CN108830784A - A kind of image processing method, device and computer storage medium - Google Patents

A kind of image processing method, device and computer storage medium Download PDF

Info

Publication number
CN108830784A
CN108830784A CN201810553761.8A CN201810553761A CN108830784A CN 108830784 A CN108830784 A CN 108830784A CN 201810553761 A CN201810553761 A CN 201810553761A CN 108830784 A CN108830784 A CN 108830784A
Authority
CN
China
Prior art keywords
limbs
point information
leg
image
processing
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
Application number
CN201810553761.8A
Other languages
Chinese (zh)
Inventor
陈晨
杨瑞健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sensetime Technology Development Co Ltd
Original Assignee
Beijing Sensetime Technology Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sensetime Technology Development Co Ltd filed Critical Beijing Sensetime Technology Development Co Ltd
Priority to CN201810553761.8A priority Critical patent/CN108830784A/en
Publication of CN108830784A publication Critical patent/CN108830784A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/04—Context-preserving transformations, e.g. by using an importance map
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The embodiment of the invention discloses a kind of image processing method, device and computer storage mediums.The method includes：The first image is obtained, the target object in the first image is identified, obtains the limbs detection information of the target object；Image procossing is carried out to the corresponding limbs region of the limbs detection information, generates the second image.

Description

A kind of image processing method, device and computer storage medium
Technical field
The present invention relates to image processing techniques, and in particular to a kind of image processing method, device and computer storage medium.
Background technique
With the rapid development of Internet technology, there are various image processing tools, it can be to the target pair in image " body moulding " " leg shaping ", " arm moulding " or " waist are carried out as being handled, such as to the target person in image Portion's moulding ", " buttocks moulding ", " shoulder moulding ", " head moulding " " chest moulding " etc. become fat or reduce or become larger or become smaller Operation, allows the stature of personage more perfectly to handle.Then, this image processing operations need operator to be manually operated, and need Wanting multiple adjustment to operate can be only achieved preferable adjustment effect.
Summary of the invention
To solve existing technical problem, the embodiment of the present invention provides a kind of image processing method, device and calculating Machine storage medium.
In order to achieve the above objectives, the technical solution of the embodiment of the present invention is realized in：
The embodiment of the invention provides a kind of image processing method, the method includes：
The first image is obtained, identifies the target object in the first image, obtains the limbs detection of the target object Information；
Image procossing is carried out to the corresponding limbs region of the limbs detection information, generates the second image.
In above scheme, the limbs detection information includes limbs key point information and/or limbs contour point information；
The limbs key point information includes the coordinate information of limbs key point；
The limbs contour point information includes the coordinate information of limbs profile point.
In above scheme, the limbs profile point is comprised at least one of the following：Arm geometry point, hand profile point, shoulder Profile point, leg profile point, foot's profile point, waist profile point, contouring head point, buttock contour point, thoracic contours point；
The limbs key point comprises at least one of the following：Arm key point, hand key point, shoulder key point, leg Key point, foot's key point, waist key point, header key point, buttocks key point, chest key point.
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information in above scheme, including：
The limbs key point information and/or the corresponding limbs region of limbs contour point information are carried out at anamorphose Reason；
Wherein, the limbs region includes at least one of following region：Head zone, shoulder regions, chest area, waist Portion region, seat area, arm regions, hand region, leg area, foot areas.
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information in above scheme, including：To institute It states the corresponding limbs region of limbs detection information and carries out at least one of following anamorphose processing：Stretch processing, compression processing, Enhancing processing.
In above scheme, the limbs key point information includes leg key point information and/or arm key point information；Institute Stating limbs contour point information includes leg profile point information and/or arm geometry point information；The leg profile point information includes First leg profile point information and the second leg profile point information；The first leg profile point information corresponds to leg foreign steamer It is wide；The second leg profile point information corresponds to leg Internal periphery；The arm geometry point information includes first-hand arm profile Point information and the second arm contour point information；The first arm contour point information corresponds to arm outer profile；The second-hand Arm contour point information corresponds to arm Internal periphery；
It is described that image procossing, including at least one of are carried out to the corresponding limbs region of the limbs detection information：
For the leg profile point information and/or the corresponding leg area of leg key point information according to the leg outside Profile carries out compression processing to the leg outer profile towards the direction of the leg Internal periphery, and according to the leg lubrication groove Exterior feature carries out compression processing to the leg Internal periphery towards the direction of the leg outer profile；
For the leg profile point information and/or the corresponding leg area of leg key point information according in the leg Profile carries out stretch processing to the leg outer profile towards the direction of the leg outer profile, and according to the leg foreign steamer Exterior feature carries out stretch processing to the leg Internal periphery towards the direction of the leg Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm outer profile towards in the arm The direction of profile carries out compression processing to the arm outer profile, and according to the arm Internal periphery towards the arm foreign steamer Wide direction carries out compression processing to the arm Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm Internal periphery towards outside the arm The direction of profile carries out stretch processing to the arm outer profile, and according to the arm outer profile towards the arm lubrication groove Wide direction carries out stretch processing to the arm Internal periphery.
In above scheme, the limbs contour point information includes leg profile point information；The leg profile point packet Include the third leg profile point information corresponding to shank profile；The limbs key point information includes leg key point information；Institute Stating leg key point information includes the first leg key point information corresponding to lower leg area；
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：
The third leg profile point information and/or the corresponding lower leg area of first leg key point information are carried out Towards the stretch processing of first direction, or carry out the compression processing towards second direction opposite to the first direction.
In above scheme, the limbs contour point information includes waist contour point information；The waist contour point information packet Include the first waist profile point sub-information relevant to the leg area of the target object；The limbs key point information includes waist Portion's key point information；The waist key point information includes that the first waist relevant to the leg area of the target object is crucial Point sub-information；
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：
To the first waist profile point sub-information and/or the corresponding part waist of the first waist key point sub-information Region carries out the compression processing towards third direction, or carries out the stretching towards the fourth direction opposite with the third direction Processing, to promote or reduce the corresponding part waist profile of the first waist profile point sub-information.
In above scheme, the limbs contour point information includes waist contour point information；The limbs key point information packet Include waist key point information；
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：
The middle line that lumbar region is determined based on the waist contour point information, to the waist contour point information and/or waist Key point information corresponding lumbar region in portion's carries out compression processing towards the direction of the middle line according to two sides waist profile；Or Person, to the waist contour point information and/or the corresponding lumbar region of waist key point information according to the middle line towards two sides The direction of waist profile carries out stretch processing.
In above scheme, the limbs contour point information includes thoracic contours point information；The limbs key point information packet Include chest key point information；
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：
Following image change is carried out for thoracic contours point information and/or the corresponding chest area of the chest key point information At least one of shape processing：Stretch processing, compression processing, enhancing processing.
In above scheme, the limbs contour point information includes thoracic contours point information；The limbs key point information packet Include chest key point information；
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：
For at least partly area in thoracic contours point information and/or the corresponding chest area of the chest key point information Domain carries out liquefaction filter processing.
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information in above scheme, including：
The first kind deformation parameter answered based on each pair of point in the limbs region is to the limbs contour point information pair The limbs region answered carries out anamorphose processing；
Wherein, the contour edge that the first kind deformation parameter is formed with corresponding point to the limbs contour point information The distance between variation and change.
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information in above scheme, generate second Image, including：
The first kind deformation parameter answered based on each pair of point in the limbs region is to the limbs contour point information pair The limbs region answered carries out anamorphose processing, obtains the first processing result；
Image is carried out at least partly background area in the first image, in addition to the target object region Deformation process, image covering treatment or the processing that respective image is generated according to the feature of at least partly background area, obtain Second processing result；
The second image is generated based on first processing result and the second processing result.
In above scheme, it is described in the first image, in addition to the target object region at least partly Background area carries out anamorphose processing, including：
The the second class deformation parameter answered based on each pair of point in at least partly background area to it is described at least partly Background area carries out anamorphose processing；
Wherein, the second class deformation parameter with corresponding point to the target object the distance between contour edge Variation and variation exponentially times.
In above scheme, described image covering treatment, including：Limbs area before limbs region adjusted is greater than adjustment When domain, at least partly background area described in the limbs region overlay adjusted；
The feature of at least partly background area generates the processing of respective image, including：When limbs region adjusted When less than limbs region before adjustment, new background area is generated according at least partly background area, by the new background area Fill the area of absence that the limbs region adjusted is formed in domain.
In above scheme, the limbs contour point information includes contour point information corresponding with pending area；
It is described that the corresponding limbs region of the limbs detection information is handled, including：
The type for identifying the corresponding pending area of the contour point information, the type based on the pending area is in institute It states and adds object information in pending area；Alternatively,
It identifies the object information in the corresponding pending area of the contour point information, it is corresponding to adjust the object information Display properties parameter.
In above scheme, the limbs key point is bone key point.
The embodiment of the invention also provides a kind of image processing apparatus, described device includes acquiring unit and image procossing list Member；Wherein,
The acquiring unit identifies the target object in the first image, obtains the mesh for obtaining the first image Mark the limbs detection information of object；
Described image processing unit, the corresponding limbs area of the limbs detection information for being obtained to the acquiring unit Domain carries out image procossing, generates the second image.
In above scheme, the limbs detection information includes limbs key point information and/or limbs contour point information；
The limbs key point information includes the coordinate information of limbs key point；
The limbs contour point information includes the coordinate information of limbs profile point.
In above scheme, the limbs profile point is comprised at least one of the following：Arm geometry point, hand profile point, shoulder Profile point, leg profile point, foot's profile point, waist profile point, contouring head point, buttock contour point, thoracic contours point；
The limbs key point comprises at least one of the following：Arm key point, hand key point, shoulder key point, leg Key point, foot's key point, waist key point, header key point, buttocks key point, chest key point.
In above scheme, described image processing unit, for the key point information and/or limbs contour point information pair The limbs region answered carries out anamorphose processing；
Wherein, the limbs region includes at least one of following region：Head zone, shoulder regions, chest area, waist Portion region, seat area, arm regions, hand region, leg area, foot areas.
In above scheme, described image processing unit, for being carried out to the corresponding limbs region of the limbs detection information At least one of following anamorphose processing：Stretch processing, compression processing, enhancing processing.
In above scheme, the limbs key point information includes leg key point information and/or arm key point information；Institute Stating limbs contour point information includes leg profile point information and/or arm geometry point information；The leg profile point information includes First leg profile point information and the second leg profile point information；The first leg profile point information corresponds to leg foreign steamer It is wide；The second leg profile point information corresponds to leg Internal periphery；The arm geometry point information includes first-hand arm profile Point information and the second arm contour point information；The first arm contour point information corresponds to arm outer profile；The second-hand Arm contour point information corresponds to arm Internal periphery；
Described image processing unit, for executing at least one of：For the leg profile point information and/or leg The corresponding leg area of key point information is according to the leg outer profile towards the direction of the leg Internal periphery to the leg Outer profile carry out compression processing, and according to the leg Internal periphery towards the direction of the leg outer profile in the leg Profile carries out compression processing；
For the leg profile point information and/or the corresponding leg area of leg key point information according in the leg Profile carries out stretch processing to the leg outer profile towards the direction of the leg outer profile, and according to the leg foreign steamer Exterior feature carries out stretch processing to the leg Internal periphery towards the direction of the leg Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm outer profile towards in the arm The direction of profile carries out compression processing to the arm outer profile, and according to the arm Internal periphery towards the arm foreign steamer Wide direction carries out compression processing to the arm Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm Internal periphery towards outside the arm The direction of profile carries out stretch processing to the arm outer profile, and according to the arm outer profile towards the arm lubrication groove Wide direction carries out stretch processing to the arm Internal periphery.
In above scheme, the limbs contour point information includes leg profile point information；The leg profile point packet Include the third leg profile point information corresponding to shank profile；The limbs key point information includes leg key point information；Institute Stating leg key point information includes the first leg key point information corresponding to lower leg area；
Described image processing unit, for the third leg profile point information and/or first leg key point The corresponding lower leg area of information carries out the stretch processing towards first direction, or carries out towards opposite to the first direction The compression processing of second direction.
In above scheme, the limbs contour point information includes waist contour point information；The waist contour point information packet Include the first waist profile point sub-information relevant to the leg area of the target object；The limbs key point information includes waist Portion's key point information；The waist key point information includes that the first waist relevant to the leg area of the target object is crucial Point sub-information；
Described image processing unit, for crucial to the first waist profile point sub-information and/or first waist The corresponding part lumbar region of point sub-information carries out the compression processing towards third direction, or carries out direction and the third party Stretch processing to opposite fourth direction, to promote or reduce the corresponding part waist of the first waist profile point sub-information Profile.
In above scheme, the limbs contour point information includes waist contour point information；The limbs key point information packet Include waist key point information；
Described image processing unit, for determining the middle line of lumbar region based on the waist contour point information, to described Waist contour point information and/or the corresponding lumbar region of waist key point information are according to two sides waist profile towards the middle line Direction carries out compression processing；Or to the corresponding lumbar region of the waist contour point information according to the middle line towards two sides waist The direction of contouring carries out stretch processing.
In above scheme, the limbs contour point information includes thoracic contours point information；The limbs key point information packet Include chest key point information；
Described image processing unit, for corresponding described for thoracic contours point information and/or chest key point information Chest area carries out at least one of following anamorphose processing：Stretch processing, compression processing, enhancing processing.
In above scheme, the limbs contour point information includes thoracic contours point information；The limbs key point information packet Include chest key point information；
Described image processing unit, for corresponding for thoracic contours point information and/or the chest key point information At least partly region in chest area carries out liquefaction filter processing.
In above scheme, described image processing unit, first for being answered based on each pair of point in the limbs region Class deformation parameter carries out anamorphose processing to the corresponding limbs region of the limbs contour point information；
Wherein, the contour edge that the first kind deformation parameter is formed with corresponding point to the limbs contour point information The distance between variation and change.
In above scheme, described image processing unit, be also used to answer based on each pair of point in the limbs region A kind of deformation parameter carries out anamorphose processing to the corresponding limbs region of the limbs contour point information, obtains the first processing knot Fruit；Anamorphose is carried out at least partly background area in the first image, in addition to the target object region Processing, image covering treatment or the processing that respective image is generated according to the feature of at least partly background area, obtain second Processing result；The second image is generated based on first processing result and the second processing result.
In above scheme, described image processing unit, for based on each pair of point in at least partly background area The the second class deformation parameter answered carries out anamorphose processing at least partly background area；Wherein, the second class deformation Parameter exponentially variation again with the variation of corresponding point to the distance between the contour edge of the target object.
In above scheme, described image covering treatment, including：Limbs area before limbs region adjusted is greater than adjustment When domain, at least partly background area described in the limbs region overlay adjusted；
The feature of at least partly background area generates the processing of respective image, including：When limbs region adjusted When less than limbs region before adjustment, new background area is generated according at least partly background area, by the new background area Fill the area of absence that the limbs region adjusted is formed in domain.
In above scheme, the limbs contour point information includes contour point information corresponding with pending area；
Described image processing unit is also used to identify the type of the corresponding pending area of the contour point information, is based on The type of the pending area adds object information in the pending area；Alternatively, identifying the contour point information pair The object information in pending area answered adjusts the corresponding display properties parameter of the object information.
In above scheme, the limbs key point is bone key point.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, this refers to The step of described image of embodiment of the present invention processing method is realized when order is executed by processor.
The embodiment of the invention also provides a kind of image processing apparatus, including memory, processor and it is stored in memory Computer program that is upper and can running on a processor, the processor are realized described in the embodiment of the present invention when executing described program The step of image processing method.
The embodiment of the invention also provides a kind of computer program product, the computer program product includes that computer can It executes instruction, after which is performed, can be realized the step of described image processing method of the embodiment of the present invention Suddenly.
Image processing method, device and computer storage medium provided in an embodiment of the present invention, the method includes：It obtains First image identifies the target object in the first image, obtains the limbs detection information of the target object；To the limb The corresponding limbs region of physical examination measurement information carries out image procossing, generates the second image.Using the technical solution of the embodiment of the present invention, Based on the acquisition of the limbs detection information to the target object in image, image is carried out to limbs region based on limbs detection information Processing, realizes the adjust automatically to the limbs region of target object, is repeatedly manually operated without user, greatly improves user Operating experience.
Detailed description of the invention
Fig. 1 is the flow diagram of the image processing method of the embodiment of the present invention；
Fig. 2 is the composed structure schematic diagram of the image processing apparatus of the embodiment of the present invention；
Fig. 3 is the hardware composed structure schematic diagram of the image processing apparatus of the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing and specific embodiment the present invention is described in further detail.
The embodiment of the invention provides a kind of image processing methods.Fig. 1 is the image processing method of the embodiment of the present invention Flow diagram；As shown in Figure 1, the method includes：
Step 101：The first image is obtained, the target object in the first image is identified, obtains the target object Limbs detection information.
Step 102：Image procossing is carried out to the corresponding limbs region of the limbs detection information, generates the second image.
In the present embodiment, image processing method is applied in image processing apparatus, and image processing apparatus can be located at mobile phone, put down In the mobile terminals such as plate computer, laptop, it may be alternatively located in the terminals such as desktop computer, integrated computer.
The image processing method of the present embodiment carries out image procossing to the first image, identifies in the first image first Target object；Wherein, the target object can be true man as object to be processed, it can be understood as true in image Personage；In other embodiments, target object is also possible to virtual portrait.
In the present embodiment, the limbs detection information includes limbs key point information and/or limbs contour point information；It is described Limbs key point information includes the coordinate information of limbs key point；The limbs contour point information includes the coordinate of limbs profile point Information.Wherein, the limbs profile in the limbs region of the limbs profile point characterization target object, that is, pass through the limbs profile point Coordinate information be capable of forming the limbs contour edge of target object.Wherein, the limbs profile point comprises at least one of the following： Arm geometry point, hand profile point, shoulder contour point, leg profile point, foot's profile point, waist profile point, contouring head point, Buttock contour point, thoracic contours point.Wherein, the key point of the bone of the limbs key point characterization target object, that is, pass through institute It states the coordinate information of limbs key point, connect the major skeletal that limbs key point is capable of forming target object.Wherein, the limbs Key point comprises at least one of the following：Arm key point, hand key point, shoulder key point, leg key point, foot are crucial Point, waist key point, header key point, buttocks key point, chest key point.
As an implementation, described that image procossing, packet are carried out to the corresponding limbs region of the limbs detection information It includes：Anamorphose processing is carried out to the limbs key point information and/or the corresponding limbs region of limbs contour point information；Its In, the limbs region includes at least one of following region：Head zone, shoulder regions, chest area, lumbar region, stern Portion region, arm regions, hand region, leg area, foot areas.
Wherein, described right to the limbs detection information (namely limbs key point information and/or limbs contour point information) The limbs region answered carries out anamorphose processing, including：The corresponding limbs region of the limbs detection information is carried out with the following figure At least one of distortion of image processing：Stretch processing, compression processing, enhancing processing.
Specifically, mainly carrying out anamorphose processing, processing mode to the limbs region of target object in the present embodiment It mainly include at least one of：The stretching (corresponding to " becoming fat " or " elongation ") and/or compression in region (correspond to " reducing " Or " shortening ") deformation process；Region can be at least one of following region：Head zone, shoulder regions, chest area, Lumbar region, seat area, arm regions, hand region, leg area, foot areas.To the limbs region of target object Processing can also include enhancing processing (corresponding to " increasing flesh " processing) etc..
Anamorphose processing for leg area and/or arm regions, in one embodiment, the limbs profile point letter Breath includes leg profile point information and/or arm geometry point information；The limbs key point information includes leg key point information And/or arm key point information；The leg profile point information includes the first leg profile point information and the second leg profile point Information；The first leg profile point information corresponds to leg outer profile；The second leg profile point information corresponds to leg Internal periphery；The arm geometry point information includes first-hand arm contour point information and the second arm contour point information；Described first Arm geometry point information corresponds to arm outer profile；The second arm contour point information corresponds to arm Internal periphery；It is then described Method further includes：Obtain the leg profile point letter in the limbs contour point information corresponding to the leg area of the target object Breath, and/or, obtain the arm geometry point letter in the limbs contour point information corresponding to the arm regions of the target object Breath.
Then it is described to the corresponding limbs region of the limbs detection information carry out anamorphose processing, including it is following at least it One：For the corresponding leg area of the leg profile point information according to the leg outer profile towards the leg Internal periphery Direction carries out compression processing to the leg outer profile, and according to the leg Internal periphery towards the side of the leg outer profile Compression processing is carried out to the leg Internal periphery；
For the leg profile point information and/or the corresponding leg area of leg key point information according in the leg Profile carries out stretch processing to the leg outer profile towards the direction of the leg outer profile, and according to the leg foreign steamer Exterior feature carries out stretch processing to the leg Internal periphery towards the direction of the leg Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm outer profile towards in the arm The direction of profile carries out compression processing to the arm outer profile, and according to the arm Internal periphery towards the arm foreign steamer Wide direction carries out compression processing to the arm Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm Internal periphery towards outside the arm The direction of profile carries out stretch processing to the arm outer profile, and according to the arm outer profile towards the arm lubrication groove Wide direction carries out stretch processing to the arm Internal periphery.
Specifically, the present embodiment is using anamorphose algorithm to leg for carrying out compressive deformation processing to leg area Portion region carries out compression processing, the width of leg area is specifically compressed, to achieve the effect that thin leg.In practical application, leg Contouring includes leg outer profile and leg Internal periphery；Leg outer profile corresponds to lateral leg, and leg Internal periphery corresponds to leg On the inside of portion.For the compression processing of leg area, compression processing is carried out towards the direction of leg Internal periphery for leg outer profile, Compression processing is carried out towards the direction of leg outer profile for leg Internal periphery, so as to shorten the width of leg area, namely contracting The distance between the both sides of the edge in short leg region, the distance be on the outer profile of leg on any point to leg Internal periphery away from From.
Pair of arm regions progress compressive deformation processing is approximate with the compressive deformation of leg area processing, and which is not described herein again. And the stretcher strain processing of leg area and arm regions is handled with compressive deformation it is contrary, it is also no longer superfluous here It states.
In another embodiment, described that image procossing is carried out to the corresponding limbs region of the limbs detection information, also May include：The leg area is determined based on the first leg profile point information and the second leg profile point information Middle line；To the corresponding leg area of the leg profile point information respectively according to the leg outer profile and the leg Internal periphery Compression processing is carried out towards the direction of the middle line, so as to shorten the width of leg area, namely shortens the two sides of leg area The distance between edge, the distance are the shortest distances on the outer profile of leg on any point to leg Internal periphery；Alternatively, to described The corresponding leg area of leg profile point information is respectively according to the middle line towards the leg outer profile and the leg lubrication groove Wide direction carries out stretch processing, to elongate the width of leg area, namely between the both sides of the edge of elongation leg area Distance.
It is similar to for the processing mode of leg area using processing mode of the anamorphose algorithm for arm regions, this In repeat no more.
In the present embodiment, on the one hand flexible processing for leg area is stretched or is compressed for lower leg area On the other hand processing is the accounting by promoting or reducing " stringcourse " to increase leg；Wherein, " stringcourse " is as stature ratio Cut-off rule is to calculate the reference line with lower part of the body ratio above the waist, in practical application, the most short distance between the profile point of waist two sides From can be described as " stringcourse ".
In one embodiment, the limbs contour point information includes leg profile point information；The leg profile point information Third leg profile point information including corresponding to shank profile；The limbs key point information includes leg key point information； The leg key point information includes the first leg key point corresponding to lower leg area；It is described to the limbs detection information pair The limbs region answered carries out image procossing, including：To the third leg profile point information and/or first leg key point The corresponding lower leg area of information carries out the stretch processing towards first direction, or carries out towards opposite to the first direction The compression processing of second direction.
Specifically, lower leg area is knee to the region between ankle；Third leg profile point information corresponds to lower leg region The outer profile and Internal periphery in domain；First leg key point information corresponds to the skeleton point of lower leg area.In the present embodiment, using figure Distortion of image algorithm carries out stretching or compression processing according to leg direction to lower leg area.Here, leg direction includes first direction And second direction, first direction are the direction that knee is directed toward foot；Second direction is the direction that foot is directed toward knee.Then using figure Distortion of image algorithm carries out stretch processing according to the first direction to the lower leg area, or is compressed according to second direction Processing, thus elongation or the brachycnemic length that contracts.
In one embodiment, the limbs contour point information includes waist contour point information；The waist contour point information Including the first waist profile point sub-information relevant to the leg area of the target object；The limbs key point information includes Waist key point information；The waist key point information includes that the first waist relevant to the leg area of the target object closes Key point sub-information；It is described that image procossing is carried out to the corresponding limbs region of the limbs contour point information, including：To described first Waist profile point sub-information and/or the corresponding part lumbar region of the first waist key point sub-information are carried out towards third party To compression processing, or carry out towards the fourth direction opposite with the third direction stretch processing, to be promoted or be reduced The corresponding part waist profile of the first waist profile point sub-information.
Specifically, as the first waist profile point sub-information relevant to leg area and/or the first waist key idea Information, in one embodiment, can be using " stringcourse " (the corresponding reference line of minimum widith that " stringcourse " is waist) as Lumbar region is divided into two parts, the corresponding waist contour point information in lower half portion therein up and down, i.e. the first waist by line of demarcation Contouring point sub-information is the waist contour point information of lower half portion；First waist key point sub-information is the waist of lower half portion Key point information.In the present embodiment, for the accounting for promoting or reducing leg, it can be shortened by way of change " stringcourse " above the waist Accounting, promote the accounting of the lower part of the body, thus visually elongate leg ratio.
It is described that the first waist profile point sub-information and/or the first waist key idea are believed in practical application It ceases corresponding part lumbar region and carries out compression or stretch processing.By taking compression processing as an example, anamorphose algorithm is specifically used To the first waist profile point sub-information and/or the corresponding part lumbar region direction of the first waist key point sub-information Third direction carries out compression processing；Wherein, the third direction can be headward direction, or the side of direction and head To the direction with specific acute angle, it can be understood as, head direction upward when, the third direction can be tiltedly on Side, i.e., by compressing the part lumbar region to promote " stringcourse ".Correspondingly, corresponding to the first waist profile point sub-information Part lumbar region carry out stretch processing, specifically using anamorphose algorithm to the first waist profile point sub-information pair The part lumbar region answered carries out stretch processing towards fourth direction；Wherein, the fourth direction can be for by the side to head To, or by with the direction on head have specific acute angle direction, it can be understood as, head direction upward when, The fourth direction can be obliquely downward, to achieve the effect that reduce " stringcourse ".
In one embodiment, the limbs contour point information includes waist contour point information；The limbs key point information Including waist key point information；It is described that image procossing is carried out to the corresponding limbs region of the limbs contour point information, including：Base The middle line of lumbar region is determined in the waist contour point information, and the waist contour point information and/or waist key point are believed It ceases corresponding lumbar region and carries out compression processing towards the direction of the middle line according to two sides waist profile；Alternatively, to the waist Contouring point information and/or the corresponding lumbar region of waist key point information are according to the middle line towards the side of two sides waist profile To progress stretch processing.
Wherein, the middle line that lumbar region is determined based on the waist contour point information, including：Based on the waist wheel The both sides of the edge of the lumbar region of exterior feature point information representation determine the middle line of lumbar region.Further according to both sides of the edge towards middle line Direction carry out compression processing, so as to shorten the width of lumbar region, namely shorten between the both sides of the edge of lumbar region away from From the distance is the shortest distance on waist one side edge profile on any point to waist other side edge contour.
In one embodiment, the anamorphose algorithm of the embodiment of the present invention is deformed for the different parts in limbs region In treatment process, using different deformation parameters；For example, for corresponding first deformation parameter of deformation process of leg area, needle Corresponding second deformation parameter of the deformation process of pair of arm regions, corresponds to third deformation parameter for the deformation process of lumbar region. Wherein, the first deformation parameter, the second deformation parameter and third deformation parameter are different.Such as in one embodiment, the third Deformation parameter is greater than first deformation parameter.
In one embodiment, the limbs contour point information includes thoracic contours point information；The limbs key point information Including chest key point information；It is described that image procossing is carried out to the corresponding limbs region of the limbs contour point information, including：Needle The chest area corresponding to thoracic contours point information and/or the chest key point information carries out following anamorphose processing At least one of：Stretch processing, compression processing, enhancing processing.
Specifically, identifying the profile point of chest two sides, the wheel based on chest two sides based on the thoracic contours point information Exterior feature point determines the central point of chest；It is radius choosing by the profile point in the center of circle, central point to chest two sides of the central point of chest Take border circular areas.By taking stretcher strain is handled as an example, centered on the central point, the radius of the border circular areas carries out stretching change outward Shape processing.It is female character that the image procossing mode of the present embodiment, which is particularly suitable for target object, can be directed to the chest of female character The image procossing of portion's realization " chest enlarge " effect.In addition, also compression processing can be carried out for chest area, it is with the central point The radial inward of the heart, the border circular areas carries out compressive deformation processing.
In practical application, the processing for chest area further includes enhancing processing, and enhancing processing is specifically feature enhancing Processing.Wherein, the feature enhancing processing specifically includes：Object information is added in the chest area；Alternatively, identifying described The object information of chest area adjusts the corresponding display properties parameter of the object information.Specifically, the object information is yin Corresponding shadow data is also added in the chest area by shadow data, alternatively, the corresponding display of regulating object information belongs to Property parameter, the display properties parameter are specifically as follows contrast level parameter, that is, adjust the contrast of the object information；Specifically Increase the contrast of the object information, to increase the three-dimensional degree of chest area, namely has the effect of " chest enlarge ".
In another embodiment, the limbs contour point information includes thoracic contours point information；The limbs key point letter Breath includes chest key point information；It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information, including：Needle It liquefies at least partly region in thoracic contours point information and/or the corresponding chest area of the chest key point information Filter processing.
Specifically, the present embodiment carries out anamorphose processing to chest area using liquefaction filter mode, can specifically be based on Pushing away, drawing, rotating, reflecting, folding in liquefaction filter mode and expansion fashion zoom in or out the chest area, are special The processing such as sign enhancing or decrease.
It is described that image procossing is carried out to the corresponding limbs region of the limbs detection information in the present embodiment, including：It is based on The first kind deformation parameter that each pair of point in the limbs region is answered is to the corresponding limbs region of the limbs contour point information Carry out anamorphose processing；Wherein, the first kind deformation parameter is formed with corresponding point to the limbs contour point information The distance between contour edge variation and change.
In one embodiment, described that image procossing is carried out to the corresponding limbs region of the limbs detection information, generate the Two images, including：The limbs profile point is believed based on the first kind deformation parameter that each pair of point in the limbs region is answered It ceases corresponding limbs region and carries out anamorphose processing, obtain the first processing result；To in the first image, remove the target At least partly background area other than object region carry out image procossing, image covering treatment or according to it is described at least partly The feature of background area generates the processing of respective image, obtains second processing result；Based on first processing result and described Second processing result generates the second image.
Wherein, it is described using described image deformation algorithm in the first image, remove the target object region At least partly background area in addition carries out anamorphose processing, including：Based on described at least partly each of background area The corresponding second class deformation parameter of point carries out anamorphose at least partly background area using described image deformation algorithm Processing；Wherein, the second class deformation parameter is with corresponding point to the distance between the contour edge of the target object Change and exponentially variation again.
Specifically, the anamorphose algorithm in the present embodiment is the profile formed with the limbs contour point information of target object Edge carries out deformation process to the corresponding deformation parameter of the distance between contour edge as benchmark, according to each point；Wherein, right In the point in target object, it can be understood as the point with personage, corresponding deformation parameter are first kind deformation parameter；And it is right In the point outside target object namely the point in background area, corresponding deformation parameter is the second class deformation parameter.
For first kind deformation parameter, change with the variation of corresponding point to the distance between contour edge；And it is right Variation in the second class deformation parameter, with the variation of corresponding point to the distance between contour edge exponentially again.It can be with It is interpreted as, the second class deformation parameter, compared to first kind deformation parameter, if corresponding point is to the variation of the distance between contour edge Identical, then the variable quantity of the second class deformation parameter is bigger, to reduce the influence to background area, so that image processing effect is more For naturally, more smooth natural in particular for the processing near contour edge.
Pair in the present embodiment, the anamorphose processing for background area can be small-scale anamorphose and handle, i.e., Part background area is handled；Wherein, the part background area is the region of the contour edge close to target object, that is, Determining and multiple points of the contour edge in the background area of preset threshold；Part background area is determined based on multiple put Domain；The part background area is carried out at deformation according to corresponding second class deformation parameter using described image deformation algorithm Reason.
It can also include image other than anamorphose processing for the processing of background area in the embodiment of the present invention Covering treatment or the processing that respective image is generated according to the feature of at least partly background area.
Wherein, described image covering treatment, including：When limbs region adjusted is greater than the limbs region before adjusting, At least partly background area described in the limbs region overlay adjusted.Specifically, if being directed to the image procossing of target object It is " become fat " processing, namely after carrying out stretch processing for the limbs region of target object, then compared to the limb before adjustment processing Body region, limbs region adjusted can cover the limbs region before adjustment and covering part background area.In present embodiment Anamorphose processing can not be carried out for background area, the will be only generated behind limbs region coverage fraction adjusted background area Two images.
The feature of at least partly background area generates the processing of respective image, including：When limbs region adjusted When less than limbs region before adjustment, new background area is generated according at least partly background area, by the new background area Fill the area of absence that the limbs region adjusted is formed in domain.Specifically, if the image procossing for target object is " to become It is thin " processing, namely for target object limbs region carry out compression processing after, then compared to adjustment processing before limbs area Domain, the limbs region that limbs region adjusted can be less than before adjustment make background area form area of absence.Based on this, this reality It applies in example and feature identification is carried out at least partly background area, new background area is generated based on the feature identified, to fill out Fill the area of absence；It is appreciated that being to fill the area of absence based on the feature identified.
Standard parameter is also configured in the anamorphose algorithm of the embodiment of the present invention；As an implementation, the mark The parameter that the limbs region of quasi- parameter list is bright treated target object meets, namely when using anamorphose algorithm to limbs area It is terminated after making limbs region meet the standard parameter after domain progress deformation process and deformation process is carried out to limbs region；Make For another embodiment, the standard parameter shows the adjustment ratio in the limbs region of target object, namely when using image Deformation algorithm makes the adjustment variable quantity in limbs region meet the adjustment ratio after handling limbs region.
In one embodiment, the limbs contour point information includes contour point information corresponding with pending area；It is described The corresponding limbs region of the limbs detection information is handled using image processing algorithm, including：Identify the profile point The type of the corresponding pending area of information, the type based on the pending area add object in the pending area Information；Alternatively, identifying the object information in the corresponding pending area of the contour point information, it is corresponding to adjust the object information Display properties parameter.
Mainly the muscle relevant range of target object is handled in the present embodiment, then the target object pending district The relevant contour point information in domain includes at least one of：Thoracic contours point information, abdomen contour point information, arm geometry point letter Breath, leg profile point information, back contour point information.
Specifically, the embodiment of the present invention may include " increasing muscle " and " building up muscle " to the processing of muscle relevant range Two ways, so-called " increase muscle " refers to increasing muscle in the region of not muscle；So-called " building up muscle " refers to The muscle of script is had the effect of becoming larger in the region for having muscle.
Based on this, as an implementation, identify that the contour point information is corresponding wait locate using image processing algorithm The type in region is managed, the type based on the pending area adds object information in the pending area.Wherein, described The type of pending area characterizes the position of the corresponding target object of corresponding contour point information；It is appreciated that chest, abdomen, The positions such as arm, leg, back correspond to different types.Further, if partially having at least two sub-portions, at least two A sub-portion corresponds to different types；For example, leg includes two sub-portions of thigh and shank, then the two sub-portions are corresponding not Same type.
Further, for the type of pending area, object information corresponding with the type is added to pending district In domain；Wherein, the object information is the shadow data for characterizing muscle region, and also corresponding shadow data is added to wait locate It manages in region.For example, then object information is the corresponding shadow data of abdominal muscles when pending area is abdomen area, it will The shadow data is added to the corresponding position of abdomen area.
As another embodiment, the corresponding pending area of the contour point information is identified using image processing algorithm In object information, adjust the corresponding display properties parameter of the object information.
It is similar to aforementioned embodiments, in present embodiment, the shadow data of the object information characterization muscle region, i.e., Identify the muscle region in the corresponding pending area of the contour point information；For example, when the pending area is abdomen When region, the muscle region in abdomen area is identified.Further, the corresponding display properties parameter of regulating object information, institute It states display properties parameter and is specifically as follows contrast level parameter, that is, adjust the contrast of the object information；Described in specifically increasing The contrast of object information, to the three-dimensional degree in the region that has the effect of building up muscle namely build up muscle.
Using the technical solution of the embodiment of the present invention, based on obtaining for the limbs detection information to the target object in image , image procossing is carried out to limbs region based on limbs detection information, realizes the automatic tune to the limbs region of target object It is whole, it is repeatedly manually operated without user, greatly improves the operating experience of user.
The embodiment of the invention also provides a kind of image processing apparatus.Fig. 2 is the image processing apparatus of the embodiment of the present invention Composed structure schematic diagram；As shown in Fig. 2, described device includes acquiring unit 21 and image processing unit 22；Wherein,
The acquiring unit 21 identifies the target object in the first image, described in acquisition for obtaining the first image The limbs detection information of target object；
Described image processing unit 22, the corresponding limb of the limbs detection information for being obtained to the acquiring unit 21 Body region carries out image procossing, generates the second image.
In the present embodiment, the limbs detection information includes limbs key point information and/or limbs contour point information；It is described Limbs key point information includes the coordinate information of limbs key point；The limbs contour point information includes the coordinate of limbs profile point Information.Wherein, the limbs key point is bone key point.
Specifically, the limbs profile point comprises at least one of the following：Arm geometry point, hand profile point, shoulder contour Point, leg profile point, foot's profile point, waist profile point, contouring head point, buttock contour point, thoracic contours point；
The limbs key point comprises at least one of the following：Arm key point, hand key point, shoulder key point, leg Key point, foot's key point, waist key point, header key point, buttocks key point, chest key point.
In one embodiment, described image processing unit 22, for believing the key point information and/or limbs profile point It ceases corresponding limbs region and carries out anamorphose processing；Wherein, the limbs region includes at least one of following region：Head Region, shoulder regions, chest area, lumbar region, seat area, arm regions, hand region, leg area, foot areas.
In one embodiment, described image processing unit 22, for the corresponding limbs region of the limbs detection information Carry out at least one of following anamorphose processing：Stretch processing, compression processing, enhancing processing.
In one embodiment, the limbs key point information includes leg key point information and/or arm key point information； The limbs contour point information includes leg profile point information and/or arm geometry point information；The leg profile point packet Include the first leg profile point information and the second leg profile point information；The first leg profile point information corresponds to leg foreign steamer It is wide；The second leg profile point information corresponds to leg Internal periphery；The arm geometry point information includes first-hand arm profile Point information and the second arm contour point information；The first arm contour point information corresponds to arm outer profile；The second-hand Arm contour point information corresponds to arm Internal periphery；
Described image processing unit 22, for executing at least one of：For the leg profile point information and/or leg Key point information corresponding leg area in portion's is according to the leg outer profile towards the direction of the leg Internal periphery to the leg Portion's outer profile carry out compression processing, and according to the leg Internal periphery towards the direction of the leg outer profile to the leg Internal periphery carries out compression processing；
For the leg profile point information and/or the corresponding leg area of leg key point information according in the leg Profile carries out stretch processing to the leg outer profile towards the direction of the leg outer profile, and according to the leg foreign steamer Exterior feature carries out stretch processing to the leg Internal periphery towards the direction of the leg Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm outer profile towards in the arm The direction of profile carries out compression processing to the arm outer profile, and according to the arm Internal periphery towards the arm foreign steamer Wide direction carries out compression processing to the arm Internal periphery；
For the corresponding arm regions of the arm geometry point information according to the arm Internal periphery towards outside the arm The direction of profile carries out stretch processing to the arm outer profile, and according to the arm outer profile towards the arm lubrication groove Wide direction carries out stretch processing to the arm Internal periphery.
In one embodiment, the limbs contour point information includes leg profile point information；The leg profile point information Third leg profile point information including corresponding to shank profile；The limbs key point information includes leg key point information； The leg key point information includes the first leg key point information corresponding to lower leg area；
Described image processing unit 22, for crucial to the third leg profile point information and/or first leg The corresponding lower leg area of point information carries out the stretch processing towards first direction, or carries out towards opposite to the first direction Second direction compression processing.
In one embodiment, the limbs contour point information includes waist contour point information；The waist contour point information Including the first waist profile point sub-information relevant to the leg area of the target object；The limbs key point information includes Waist key point information；The waist key point information includes that the first waist relevant to the leg area of the target object closes Key point sub-information；
Described image processing unit 22, for being closed to the first waist profile point sub-information and/or first waist The corresponding part lumbar region of key point sub-information carries out the compression processing towards third direction, or carries out direction and the third The stretch processing of contrary fourth direction, to promote or reduce the corresponding part waist of the first waist profile point sub-information Contouring.
In one embodiment, the limbs contour point information includes waist contour point information；The limbs key point information Including waist key point information；
Described image processing unit 22, for determining the middle line of lumbar region based on the waist contour point information, to institute Waist contour point information and/or the corresponding lumbar region of waist key point information are stated according to two sides waist profile towards the middle line Direction carry out compression processing；Or to the corresponding lumbar region of the waist contour point information according to the middle line towards two sides The direction of waist profile carries out stretch processing.
In one embodiment, the limbs contour point information includes thoracic contours point information；The limbs key point information Including chest key point information；
Described image processing unit 22, for being directed to thoracic contours point information and/or the corresponding institute of chest key point information It states chest area and carries out at least one of following anamorphose processing：Stretch processing, compression processing, enhancing processing.
