CN107424138A - Image interfusion method and computer-readable storage medium based on cloud server - Google Patents
Image interfusion method and computer-readable storage medium based on cloud server Download PDFInfo
- Publication number
- CN107424138A CN107424138A CN201710197816.1A CN201710197816A CN107424138A CN 107424138 A CN107424138 A CN 107424138A CN 201710197816 A CN201710197816 A CN 201710197816A CN 107424138 A CN107424138 A CN 107424138A
- Authority
- CN
- China
- Prior art keywords
- image
- pending picture
- portrait
- terminal
- picture
- 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 46
- 206010013654 Drug abuse Diseases 0.000 claims abstract description 52
- 208000011117 substance-related disease Diseases 0.000 claims abstract description 52
- 230000004927 fusion Effects 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims description 36
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 4
- 239000003814 drug Substances 0.000 abstract description 28
- 229940079593 drug Drugs 0.000 abstract description 28
- 230000000694 effects Effects 0.000 abstract description 17
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013527 convolutional neural network Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006378 damage Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000032258 transport Effects 0.000 description 4
- 230000002457 bidirectional effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010024642 Listless Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 201000009310 astigmatism Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000857 drug effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000155 melt Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002574 poison Substances 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of image interfusion method and computer-readable storage medium based on cloud server.Wherein the image interfusion method based on cloud server includes：Obtain pending picture and the image procossing rank uploaded by terminal；The fusion treatment of drug abuse portrait feature is carried out to pending picture according to image procossing rank, to obtain the result images of pending picture and drug abuse portrait Fusion Features；And result images are fed back into terminal, for terminal display.The solution of the present invention, the portrait of people is handled by image fusion technology, it is allowed to show the effect after taking drugs, the purpose of publicity drug abuse negative unhealthy can be reached, publicity against drugs are carried out by way of terminal display, so that range of publicity is extensive, the effect of publicity is not only improved, also effectively reduces publicity cost.
Description
Technical field
The present invention relates to Computer Image Processing field, more particularly to a kind of image co-registration side based on cloud server
Method and computer-readable storage medium.
Background technology
At present, the drug issue being on the rise has become global disaster.Drugs not only can seriously damage human body and be good for
Health, but also wrecked from soul and psychosoma and destroy abuse individual.On the one hand can cause to abuse individual economy collapse, family's solution
Body；On the other hand it can also inevitably derive the major crimes such as theft, robbery, violence, homicide, be brought not to public society
Appreciable calamitous harm.
But publicity against drugs are mainly carried out using the space of a whole page of public service ads and period by network newspapers and periodicals, radio station at present, this
The mode of a little publicity against drugs has disadvantages that, such as the speed that information is propagated is slower, and the scope of propagation is not extensive enough, publicizes simultaneously
Required cost is very high.
The content of the invention
It is an object of the present invention to provide a kind of efficient and inexpensive publicity against drugs approach.
The present invention one is further objective is that the application of expanded images fusion.
Especially, the invention provides a kind of image interfusion method based on cloud server, this method to include：Obtain by
Pending picture and the image procossing rank that terminal uploads；Drug abuse portrait is carried out to pending picture according to image procossing rank
The fusion treatment of feature, to obtain the result images of pending picture and drug abuse portrait Fusion Features；It is and result images are anti-
Terminal is fed to, for terminal display.
Alternatively, image procossing rank correspond to different drug abuse portrait features texture image, and according to image at
The step of reason rank carries out the fusion treatment of drug abuse portrait feature to pending picture includes：Obtain corresponding to image procossing rank
The texture image of drug abuse portrait feature, carried out as target texture image, and by target texture image and pending picture
Image co-registration processing.
Alternatively, portrait fusion python codes are configured with cloud server, and target texture image is located with waiting
The step of reason picture carries out image co-registration processing includes：Call portrait fusion python codes, with performance objective texture image with
The step of image co-registration processing of pending picture.
