The method and apparatus of sharing information |
| CN110163644A (en) * | 2018-07-17 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Article distribution method, device and storage medium |
-
2019
- 2019-09-06 CN CN201910841756.1A patent/CN110751500B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108494947A (en) * | 2018-02-09 | 2018-09-04 | 维沃移动通信有限公司 | A kind of images share method and mobile terminal |
| CN110163644A (en) * | 2018-07-17 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Article distribution method, device and storage medium |
| CN109636127A (en) * | 2018-11-19 | 2019-04-16 | 贵州创汇众投科技信息咨询有限公司 | A kind of network based on positioning puts mutual assistance platform and its application method on someone's head |
| CN109871497A (en) * | 2019-02-28 | 2019-06-11 | 广州酷狗计算机科技有限公司 | The method and apparatus of sharing information |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785353A (en) * | 2021-03-04 | 2021-05-11 | 深圳大智软件技术有限公司 | Method for guiding vermicelli to be added to sales WeChat |
| CN112785353B (en) * | 2021-03-04 | 2024-03-22 | 深圳大智软件技术有限公司 | Method for adding vermicelli to sales WeChat in guiding way |
| CN112988688A (en) * | 2021-03-24 | 2021-06-18 | 百度在线网络技术（北京）有限公司 | Picture sharing method and device, electronic equipment and storage medium |
| CN112988688B (en) * | 2021-03-24 | 2024-06-11 | 百度在线网络技术（北京）有限公司 | Picture sharing method and device, electronic equipment and storage medium |
| CN113420205A (en) * | 2021-05-28 | 2021-09-21 | 北京达佳互联信息技术有限公司 | Method and device for determining sharing source account, terminal equipment and server |
| CN113420205B (en) * | 2021-05-28 | 2024-02-23 | 北京达佳互联信息技术有限公司 | Method and device for determining shared source account, terminal equipment and server |
| CN114996766A (en) * | 2022-08-01 | 2022-09-02 | 江西财经大学 | Image sharing method and system based on two-dimension code social network and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110751500B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492643B (en) | Certificate identification method and device based on OCR, computer equipment and storage medium | |
| CN110751500B (en) | Processing method and device for sharing pictures, computer equipment and storage medium | |
| US10635946B2 (en) | Eyeglass positioning method, apparatus and storage medium | |
| US10445569B1 (en) | Combination of heterogeneous recognizer for image-based character recognition | |
| WO2019109526A1 (en) | Method and device for age recognition of face image, storage medium | |
| CN110033018B (en) | Graph similarity judging method and device and computer readable storage medium | |
| CN111160434B (en) | Training method and device for target detection model and computer readable storage medium | |
| US11836969B2 (en) | Preprocessing images for OCR using character pixel height estimation and cycle generative adversarial networks for better character recognition | |
| CN110222687A (en) | Complex background card face information identifying method and system | |
| CN111783757A (en) | OCR technology-based identification card recognition method in complex scene | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN111340022A (en) | Identity card information identification method and device, computer equipment and storage medium | |
| CN105335760A (en) | Image number character recognition method | |
| CN108615006B (en) | Method and apparatus for outputting information | |
| CN111858977B (en) | Bill information acquisition method, device, computer equipment and storage medium | |
| CN111915635A (en) | Test question analysis information generation method and system supporting self-examination paper marking | |
| CN110942067A (en) | Text recognition method and device, computer equipment and storage medium | |
| CN112232336A (en) | Certificate identification method, device, equipment and storage medium | |
| CN112801099A (en) | Image processing method, device, terminal equipment and medium | |
| CN114049540A (en) | Method, device, equipment and medium for detecting marked image based on artificial intelligence | |
| CN114241463A (en) | Signature verification method and device, computer equipment and storage medium | |
| CN113780116A (en) | Invoice classification method and device, computer equipment and storage medium | |
| CN110795995B (en) | Data processing method, device and computer readable storage medium | |
| CN109635798B (en) | Information extraction method and device | |
| CN116912881A (en) | Animal species identification method, computer equipment and identification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |