CN107622428A - A kind of method and device for realizing virtually trying - Google Patents
A kind of method and device for realizing virtually trying Download PDFInfo
- Publication number
- CN107622428A CN107622428A CN201610556512.5A CN201610556512A CN107622428A CN 107622428 A CN107622428 A CN 107622428A CN 201610556512 A CN201610556512 A CN 201610556512A CN 107622428 A CN107622428 A CN 107622428A
- Authority
- CN
- China
- Prior art keywords
- image
- model
- trying
- user
- clothing
- 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
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of method and device for realizing virtually trying, this method includes：Be used as the picture or video for trying model on to the user itself that previously generates of user's displaying, when receiving user and trying the instruction of clothing on, according to the type of the clothing, identify described in try the matching position of model's body on；The image for the clothing that user in clothing database is selected, the image for matching position with trying model's body described in described identify on are synthesized and shown.Using method disclosed in the present embodiment, it is possible to achieve the effect that simulation customer itself tries on, it is time saving and energy saving, efficiency high of doing shopping, improve user's purchase experiences.
Description
Technical field
The present invention relates to computer modeling technique field, more particularly to a kind of method and device for realizing virtually trying.
Background technology
Traditional mode of trying on is customer in market, shop, is tried on using the fitting room of businessman, experiences upper body effect, with
The development of ecommerce, increasing people's shopping on the web, network businessman is embodied using the photo of various models to try on
Effect, so as to attract consumer to buy clothing.
Traditional mode customer need of trying on is in the action, and different clothings needs repeatedly to wear off, to reach satisfied effect
Fruit, causes waste of time and shopping is less efficient.
The photo of the model of shopping online experiences the effect tried on, equally can only be carried out respectively for different photos
With reference to fitting effects of the different clothings on same model can not embody.
How a kind of virtual clothes effect is provided, embodies fitting effects rapidly on same model to reach, improves
Fitting efficiency, becomes focus.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State a kind of method and device for realizing virtually trying of problem.
In a first aspect, the embodiment of the present invention provides a kind of method for realizing virtually trying, this method includes：
The user itself previously generated to user's displaying is as the image for trying model on；Described image includes：Picture
Or video；
When receiving user and trying the instruction of clothing on, according to the type of the clothing, identify and described try model's body on
The matching position of body；
The image for the clothing that user in clothing database is selected, with trying model's body described in described identify on
Image with position is synthesized and shown.
In one embodiment, the user itself is previously generated as the image for trying model on by following manner：
Shoot the posture photo or video of the user different angle of itself；
By the posture photo or video of the captured user different angle of itself, it is associated with the account of the user
Storage；
Correspondingly, the image for trying model on previously generated to user's displaying, is specifically included：
The account logged according to user, read image and the displaying of the user itself of user account association.
In one embodiment, according to the type of the clothing, the matching position for trying model's body on, bag are identified
Include：
The image for trying model on is decomposed into different positions according to characteristic point；
According to the type of the default clothing and the corresponding relation of parts of body, it is determined that the matching for trying model on
Position.
In one embodiment, the characteristic point is to try each joint of the body of model on；
The image for trying model on is decomposed into different positions according to characteristic point, including：
Try the coordinate in each joint of model's body described in detection on；
Default head is divided each key point detected successively to foot or foot to the order on head
Cut, obtain different positions.
In one embodiment, the image of clothing user in clothing database selected, described in described identify
The image for trying the matching position of model's body on is synthesized, including：
Identify the angle for trying model's current body posture on；
According to the angle of the current body posture for trying model on, clothing corresponding angle described in database is chosen
Image；
By the covering of the image of the clothing corresponding angle try on model match on the image at position and with try on model its
His image at position is merged.
In one embodiment, select described in database after the image of clothing corresponding angle, the clothing is corresponding
The image of angle with it is described try on model's image except it is described matching position in addition to image spliced and merged the step of it
Before, in addition to：
According to the size at the matching position for trying model's body on identified, the figure of the clothing corresponding angle is adjusted
The size of picture.
Second aspect, the embodiment of the present invention provide a kind of device for realizing virtually trying, including：Display module, for
The user itself that user's displaying previously generates is as the image for trying model on；Described image includes：Picture or video；And
The image after image synthesis unit synthesis is shown to user；
Picture recognition module, for when receiving user and trying the instruction of clothing on, according to the type of the clothing, identification
Go out the matching position for trying model's body on；
Image synthesis unit, for the image for the clothing for selecting user in clothing database, with the institute identified
The image for stating the matching position for trying model's body on is synthesized.
In one embodiment, said apparatus also includes：
User images acquisition module, for shooting the posture photo or video of the user different angle of itself；By institute
The posture photo or video of the user of the shooting different angle of itself, storage is associated with the account of the user；
Correspondingly, above-mentioned display module, specifically for the account logged according to user, the described of user account association is read
The image of user itself and displaying.
In one embodiment, picture recognition module, including：
Submodule is decomposed, for the image for trying model on to be decomposed into different positions according to characteristic point；
Determination sub-module, for the type and the corresponding relation of parts of body according to the default clothing, determine institute
State the matching position for trying model on.
In one embodiment, the characteristic point is to try each joint of the body of model on；
The decomposition submodule, for detecting the coordinate in each joint for trying model's body on；Default head is arrived
Foot or foot split to each key point detected to the order on head, obtain different positions successively.
In one embodiment, described image synthesis module, including：
Submodule is identified, for identifying the angle for trying model's current body posture on；
Submodule is chosen, the angle of the current body posture for trying model on according to, chooses institute in database
State the image of clothing corresponding angle；
Submodule is synthesized, is matched for trying the image covering of the clothing corresponding angle on model on the image at position
And the image with trying other positions of model on is merged.
In one embodiment, described image synthesis module, in addition to：
Adjust submodule, for it is described selection submodule selection database described in clothing corresponding angle image it
Afterwards, it is described synthesis submodule by the image of the clothing corresponding angle with it is described try on model's image except it is described match position it
Before the step of outer image is spliced and merged, try the image covering of the clothing corresponding angle on model and match position
Image on and the image with trying other positions of model on merged.
The beneficial effect of above-mentioned technical proposal provided in an embodiment of the present invention comprises at least：
The present invention discloses a kind of method and device for realizing virtually trying of embodiment offer, and this method includes：To user
The user itself that previously generates is shown as the picture or video for trying model on, when receiving user and trying the instruction of clothing on,
According to the type of the clothing, the matching position for trying model's body on is identified；User in clothing database is selected
The image of clothing, synthesized and shown with the image for matching position of the model's body identified.Using this reality
The method and device for realizing virtually trying of example offer is provided, the figure for trying model on can be used as by the use of the user previously generated itself
Picture, is synthesized with trying clothing on, easily shows the fitting effects of different clothings, embodies fitting effects rapidly, improves fitting
Efficiency.Also, the method and device of virtually trying is realized provided in an embodiment of the present invention, what is previously generated try model's on
Image, it is the image of the user itself of user's shooting, so, can be using user itself as model is tried on, preferably displaying examination
Effect is worn, efficiency is tried in raising on, avoids, using other models fitting effects error caused by stature differs, lifting network
The success rate and user's purchase experiences of purchase.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
Specifically noted structure is realized and obtained in book, claims and accompanying drawing.
Below by drawings and examples, technical scheme is described in further detail.
Brief description of the drawings
Accompanying drawing is used for providing a further understanding of the present invention, and a part for constitution instruction, the reality with the present invention
Apply example to be used to explain the present invention together, be not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is the flow chart for the method that virtually trying is realized in the embodiment of the present invention；
Fig. 2 is the flow chart for trying the image generating method of model in the embodiment of the present invention on；
Fig. 3 is human synovial and portion structure schematic diagram in the embodiment of the present invention；
Fig. 4 is the flow chart of step S13 in the embodiment of the present invention；
Fig. 5 is the block diagram for the device that virtually trying is realized in the embodiment of the present invention；
Fig. 6 is the block diagram of picture recognition module 52 in the embodiment of the present invention；
Fig. 7 is the block diagram of image synthesis unit 53 in the embodiment of the present invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Below in conjunction with the accompanying drawings, to the specific implementation of the method and its device provided in an embodiment of the present invention for realizing virtually trying
Mode is described in detail.
The method provided in an embodiment of the present invention for realizing virtually trying is illustrated first.
The method for realizing virtually trying that the embodiment of the present disclosure provides, shown in reference picture 1, including：
S11, to the user itself that previously generates of user's displaying as the image for trying model on；Described image includes：Picture
Or video；
S12, when receiving user and trying the instruction of clothing on, according to the type of the clothing, identify and described try mould on
The matching position of special body；
S13, the clothing for selecting user in clothing database image, with for trying model's body on identified
Image with position is synthesized and shown.
In step s 11, in virtually trying, it is necessary to first generate the image of user itself, as model is tried on, first to
The picture or video of trying model on that family displaying previously generates；
In step s 12, when receiving user and trying the instruction of clothing on, above-mentioned instruction for example can be phonetic order,
The instruction sent according to speech recognition technology, identification user；Such as can also be touch command, the embodiment of the present disclosure is not done to this
Limit.
In step s 12, the type of clothing, such as the clothing of jacket, trousers, skirt, shoes etc., also such as decorative kind：
Scarf, necktie, knot, cap, headwear etc., such as：When receiving user and trying the instruction of jacket on, identify matched
Position is the metastomium and arm of model.
In step s 13, the image of kinds of laundry user selected, the clothing of one or more types can be selected,
For example a jacket, reselection a pair of trousers can be selected；By the image for the clothing selected with step s 12 identifying
The image at the matching position of model's body corresponding to kinds of laundry is synthesized and shown.
In a kind of method for realizing virtually trying that the above-mentioned embodiment of the present disclosure provides, the examination previously generated is shown to user
The picture or video of model is worn, when receiving user and trying the instruction of clothing on, according to the type of the clothing, is identified described
Try the matching position of model's body on；By in clothing database user select clothing image, with it is described identify try on
The image at the matching position of model's body is synthesized and shown.The above-mentioned side for realizing virtually trying provided using the present embodiment
Method, it can be synthesized with trying clothing on, easily shown by the use of the user previously generated itself as the image for trying model on
The fitting effects of different clothings, fitting effects are embodied rapidly, improve fitting efficiency.Also, in reality provided in an embodiment of the present invention
In the method and device of existing virtually trying, what is previously generated tries the image of model on, is the image of the user itself of user's shooting,
So, fitting effects can be preferably shown using user itself as model is tried on, raising tries efficiency on, avoids using other
Model's fitting effects error caused by stature differs, lift the success rate and user's purchase experiences of Online Shopping.
Further, the above method provided in an embodiment of the present invention, can also directly using user itself as trying model on,
The picture or video of user itself is namely directly gathered in advance, in this case, can directly be used itself as trying mould on
It is special so that simulate the effect tried on closer to truth, improve the accuracy tried on, avoid using other try on model due to
Error caused by stature build is inconsistent.
Shown in reference picture 2, the image for trying model in step S11, including photo or video, following step can be passed through
Previously generate：
S21, the shooting user itself different angle posture photo or video；
S22, posture photo or video by the captured user different angle of itself, carried out with the account of the user
Associated storage.
Correspondingly, step S11 can be specifically embodied as, the account logged according to user, read the institute of user account association
State the image of user itself and displaying.
In the above-described embodiments, the user itself in step S21 is the model in S11, shoots the appearance of different angle
State photo includes following one or more：Left side body, body front, right side body, behind etc..
Or a short-sighted frequency can also be shot, such as：User is allowed gradually to go to front, Ran Houzai from left side as model
Right side is gone to, or is rotated otherwise, is rotated a circle 360 degree.
By the posture photo or video of itself different angle of captured user, the account of user itself is uploaded to, is gone forward side by side
Row association preserve, can according to the time name preserve, can also according to shooting photo posture name preserve, user can with
During shopping is tried on every time afterwards, above-mentioned photo or video can be selected to try on.User is also an option that shooting is other
Under varying environment, the photo or video of more multi-pose carry out uploading association preservation.
The above-mentioned image for trying model on previously generated to user's displaying, the account logged according to user, directly reads use
The image of the above-mentioned user itself of family account association and displaying.The account of login, such as account can be manually entered according to user
Password login, it can also realize that user steps on by way of near-field communication NFC (Near Field Communication) scannings
Record (such as on user's body wear NFC chip wearable device, one close to when, NFC read equipment just have read user's
Accounts information).
In one embodiment, step S12, including：The above-mentioned image for trying model on is decomposed into difference according to characteristic point
Position；According to the type of default above-mentioned clothing and the corresponding relation of parts of body, the above-mentioned matching for trying model on is determined
Position.
Above-mentioned image can be any picture that can be digitized as two-dimensional lattice, for example, RGB (represents red, green, blue three
The color of individual passage) picture etc. or the video file that is made up of substantial amounts of frame of video etc., the image of model can not be by appearance
Gesture or the limitation of dress, can shoot more various posture, angular image.
In the above-described embodiments, shown in reference picture 3, the image for trying model on is decomposed into different positions according to characteristic point,
Such as can be head, trunk, upper arm, forearm, chest, back, waist, belly, buttocks, thigh, shank, foot etc., this
A little positions are the key positions that can embody wears effect, can be corresponding with parts of body according to the type of default clothing
Relation, it is determined that trying the matching position of model on, when the fitting effects at these positions are determined respectively, correspondingly also determine that
Try the overall fitting effects of wearer.Such as the clothing of selection is shorts, then the body part of shorts matching is buttocks and thigh.
In one embodiment, features described above point is each joint for trying the body of model on；Try model's on by described
Image is decomposed into different positions according to characteristic point, including：Try the coordinate in each joint of model's body described in detection on；It is default
Head to foot or foot to the order on head, each key point detected is split successively, obtained different
Position.
Above-mentioned characteristic point is to try each joint of the body of model on；Such as：Shoulder joint, elbow joint, wrist joint, knee close
Section, ankle-joint etc..Certain features described above point can also be each position, such as：Chest, back, belly, buttocks etc..Above-mentioned spy
Sign point can be split by each joint of body or the key point at each position, so as to obtain different positions.
The embodiment of the present disclosure is not limited this.
By detecting the coordinate in the above-mentioned each joint for trying model's body on, wherein the coordinate in each joint for example can be
Two dimension or three-dimensional coordinate, can be calculated by known algorithm in correlation technique or other algorithms to obtain, the embodiment of the present invention
Above-mentioned algorithm is not limited.
The each key point detected is split successively according to the order on default head to foot, obtained different
Position；Or the order according to default foot to head, each key point detected is split successively, obtains difference
Position.Above-mentioned partitioning scheme, by detect each joint three-dimensional or two-dimensional coordinate after, can be along each pass detected
The three-dimensional or two-dimensional coordinate of section carry out dividing processing, (such as are tried so as to obtain each position of the model in clothing region is tried on
Trunk, upper arm, forearm when putting on clothing etc., buttocks, thigh, shank when trying trousers on etc.).When splitting above-mentioned position, also
Certain lap can be reserved between each position, to be easy to carry out splicing in follow-up synthetic effect figure.
Illustrate：Shown in reference picture 3, for example, being head from the crown to the position two shoulder joint, from shoulder joint
Be upper arm to elbow joint, be forearm from elbow joint to wrist joint, be thigh from buttocks to knee joint, from knee joint to ankle-joint to
Shank, it is foot from ankle-joint to toe.And pass through metastomium key point, it may be determined that chest, waist and belly, buttocks etc..
In one embodiment, in above-mentioned steps S13, the image for the clothing that user in clothing database is selected, with institute
The image for stating the matching position for trying model's body on identified is synthesized, shown in reference picture 4, including：
S131, identify the angle for trying model's current body posture on；
Try the angle of the current body posture of model described in S132, basis on, it is corresponding to choose clothing described in database
The image of angle；
S133, try the covering of the image of the clothing corresponding angle on model and match on the image at position and with trying mould on
The image at other special positions is merged.
Try the angle of the body posture of model on, various ways can be used to identify, such as selection passes through substantial amounts of human body
The image of posture, which is trained, establishes ATL, then will try the posture that model is currently presented on and is matched with the ATL,
According to similarity, it is determined that trying the current body posture of model on.
In the above-described embodiments, the image of clothing corresponding angle can have a variety of in database, such as clothing can be short
Trousers, corresponding angular image such as can be that shorts direct picture, shorts side image, the image of shorts behind or side are more
The image of individual angle, to fully ensure that the current body posture that can match model；Simultaneously it is also an option that jacket, shoes,
Cap etc..Such as：The body posture of model is positive photograph, can choose the direct picture of database mid length shorts, by shorts just
Face image covering tries the buttocks in model on at thigh；The direct picture of jacket cotta in database can also be chosen, will be short
The direct picture covering of sleeve is tried on the trunk of model and arm position；The direct picture covering examination of shoes can also be chosen
The foot of model is through, is then merged with the image at other positions, overall effect can be watched.It can be tried on single-piece,
Can also more than one piece combination try on, the embodiment of the present disclosure is not limited this.
In one embodiment, described in above-mentioned steps S132 selection databases after the image of clothing corresponding angle,
Above-mentioned steps S133 by the image of above-mentioned clothing corresponding angle with it is described try on model's image except it is described match position in addition to
Image spliced and merged before, can also carry out following step：
According to the size at the matching position for trying model's body on identified, the figure of the clothing corresponding angle is adjusted
The size of picture.
In above-mentioned steps, the size at the matching position of model's body for example can be shoulder breadth, bust, waistline, height, arm
Length, upper body length, leg length, head circumference, hip circumference, calf circumference etc., get above-mentioned size or size from user itself picture or video
Ratio data, adjust corresponding site on clothing corresponding angle image size, be allowed to preferably match, strengthen the sense of reality.
For the image or video of the trying model's (being probably user itself) on that gather in advance, the embodiment of the present invention is not
Clothing when user shoots images themselves is limited, it is necessary to carry out the place of image during progress later stage synthesis in above-mentioned steps S133
Reason, the effect being bonded completely with reaching the clothing tried on trying model's body on.If examination can not be completely covered in the clothing tried on
The clothing at the original position of model is worn, then needs to carry out additional treatments to original image, with reference to default conventional dressing habits, goes
Except the part that the part or modification that can not cover can not cover, the dressing habits for meeting people are allowed to.Such as user itself is pre-
Trousers are worn in the picture or video that first gather, can be to the Leg portion below shorts or skirt when trying shorts or skirt on
Modify, be rendered to the effect of exposed leg.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of device for realizing virtually trying, due to above-mentioned
The principle that device solves problem is similar to the foregoing method for realizing virtually trying, therefore the device is implemented to may refer to foregoing side
The implementation of method, repeat part and repeat no more.
The embodiment of the present disclosure provides a kind of device for realizing virtually trying, shown in reference picture 5, including：
Display module 51, for showing the user itself previously generated as the image for trying model on to user；The figure
As including：Picture or video；And show the image after image synthesis unit synthesis to user；
Picture recognition module 52, for when receiving user and trying the instruction of clothing on, according to the type of the clothing, knowing
Do not go out the matching position for trying model's body on；
Image synthesis unit 53, for the image for the clothing for selecting user in clothing database, identified with described
The image at the matching position for trying model's body on is synthesized.
In one embodiment, shown in reference picture 5, said apparatus also includes：User images acquisition module 50, for shooting
The posture photo or video of the user different angle of itself；By the posture photo of the captured user different angle of itself
Or video, it is associated storage with the account of the user；
Correspondingly, above-mentioned display module 51, specifically for the account logged according to user, the institute that user account associates is read
State the image of user itself and displaying.
In one embodiment, picture recognition module 52, shown in reference picture 6, including：
Submodule 521 is decomposed, for the image for trying model on to be decomposed into different positions according to characteristic point；
Determination sub-module 522, for the type and the corresponding relation of parts of body according to the default clothing, it is determined that
The matching position for trying model on.
In one embodiment, the characteristic point is to try each joint of the body of model on；
The decomposition submodule 521, for detecting the coordinate in each joint for trying model's body on；Default head
To foot or foot to the order on head, each key point detected is split successively, obtains different positions.
In one embodiment, above-mentioned image synthesis unit 53, shown in reference picture 7, including：
Submodule 531 is identified, for identifying the angle for trying model's current body posture on；
Submodule 532 is chosen, the angle of the current body posture for trying model on according to, is chosen in database
The image of the clothing corresponding angle；
Submodule 533 is synthesized, for the image covering of the clothing corresponding angle to be tried on to the image at model's matching position
On and the image with trying other positions of model on merged.
In one embodiment, described image synthesis module 53, in addition to：
Submodule 534 is adjusted, the image for the clothing corresponding angle described in the selection submodule selection database
Afterwards, it is described to synthesize submodule by the image of the clothing corresponding angle and model's image of trying on except the matching position
Outside image the step of being spliced and being merged before, try the image covering of the clothing corresponding angle on model matching part
On the image of position and the image with trying other positions of model on is merged.
The embodiment of the present invention also provides a kind of device for realizing virtually trying, including：
Processor；
For storing the memory of processor executable command；
Wherein, processor is configured as：
The user itself previously generated to user's displaying is as the image for trying model on；Described image includes：Picture
Or video；
When receiving user and trying the instruction of clothing on, according to the type of the clothing, identify and described try model's body on
The matching position of body；
The image for the clothing that user in clothing database is selected, with trying model's body described in described identify on
Image with position is synthesized and shown.
The embodiment of the present invention additionally provides a kind of non-transitorycomputer readable storage medium, when in the storage medium
When instructing the computing device by server so that server is able to carry out a kind of method for realizing virtually trying, methods described
Including：
The user itself previously generated to user's displaying is as the image for trying model on；Described image includes：Picture
Or video；
When receiving user and trying the instruction of clothing on, according to the type of the clothing, identify and described try model's body on
The matching position of body；
The image for the clothing that user in clothing database is selected, with trying model's body described in described identify on
Image with position is synthesized and shown.
The present invention discloses a kind of method and device for realizing virtually trying of embodiment offer, is previously generated to user's displaying
User itself as the picture or video for trying model on, when receiving user and trying the instruction of clothing on, according to the clothing
Type, identify the matching position for trying model's body on；The image for the clothing that user in clothing database is selected, with
The image at the matching position of the model's body identified is synthesized and shown.The realization provided using the present embodiment
The method and device of virtually trying, the image for trying model on previously generated can be utilized, is synthesized with trying clothing on, it is convenient
Ground shows the fitting effects of different clothings, embodies fitting effects rapidly, improves fitting efficiency.Also, carried in the embodiment of the present invention
In the method and device for realizing virtually trying supplied, the user itself previously generated is user's bat as the image for trying model on
The posture photo or video for itself different angle taken the photograph, so, can be using itself as model is tried on, and effect is tried in preferably displaying on
Efficiency is tried in fruit, raising on, avoids, using other models fitting effects error caused by stature differs, lifting Online Shopping
Success rate and user's purchase experiences.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The shape for the computer program product that usable storage medium is implemented on (including but is not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (12)
- A kind of 1. method for realizing virtually trying, it is characterised in that including：The user itself previously generated to user's displaying is as the image for trying model on；Described image includes：Picture regards Frequently；When receiving user and trying the instruction of clothing on, according to the type of the clothing, identify and described try model's body on Match position；The image for the clothing that user in clothing database is selected, the matching part with trying model's body described in described identify on The image of position is synthesized and shown.
- 2. the method as described in claim 1, it is characterised in that the user itself is as the image for trying model on, under The mode of stating previously generates：Shoot the posture photo or video of the user different angle of itself；By the posture photo or video of the captured user different angle of itself, it is associated and deposits with the account of the user Storage；Correspondingly, the image for trying model on previously generated to user's displaying, is specifically included：The account logged according to user, read image and the displaying of the user itself of user account association.
- 3. the method as described in claim 1, it is characterised in that according to the type of the clothing, identify and described try model on The matching position of body, including：The image for trying model on is decomposed into different positions according to characteristic point；According to the type of the default clothing and the corresponding relation of parts of body, it is determined that the matching part for trying model on Position.
- 4. method as claimed in claim 3, it is characterised in that the characteristic point is to try each joint of the body of model on；The image for trying model on is decomposed into different positions according to characteristic point, including：Try the coordinate in each joint of model's body described in detection on；The each key point detected is split successively, obtained to foot or foot to the order on head in default head To different positions.
- 5. the method as described in claim 1, it is characterised in that the image for the clothing for selecting user in clothing database, with The image at the matching position for trying model's body on identified is synthesized, including：Identify the angle for trying model's current body posture on；According to the angle of the current body posture for trying model on, the figure of clothing corresponding angle described in selection database Picture；The image covering of the clothing corresponding angle is tried on model to match on the image at position and with trying other portions of model on The image of position is merged.
- 6. method as claimed in claim 5, it is characterised in that selection database described in clothing corresponding angle image it Afterwards, by the image of the clothing corresponding angle with it is described try on model's image except it is described match position in addition to image spelled Before the step of connecing and merging, in addition to：According to the size at the matching position for trying model's body on identified, the image of the clothing corresponding angle is adjusted Size.
- A kind of 7. device for realizing virtually trying, it is characterised in that including：Display module, for showing the user itself previously generated as the image for trying model on to user；Described image Including：Picture or video；And show the image after image synthesis unit synthesis to user；Picture recognition module, for when receiving user and trying the instruction of clothing on, according to the type of the clothing, identifying institute State the matching position for trying model's body on；Image synthesis unit, for the image for the clothing for selecting user in clothing database, with the examination identified The image for wearing the matching position of model's body is synthesized.
- 8. device as claimed in claim 7, it is characterised in that said apparatus also includes：User images acquisition module, for shooting the posture photo or video of the user different angle of itself；By captured by User itself different angle posture photo or video, be associated storage with the account of the user；Correspondingly, above-mentioned display module, specifically for the account logged according to user, the user for reading user account association The image of itself and displaying.
- 9. device as claimed in claim 7, it is characterised in that picture recognition module, including：Submodule is decomposed, for the image for trying model on to be decomposed into different positions according to characteristic point；Determination sub-module, for the type and the corresponding relation of parts of body according to the default clothing, determine the examination Wear the matching position of model.
- 10. device as claimed in claim 7, it is characterised in that the characteristic point is to try each joint of the body of model on；The decomposition submodule, for detecting the coordinate in each joint for trying model's body on；Default head is to foot Or foot splits to each key point detected to the order on head, obtains different positions successively.
- 11. device as claimed in claim 7, it is characterised in that described image synthesis module, including：Submodule is identified, for identifying the angle for trying model's current body posture on；Submodule is chosen, the angle of the current body posture for trying model on according to, chooses clothing described in database The image of thing corresponding angle；Synthesize submodule, for by the covering of the image of the clothing corresponding angle try on model match on the image at position and with The image for trying other positions of model on is merged.
- 12. device as claimed in claim 11, it is characterised in that described image synthesis module, in addition to：Submodule is adjusted, after the image of clothing corresponding angle described in the selection submodule selection database, institute State synthesis submodule by the image of the clothing corresponding angle with it is described try on model's image except it is described match position in addition to Before the step of image is spliced and merged, the image covering of the clothing corresponding angle is tried the figure of model's matching position on As on and the image with trying other positions of model on is merged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556512.5A CN107622428A (en) | 2016-07-14 | 2016-07-14 | A kind of method and device for realizing virtually trying |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556512.5A CN107622428A (en) | 2016-07-14 | 2016-07-14 | A kind of method and device for realizing virtually trying |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107622428A true CN107622428A (en) | 2018-01-23 |
Family
ID=61087621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610556512.5A Pending CN107622428A (en) | 2016-07-14 | 2016-07-14 | A kind of method and device for realizing virtually trying |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107622428A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932660A (en) * | 2018-07-26 | 2018-12-04 | 北京旷视科技有限公司 | A kind of commodity using effect analogy method, device and equipment |
| CN110473296A (en) * | 2019-08-15 | 2019-11-19 | 浙江中国轻纺城网络有限公司 | Chart pasting method and device |
| CN111787242A (en) * | 2019-07-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
| WO2021043204A1 (en) * | 2019-09-03 | 2021-03-11 | 程立苇 | Data processing method and apparatus, computer device and computer-readable storage medium |
| CN113559503A (en) * | 2021-06-30 | 2021-10-29 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982581A (en) * | 2011-09-05 | 2013-03-20 | 北京三星通信技术研究有限公司 | Virtual try-on system and method based on images |
| CN104820930A (en) * | 2015-05-19 | 2015-08-05 | 北京五悦信息科技有限公司 | Intelligent fitting system and virtual fitting method thereof |
| CN105069836A (en) * | 2015-07-28 | 2015-11-18 | 哈尔滨理工大学 | Electronic fitting system based on stereoscopic vision and multi-feature image retrieval |
| CN105184584A (en) * | 2015-09-17 | 2015-12-23 | 北京京东方多媒体科技有限公司 | Virtual fitting system and method |
| CN105303380A (en) * | 2014-06-23 | 2016-02-03 | 南京专创知识产权服务有限公司 | Virtual fitting system |
-
2016
- 2016-07-14 CN CN201610556512.5A patent/CN107622428A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982581A (en) * | 2011-09-05 | 2013-03-20 | 北京三星通信技术研究有限公司 | Virtual try-on system and method based on images |
| CN105303380A (en) * | 2014-06-23 | 2016-02-03 | 南京专创知识产权服务有限公司 | Virtual fitting system |
| CN104820930A (en) * | 2015-05-19 | 2015-08-05 | 北京五悦信息科技有限公司 | Intelligent fitting system and virtual fitting method thereof |
| CN105069836A (en) * | 2015-07-28 | 2015-11-18 | 哈尔滨理工大学 | Electronic fitting system based on stereoscopic vision and multi-feature image retrieval |
| CN105184584A (en) * | 2015-09-17 | 2015-12-23 | 北京京东方多媒体科技有限公司 | Virtual fitting system and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932660A (en) * | 2018-07-26 | 2018-12-04 | 北京旷视科技有限公司 | A kind of commodity using effect analogy method, device and equipment |
| CN111787242A (en) * | 2019-07-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
| WO2021008166A1 (en) * | 2019-07-17 | 2021-01-21 | 北京京东尚科信息技术有限公司 | Method and apparatus for virtual fitting |
| US11935167B2 (en) | 2019-07-17 | 2024-03-19 | Reling Jingdong Shangke Information Technology Co., Ltd. | Method and apparatus for virtual fitting |
| CN110473296A (en) * | 2019-08-15 | 2019-11-19 | 浙江中国轻纺城网络有限公司 | Chart pasting method and device |
| CN110473296B (en) * | 2019-08-15 | 2023-09-26 | 浙江中国轻纺城网络有限公司 | Mapping method and device |
| WO2021043204A1 (en) * | 2019-09-03 | 2021-03-11 | 程立苇 | Data processing method and apparatus, computer device and computer-readable storage medium |
| US11849790B2 (en) | 2019-09-03 | 2023-12-26 | Liwei Cheng | Apparel fitting simulation based upon a captured two-dimensional human body posture image |
| CN113559503A (en) * | 2021-06-30 | 2021-10-29 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
| CN113559503B (en) * | 2021-06-30 | 2024-03-12 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11941772B2 (en) | Method and system for generating a 3D reconstruction of a human | |
| CN110609617B (en) | Apparatus, system and method for virtual mirror | |
| US10964078B2 (en) | System, device, and method of virtual dressing utilizing image processing, machine learning, and computer vision | |
| CN107622428A (en) | A kind of method and device for realizing virtually trying | |
| US9369638B2 (en) | Methods for extracting objects from digital images and for performing color change on the object | |
| US8976160B2 (en) | User interface and authentication for a virtual mirror | |
| KR102044348B1 (en) | Apparatus system for virtual fitting cloth based on augmented reality | |
| CN110021061A (en) | Collocation model building method, dress ornament recommended method, device, medium and terminal | |
| KR101710521B1 (en) | Apparatus and method of performing simulation for virtual fitting with computer-graphics representation of user body and computer program for the same | |
| JP6320237B2 (en) | Virtual try-on device, virtual try-on method, and program | |
| US20220044311A1 (en) | Method for enhancing a user's image while e-commerce shopping for the purpose of enhancing the item that is for sale | |
| US20130173226A1 (en) | Garment modeling simulation system and process | |
| TW200828043A (en) | Terminal try-on simulation system and operating and applying method thereof | |
| CN107211165A (en) | Devices, systems, and methods for automatically delaying video display | |
| JP2016038811A (en) | Virtual try-on apparatus, virtual try-on method and program | |
| CN105869217B (en) | A kind of virtual real fit method | |
| JP2020016961A (en) | Information processing apparatus, information processing method, and information processing program | |
| WO2014081394A1 (en) | Method, apparatus and system for virtual clothes modelling | |
| JP2016038813A (en) | Virtual try-on apparatus, virtual try-on system, virtual try-on method and program | |
| JP2020198053A (en) | Information processing device, information processing method, person search system, and person search method | |
| US11386615B2 (en) | Creating a custom three-dimensional body shape model | |
| KR102466408B1 (en) | Styling device and the driving method thereof | |
| CN109118590A (en) | A kind of 3D fitting platform based on machine learning | |
| CN108682045A (en) | A kind of mirror and its control method based on smart home | |
| JP2018113060A (en) | Virtual try-on apparatus, virtual try-on system, virtual try-on method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180123 |
|
| RJ01 | Rejection of invention patent application after publication |