Alternatively, also include before the step of target texture image is carried out into image co-registration processing with pending picture：
Recognition of face is carried out by portrait fusion python code call dlib storehouses；And when pending picture does not include face-image,
The pending undesirable prompt message of picture is fed back to terminal.
Alternatively, also include before the step of fusion treatment of drug abuse portrait feature is carried out to pending picture：Treat
Handle picture and carry out image preprocessing, so that pending picture meets the treatment conditions of setting.
Alternatively, the step of carrying out image preprocessing to pending picture includes：Detect the characteristic point of pending picture；Root
The position of eyes in the face-image of pending picture is determined according to characteristic point；Pending picture is rotated, is in the position of eyes
It is horizontal；And the pending picture of cutting, the pixel value of pending picture is equal to preset value.
Alternatively, the step of terminal upload pending picture includes：The html tables of user's submission are judged using ajax codes
Whether include view data in list；And if so, image upload code in preset ph p is called by pending picture transfer to cloud
Hold server.
Alternatively, the step of terminal upload image procossing rank includes：The html tables submitted using ajax codes from user
Image procossing rank is extracted in list；Order line command code in preset ph p is called by image procossing class transport to high in the clouds
Server.
Alternatively, the step of terminal display result images include：Using terminal browser webpage div tag image
Result images are shown in placeholder.
According to another aspect of the present invention, a kind of computer-readable storage medium is additionally provided, wherein being stored with computer journey
Sequence, and cause the place equipment of computer-readable storage medium to perform any of the above-described kind during computer program operation and be based on cloud service
The image interfusion method of device.
The present invention the image interfusion method based on cloud server, by obtain by terminal upload pending picture with
And image procossing rank, the fusion treatment of drug abuse portrait feature is carried out to pending picture according to image procossing rank, to obtain
The result images of pending picture and drug abuse portrait Fusion Features, and result images are fed back into terminal, for terminal display, lead to
Image fusion technology is crossed to handle the portrait of people, is allowed to show the effect after taking drugs, publicity drug abuse can be reached and be harmful to health
The purpose of health, uploads the portrait of oneself as pending picture, after image co-registration is handled, using the portrait of oneself to be defeated
Go out, it is more genuine and believable compared to traditional example using other people as point of penetration, effective improving warning effect, pass through terminal display
Mode carry out publicity against drugs so that range of publicity is extensive, not only improves the effect of publicity, also reduces publicity cost.
Further, the image interfusion method of the invention based on cloud server, wherein image procossing rank correspond to
The texture image of different drug abuse portrait features, the texture maps of drug abuse portrait feature corresponding to image procossing rank can be obtained
Picture, image co-registration processing is carried out as target texture image, and by target texture image and pending picture, so as to
Different degrees of drug abuse effect is shown, can more clearly show the harm taken drugs progressively, in addition, being carried out to pending picture
Image preprocessing can also be carried out to pending picture, before the fusion treatment of drug abuse portrait feature so that pending picture meets
The treatment conditions of setting, by lift the quality of pending picture lifted the quality of the result images after image co-registration and
The efficiency of image co-registration so that the drug abuse effect that result images show is more genuine and believable, and the process of image preprocessing is pre-
First it is automatically performed, reduces the operation bidirectional of user, improve ease of use, avoids influenceing the usage experience of user, so as to influence
The popularity of publicity.
According to the accompanying drawings will be brighter to the detailed description of the specific embodiment of the invention, those skilled in the art
Above-mentioned and other purposes, the advantages and features of the present invention.
Brief description of the drawings
Some specific embodiments of the present invention are described in detail by way of example, and not by way of limitation with reference to the accompanying drawings hereinafter.
Identical reference denotes same or similar part or part in accompanying drawing.It should be appreciated by those skilled in the art that these
What accompanying drawing was not necessarily drawn to scale.In accompanying drawing：
Fig. 1 is the applicable hardware system of the image interfusion method according to an embodiment of the invention based on cloud server
Configuration diagram；
Fig. 2 is the schematic diagram of the image interfusion method according to an embodiment of the invention based on cloud server；
Fig. 3 is the detail flowchart of the image interfusion method according to an embodiment of the invention based on cloud server；
And
Fig. 4 is the schematic diagram of computer-readable storage medium according to an embodiment of the invention.
Embodiment
Image interfusion method provided in an embodiment of the present invention based on cloud server provides a kind of inexpensive, efficient
Publicity against drugs approach, and the application of image co-registration is extended, the prohibition of drug, the effect of drug law enforcement can be effectively improved.
Fig. 1 is the applicable hardware system of the image interfusion method according to an embodiment of the invention based on cloud server
Configuration diagram.As illustrated, the hardware system can include in general manner：Terminal 110, the network equipment 120 and high in the clouds clothes
Business device 130.The computer-readable storage medium of wherein cloud server 130 is stored with for realizing that the image based on cloud server melts
The computer program of conjunction method, when the computer program is run, cloud server 130 can be caused to perform the base of the present embodiment
In the Image Fusion of cloud server.
Terminal 110 and cloud server 130 can carry out data interaction by the network equipment 120, for example, terminal 110 is logical
Crossing network can be to the uploading pictures of cloud server 130, as pending picture；Cloud server 130 is to pending picture
After carrying out image co-registration processing, the result picture of image co-registration processing processing can be preserved, and by network by result figure
Piece feeds back to terminal 110, so that terminal 110 is shown.Wherein, terminal 110 can be personal computer, tablet personal computer, intelligent hand
The equipment such as machine, the network equipment 120 can include various communication lines and routing device etc..Uploaded by the picture of terminal 110
Interface uploads to the portrait pictures of individual subscriber on cloud server 130, and (Software-as-a- is serviced with software
Service, abbreviation SaaS) pattern provide image co-registration service.Melted by the image based on cloud server of the present embodiment
Hop algorithm handles the portrait of people, is allowed to show the effect after taking drugs, can reach the purpose of publicity drug abuse negative unhealthy.
In addition, the law that drug abuse and drug trafficking is carried out using network as medium publicizes, and it is more rapider than traditional paper medium, propagate also more wide
It is general.
Fig. 2 is the schematic diagram of the image interfusion method according to an embodiment of the invention based on cloud server.Such as figure
It is shown, it is somebody's turn to do the image interfusion method based on cloud server and comprises the following steps：
Step S202, obtain pending picture and the image procossing rank uploaded by terminal 110；
Step S204, the fusion treatment of drug abuse portrait feature is carried out to pending picture according to image procossing rank, with
To pending picture and the result images of drug abuse portrait Fusion Features；
Step S206, result images are fed back into terminal 110, so that terminal 110 is shown.
In above step, the pending picture in step S202 comprises at least face-image, and can be terminal 110
Cloud server 130 is uploaded to by network.Usually, the pending picture can include the face-image of user oneself, with
After image co-registration processing is carried out, the picture of output is more felt added with substitution.Terminal 110 can be the terminal for possessing camera function
Equipment, directly using the image of shooting as picture or the equipment with picture store function, with from the picture stored
It is middle to choose local picture as pending picture., can be relative after pending picture is obtained in a kind of specific embodiment
Pending picture carries out Face datection, if detecting including face-image, is determined as reasonable picture；If do not detect face
Image, then it is determined as unreasonable picture, at the same time, the prompt message to report an error can be exported, reminds user to upload bag again
Include the reasonable picture of face-image.
Further, since the result of image co-registration and the quality of pending picture are closely bound up, the matter of pending picture is improved
Amount can improve the quality and efficiency of image co-registration result.Therefore, image can be carried out first before image co-registration is carried out
Pretreatment, a specific image preprocessing example are：Some characteristic points of face-image are detected, then according to characteristic point, are looked for
To the position of people's eyes.After people's eyes position is found, image is rotated, makes its two horizontal alignments, then image is cut
Cut, it is possessed suitable pixel value, and be easy to follow-up fusion treatment.
Image procossing rank in step S202 corresponds to the texture image of different drug abuse portrait features, for example, image
Processing rank is higher, and the drug abuse portrait feature that its corresponding texture image is showed is more obvious, and specifically, drug abuse portrait feature can
With partially yellow, partially dark, partially blue or green including face's complexion；Look decadent, listless；Eyes is without god, One's eyesight is restrained, pupil severe astigmatism
Deng.
It can be made in step S204 by obtaining the texture image of drug abuse portrait feature corresponding to image procossing rank
For target texture image, and target texture image and pending picture are subjected to image co-registration processing.Wherein, drug abuse portrait feature
Can be by deep learning network model by being drawn to sample image training, sample image is the face-image of drug addict.It is logical
Cross and the drug abuse portrait feature of drug addict and pending picture are subjected to image co-registration processing, can show the picture after processing
The effect gone out after taking drugs, in the case where pending picture is user's portrait so that user faces the consequence of drug abuse directly, can
Effective improving warning effect.
Result images can also be preserved in advance before result images are fed back into terminal 110 in step S206.
Pass through the result picture after receiving and showing that image co-registration is handled in terminal 110 so that the scope of publicity against drugs is more extensive, prohibits
The mode of poison publicity is more convenient, and cost can be effectively reduced while publicity against drugs effect is lifted.
In some alternative embodiments, it can be taken by the further optimization to above-mentioned steps and configuration based on high in the clouds
The image interfusion method of business device realizes higher technique effect, below in conjunction with Jie for optionally performing flow to the present embodiment
Continue and the image interfusion method based on cloud server of the present embodiment is described in detail, the embodiment is only to performing flow
For example, in the specific implementation, can be according to specific implementation demand, execution sequence, execution condition to part steps enter
Row modification.Fig. 3 is the detail flowchart of the image interfusion method according to an embodiment of the invention based on cloud server.Should
Image interfusion method based on cloud server comprises the following steps：
Step S302, judge whether include view data in the html lists of user's submission using ajax codes, if so, holding
Row step S304, if it is not, re-executing step S302；
Step S304, image upload code in preset ph p is called by pending picture transfer to cloud server 130；
Step S306, image procossing rank is extracted in the html lists submitted using ajax codes from user；
Step S308, order line command code in preset ph p is called by image procossing class transport to cloud server
130；
Step S310, the texture image of drug abuse portrait feature corresponding to image procossing rank is obtained, as target line
Manage image；
Step S312, python code call dlib storehouses are merged by portrait and carry out recognition of face；
Step S314, judges whether pending picture includes face-image, if so, step S318 is performed, if it is not, performing step
Rapid S316；
Step S316, feed back the undesirable prompt message of pending picture to terminal 110；
Step S318, calls portrait fusion python codes, and target texture image is carried out into image with pending picture melts
Conjunction is handled, to obtain result images；
Step S320, result images are fed back into terminal 110, using terminal 110 browser webpage div tag figure
As showing result images in placeholder.
In above step, asynchronous JavaScript and XML (the Asynchronous Javascript in step S302
And XML, abbreviation ajax), it is a kind of web development technologies for creating interaction network page application.HyperText Markup Language
(HyperText Markup Language, abbreviation html) list includes view data, then it is pending to illustrate that user have submitted
Picture；Without view data is included in html lists, then illustrate that user does not submit pending picture.
Step S304, call the pending picture transfer that the image upload code in preset ph p can submit user extremely
Cloud server 130.HyperText Preprocessor (Hypertext Preprocessor, abbreviation php) is a kind of general pin of increasing income
Program, can be embedded into html by this language, and execution efficiency is higher.
Image procossing rank in step S306 corresponds to the texture image of different drug abuse portrait features, for example, image
Processing rank is higher, and the drug abuse portrait feature that its corresponding texture image is showed is more obvious, and specifically, drug abuse portrait feature can
With partially yellow, partially dark, partially blue or green including face's complexion；Look decadent, listless；Eyes is without god, One's eyesight is restrained, pupil severe astigmatism
Deng.Image procossing rank can reflect the degree of drug abuse, such as take drugs time etc., so as to improve the impact sense to user.
The image procossing level supplementary biography for calling the order line command code in preset ph p to select user in step S308
Transport to cloud server 130.
In step S310, pass through the texture maps of drug abuse portrait feature corresponding to the image procossing rank determination of user's selection
Picture, and as target texture image.
Python code call dlib storehouses are merged by portrait in step S312 and carry out recognition of face, wherein python is a kind of
The explanation type computer programming language of object-oriented, grammer simple and clear.Python has abundant and powerful storehouse, its energy
It is enough that the various modules made of other language are bound up.Dlib storehouses are the storehouses of increasing income of a machine learning, are used
Easily, header file is directly included, and independent of other storehouses (carrying image coding and decoding storehouse source code), you can to realize
Face datection function.
Judge whether pending picture includes face-image in step S314, it may be determined that whether pending picture conforms to
Ask, to be further ensured that the success rate of image co-registration.
In step S316, in the case where pending picture does not include face-image, it can be fed back to terminal 110 pending
The undesirable prompt message of picture, in order to which user changes pending picture in time, avoid influenceing at successive image fusion
The process of reason.Usually, the pending picture can include the face-image of user oneself, to carry out image co-registration processing
Afterwards, the picture of output is more felt added with substitution.
Portrait fusion python code configurations in step S318 in server 130, call portrait fusion beyond the clouds
Python codes, target texture image and pending picture are subjected to image co-registration processing, to obtain result images.Wherein target
Texture image is corresponding with the image procossing rank that user selects, and what it showed is corresponding to the image procossing rank of user's selection
Drug abuse portrait feature.
Drug abuse portrait feature show that its specific extraction step can include by advance deep learning：To being inhaled in picture library
The face-image of malicious personnel carries out picture quality screening, extracts predetermined quantity picture quality and meets the image of requirement as sample
Image；And sample image is passed to convolutional neural networks and is trained, to extract drug abuse portrait feature.Wherein in picture library
The face-image of drug addict carries out picture quality screening to select sample image, is due to the result of image co-registration processing picture
Closely bound up with the quality of the facial picture of drug addict, the quality by lifting sample image can improve image co-registration processing
Picture quality and handle image efficiency.Specifically, can be according to the type of the face-image of drug addict and big
It is small come judge whether meet require.In addition, the concrete numerical value of predetermined quantity can be preset according to the actual requirements.
Sample image is passed into the specific steps that convolutional neural networks are trained to include：Obtain convolutional neural networks
The picture material that middle certain layer extracts from sample image, and gradient descent algorithm is performed with white noise image, to look for
The image to match to the image content features with sample image；And calculated using standard error backpropagation relative to phase
The gradient of the image of matching, so as to extract drug abuse portrait feature.Also, the convolutional neural networks that the present embodiment uses are by 19 layers
16 convolutional layers of VGG networks and 5 pond layers provide.Convolutional neural networks (Convolutional Neural Networks,
Abbreviation CNN) it is widely used in pattern classification field, its basic structure includes two layers, and one is characterized extract layer, each neuron
Input be connected with the local acceptance region of preceding layer, and extract the local feature.After the local feature is extracted, it with
Position relationship between further feature is also decided therewith；The second is Feature Mapping layer, each computation layer of network is by multiple spies
Sign mapping composition, each Feature Mapping is a plane, and the weights of all neurons are equal in plane.In convolutional neural networks
Each convolutional layer followed by one is used for asking the computation layer of local average and second extraction, and this distinctive feature twice carries
Structure is taken to reduce feature resolution.
Target texture image with pending picture before image co-registration processing can also include in step S318：It is right
Pending picture carries out image preprocessing, so that pending picture meets the treatment conditions of setting.Specifically, to pending picture
The step of carrying out image preprocessing includes：Detect the characteristic point of pending picture；The face of pending picture is determined according to characteristic point
The position of eyes in portion's image；Pending picture is rotated, the position of eyes is in level；And the pending picture of cutting, make
The pixel value of pending picture is equal to preset value.The characteristic point of the face-image wherein detected is several, a kind of specific
In embodiment, 68 characteristic points of face-image can be detected.It should be noted that the particular number of features described above point is only
Enumerate, and not limitation of the invention, in some other embodiment, other quantity can also be set according to the actual requirements
Characteristic point.
The result and the quality of pending picture of image co-registration processing are closely bound up, and the quality for improving pending picture can be with
Improve the quality of the result picture of image co-registration processing and the efficiency of image co-registration processing.And the process of image preprocessing is pre-
First it is automatically performed, reduces the operation bidirectional of user, improve ease of use, avoids influenceing the usage experience of user, so as to influence
The popularity of publicity.
Result images are fed back to before terminal 110 and can be preserved result images in step S320, then can be with
Using the browser of terminal 110 result images are shown in the image placeholder of webpage div tag.Wherein div tag be for
The element of structure and background is provided for the content of bulk (block-level) in html documents.Div start-tag and end are marked
All the elements between label are all for forming this block, and characteristic of element is controlled by the attribute of div tag included in it
System, or be controlled by using this block of fstyleformat.scrolltrackization.Div tag be referred to as separate mark, can set word,
The putting position of picture, form etc..
The result picture after image co-registration processing is shown by terminal 110 in step S320 so that the scope of publicity against drugs
More extensively, the mode of publicity against drugs is more convenient, and cost can be effectively reduced while publicity against drugs effect is lifted.If with
The other portrait pictures of processing are wanted at family after a pictures have been handled, and new portrait pictures can be directly uploaded by network
, without refresh page again, ensuing picture processing is consistent with image processing flow before, re-executes step
S304 to step S320.
The image interfusion method based on cloud server of the present embodiment, by obtain uploaded by terminal 110 it is pending
Picture and image procossing rank, the fusion treatment of drug abuse portrait feature is carried out to pending picture according to image procossing rank,
To obtain the result images of pending picture and drug abuse portrait Fusion Features, and result images are fed back into terminal 110, for end
The displaying of end 110, the portrait of people is handled by image fusion technology, be allowed to show the effect after taking drugs, publicity can be reached
The purpose of drug abuse negative unhealthy, the portrait of oneself is uploaded as pending picture, after image co-registration is handled, with oneself
Portrait for output, more genuine and believable compared to traditional example using other people as point of penetration, effective improving warning effect, lead to
The mode for crossing the displaying of terminal 110 carries out publicity against drugs so that range of publicity is extensive, not only improves the effect of publicity, also effectively drops
Low publicity cost.
Further, the image interfusion method based on cloud server of the present embodiment, wherein image procossing rank are corresponding
In the texture image of different drug abuse portrait features, the texture maps of drug abuse portrait feature corresponding to image procossing rank can be obtained
Picture, image co-registration processing is carried out as target texture image, and by target texture image and pending picture, so as to
Different degrees of drug abuse effect is shown, can more clearly show the harm taken drugs progressively, in addition, being carried out to pending picture
Image preprocessing can also be carried out to pending picture, before the fusion treatment of drug abuse portrait feature so that pending picture meets
The treatment conditions of setting, by lift the quality of pending picture lifted the quality of the result images after image co-registration and
The efficiency of image co-registration so that the drug abuse effect that result images show is more genuine and believable, and the process of image preprocessing is pre-
First it is automatically performed, reduces the operation bidirectional of user, improve ease of use, avoids influenceing the usage experience of user, so as to influence
The popularity of publicity.
The present embodiment additionally provides a kind of computer-readable storage medium 10, and Fig. 4 is calculating according to an embodiment of the invention
The schematic diagram of machine storage medium 10, the computer-readable storage medium preserves computer program 11, and computer program 11 is run
When cause the place equipment of computer-readable storage medium 10 to perform the image co-registration based on cloud server of any of the above-described embodiment
The place equipment of method, wherein computer-readable storage medium 10 is cloud server 130, can be performed by cloud server 130
The image interfusion method based on cloud server of any of the above-described embodiment.
The computer-readable storage medium 10 of the present embodiment can be that (electrically erasable is read-only to be deposited for such as flash memory, EEPROM
Reservoir), EPROM, hard disk or ROM etc electronic memory.Computer-readable storage medium 10, which has, to be used to perform the above method
In any method and step computer program 11 memory space.These computer programs 11 can be from one or more meter
Read or be written in calculation machine program product in this one or more computer program product.These computer program products
Including such as hard disk, the program code carrier of compact-disc (CD), storage card or floppy disk etc.The institute of computer-readable storage medium 10
When equipment runs above computer program 11, each step in the method for foregoing description can be performed.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, still can be direct according to present disclosure without departing from the spirit and scope of the present invention
It is determined that or derive many other variations or modifications for meeting the principle of the invention.Therefore, the scope of the present invention is understood that and recognized
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of image interfusion method based on cloud server, including：
Obtain pending picture and the image procossing rank uploaded by terminal；
The fusion treatment of drug abuse portrait feature is carried out to the pending picture according to described image processing rank, it is described to obtain
The result images of pending picture and the drug abuse portrait Fusion Features；And
The result images are fed back into the terminal, for the terminal display.
2. the method according to claim 11, wherein,
Described image processing rank corresponds to the texture image of different drug abuse portrait features, and
The step of carrying out the fusion treatment of drug abuse portrait feature to the pending picture according to described image processing rank includes：
The texture image of drug abuse portrait feature corresponding to described image processing rank is obtained, as target texture image, and by institute
State target texture image and carry out image co-registration processing with the pending picture.
3. according to the method for claim 2, wherein being configured with portrait fusion python codes in the cloud server, and
And the step of target texture image is carried out into image co-registration processing with the pending picture, includes：
The portrait fusion python codes are called, are melted with performing the image of the target texture image and the pending picture
The step of closing processing.
4. according to the method for claim 3, wherein the target texture image and the pending picture are being carried out into figure
Also include before as the step of fusion treatment：
Recognition of face is carried out by portrait fusion python code call dlib storehouses；And
When the pending picture does not include face-image, it is undesirable to feed back the pending picture to the terminal
Prompt message.
5. according to the method for claim 1, wherein being carried out to the pending picture at the fusion of drug abuse portrait feature
Also include before the step of reason：
Image preprocessing is carried out to the pending picture, so that the pending picture meets the treatment conditions of setting.
6. according to the method for claim 5, wherein the step of carrying out image preprocessing to the pending picture includes：
Detect the characteristic point of the pending picture；
The position of eyes in the face-image of the pending picture is determined according to the characteristic point；
The pending picture is rotated, the position of the eyes is in level；And
The pending picture is cut, the pixel value of the pending picture is equal to preset value.
7. according to the method for claim 1, wherein the terminal includes the step of uploading the pending picture：
Judge whether include view data in the html lists of user's submission using ajax codes；And
If so, image upload code in preset ph p is called by the pending picture transfer to the cloud server.
8. according to the method for claim 1, wherein the terminal upload other step of described image process level includes：
Described image processing rank is extracted in the html lists submitted using ajax codes from user；
Call the order line command code in preset ph p that described image process level supplementary biography is transported into the cloud server.
9. according to the method for claim 1, wherein including described in the terminal display the step of result images：
The result images are shown in the image placeholder of webpage div tag using the browser of the terminal.
10. a kind of computer-readable storage medium, wherein being stored with computer program, and cause institute during computer program operation
State computer-readable storage medium place equipment perform it is according to any one of claim 1 to 9 based on cloud server
Image interfusion method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710197816.1A CN107424138A (en) | 2017-03-29 | 2017-03-29 | Image interfusion method and computer-readable storage medium based on cloud server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710197816.1A CN107424138A (en) | 2017-03-29 | 2017-03-29 | Image interfusion method and computer-readable storage medium based on cloud server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107424138A true CN107424138A (en) | 2017-12-01 |
Family
ID=60423140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710197816.1A Pending CN107424138A (en) | 2017-03-29 | 2017-03-29 | Image interfusion method and computer-readable storage medium based on cloud server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107424138A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784850A (en) * | 2019-01-08 | 2019-05-21 | 腾讯科技（深圳）有限公司 | Prompt information processing method, device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204904298U (en) * | 2015-08-18 | 2015-12-23 | 苏州旭智设计营造有限公司 | A appearance collection conversion systems for taking drugs simulation |
| CN106156730A (en) * | 2016-06-30 | 2016-11-23 | 腾讯科技（深圳）有限公司 | The synthetic method of a kind of facial image and device |
-
2017
- 2017-03-29 CN CN201710197816.1A patent/CN107424138A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204904298U (en) * | 2015-08-18 | 2015-12-23 | 苏州旭智设计营造有限公司 | A appearance collection conversion systems for taking drugs simulation |
| CN106156730A (en) * | 2016-06-30 | 2016-11-23 | 腾讯科技（深圳）有限公司 | The synthetic method of a kind of facial image and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784850A (en) * | 2019-01-08 | 2019-05-21 | 腾讯科技（深圳）有限公司 | Prompt information processing method, device, computer equipment and storage medium |
| CN109784850B (en) * | 2019-01-08 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Prompt information processing method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492643A (en) | Certificate recognition methods, device, computer equipment and storage medium based on OCR | |
| CN110334585A (en) | Table recognition method, apparatus, computer equipment and storage medium | |
| CN110321755A (en) | A kind of recognition methods and device | |
| CN107742107A (en) | Facial image sorting technique, device and server | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| CN111212303B (en) | Video recommendation method, server and computer-readable storage medium | |
| CN112016502B (en) | Safety belt detection method, safety belt detection device, computer equipment and storage medium | |
| CN113111880A (en) | Certificate image correction method and device, electronic equipment and storage medium | |
| TW201118780A (en) | Intelligent mobile dervice product evaluation system and method based on information retrieval technnology | |
| CN109962975A (en) | Information-pushing method, device, electronic equipment and system based on object identification | |
| CN109829484B (en) | Clothing classification method and equipment and computer-readable storage medium | |
| CN112836515A (en) | Text analysis method, recommendation device, electronic equipment and storage medium | |
| CN107424138A (en) | Image interfusion method and computer-readable storage medium based on cloud server | |
| CN108154070A (en) | Face identification method and device | |
| CN111695971B (en) | Article recommendation method, apparatus and device, and computer storage medium | |
| CN111402027B (en) | Identity recognition method, commodity loan auditing method, device and terminal equipment | |
| WO2022006829A1 (en) | Bill image recognition method and system, electronic device, and storage medium | |
| CN114926203A (en) | Advertisement short video label processing method, device, equipment and storage medium | |
| CN114187106A (en) | Method and device for identifying illegal node in block chain | |
| KR102624783B1 (en) | Method and apparatus for machine learning based authenticity determination | |
| CN112329841A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| Young et al. | Eyeglasses frame selection based on oval face shape using convolutional neural network | |
| US20240104900A1 (en) | Fish school detection method and system thereof, electronic device and storage medium | |
| CN113449756B (en) | Improved DenseNet-based multi-scale image identification method and device | |
| CN113780124B (en) | Transformer-based face beauty prediction method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171201 |
|
| RJ01 | Rejection of invention patent application after publication |