In one embodiment, the limbs contour point information includes thoracic contours point information；The limbs key point information Including chest key point information；
Described image processing unit 22, for corresponding for thoracic contours point information and/or the chest key point information Chest area at least partly region carry out liquefaction filter processing.
In one embodiment, described image processing unit 22, for what is answered based on each pair of point in the limbs region First kind deformation parameter carries out anamorphose processing to the corresponding limbs region of the limbs contour point information；
Wherein, the contour edge that the first kind deformation parameter is formed with corresponding point to the limbs contour point information The distance between variation and change.
In one embodiment, described image processing unit 22 is also used to answer based on each pair of point in the limbs region First kind deformation parameter to the corresponding limbs region of the limbs contour point information carry out anamorphose processing, obtain first at Manage result；Image is carried out at least partly background area in the first image, in addition to the target object region Deformation process, image covering treatment or the processing that respective image is generated according to the feature of at least partly background area, obtain Second processing result；The second image is generated based on first processing result and the second processing result.
Wherein, described image processing unit 22, for what is answered based on each pair of point in at least partly background area Second class deformation parameter carries out anamorphose processing at least partly background area；Wherein, the second class deformation parameter Variation with the variation of corresponding point to the distance between the contour edge of the target object exponentially again.
Wherein, described image covering treatment, including：When limbs region adjusted is greater than the limbs region before adjusting, At least partly background area described in the limbs region overlay adjusted；
The feature of at least partly background area generates the processing of respective image, including：When limbs region adjusted When less than limbs region before adjustment, new background area is generated according at least partly background area, by the new background area Fill the area of absence that the limbs region adjusted is formed in domain.
In one embodiment, the limbs contour point information includes contour point information corresponding with pending area；
Described image processing unit 22 is also used to identify the type of the corresponding pending area of the contour point information, base Object information is added in the pending area in the type of the pending area；Alternatively, identifying the contour point information Object information in corresponding pending area adjusts the corresponding display properties parameter of the object information.
In the embodiment of the present invention, acquiring unit 21 and image processing unit 22 in described image processing unit, in reality It can be by the central processing unit (CPU, Central Processing Unit) in the terminal, Digital Signal Processing in Device (DSP, Digital Signal Processor), micro-control unit (MCU, Microcontroller Unit) or programmable Gate array (FPGA, Field-Programmable Gate Array) is realized.
The embodiment of the invention also provides a kind of image processing apparatus, Fig. 3 is the image processing apparatus of the embodiment of the present invention Hardware composed structure schematic diagram, as shown in figure 3, image processing apparatus includes memory 32, processor 31 and is stored in storage On device 32 and the computer program that can run on processor 31, the processor 31 realize that the present invention is real when executing described program Apply the aforementioned any one described image processing method of example.
It is appreciated that the various components in image processing apparatus are coupled by bus system 33.It is understood that bus System 33 is for realizing the connection communication between these components.Bus system 33 further includes power supply in addition to including data/address bus Bus, control bus and status signal bus in addition.But for the sake of clear explanation, various buses are all designated as bus in Fig. 3 System 33.
It is appreciated that memory 32 can be volatile memory or nonvolatile memory, may also comprise volatibility and Both nonvolatile memories.Wherein, nonvolatile memory can be read-only memory (ROM, Read Only Memory), Programmable read only memory (PROM, Programmable Read-Only Memory), Erasable Programmable Read Only Memory EPROM (EPROM, Erasable Programmable Read-Only Memory), electrically erasable programmable read-only memory The storage of (EEPROM, Electrically Erasable Programmable Read-Only Memory), magnetic random access Device (FRAM, ferromagnetic random access memory), flash memory (Flash Memory), magnetic surface are deposited Reservoir, CD or CD-ROM (CD-ROM, Compact Disc Read-Only Memory)；Magnetic surface storage can be Magnetic disk storage or magnetic tape storage.Volatile memory can be random access memory (RAM, Random Access Memory), it is used as External Cache.By exemplary but be not restricted explanation, the RAM of many forms is available, such as Static random access memory (SRAM, Static Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory), dynamic random access memory (DRAM, Dynamic Random Access Memory), Synchronous Dynamic Random Access Memory (SDRAM, Synchronous Dynamic Random Access Memory), double data speed synchronous dynamic RAM (DDRSDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), enhanced synchronous dynamic random Access memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), synchronized links Dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), direct rambus Random access memory (DRRAM, Direct Rambus Random Access Memory).Description of the embodiment of the present invention is deposited Reservoir 32 is intended to include but is not limited to the memory of these and any other suitable type.
The method that the embodiments of the present invention disclose can be applied in processor 31, or be realized by processor 31.Place Managing device 31 may be a kind of IC chip, the processing capacity with signal.During realization, each step of the above method It can be completed by the integrated logic circuit of the hardware in processor 31 or the instruction of software form.Above-mentioned processor 31 can To be general processor, DSP or other programmable logic device, discrete gate or transistor logic, discrete hardware group Part etc..Processor 31 may be implemented or execute disclosed each method, step and logic diagram in the embodiment of the present invention.It is general Processor can be microprocessor or any conventional processor etc..The step of the method in conjunction with disclosed in the embodiment of the present invention Suddenly, hardware decoding processor can be embodied directly in and execute completion, or with the hardware and software module group in decoding processor Conjunction executes completion.Software module can be located in storage medium, which is located at memory 32, and processor 31 reads storage Information in device 32, in conjunction with the step of its hardware completion preceding method.
It should be noted that：Image processing apparatus provided by the above embodiment when performing image processing, only with above-mentioned each The division progress of program module can according to need for example, in practical application and distribute above-mentioned processing by different journeys Sequence module is completed, i.e., the internal structure of device is divided into different program modules, to complete whole described above or portion Divide processing.In addition, image processing apparatus provided by the above embodiment and image processing method embodiment belong to same design, have Body realizes that process is detailed in embodiment of the method, and which is not described herein again.
In the exemplary embodiment, the embodiment of the invention also provides a kind of computer readable storage medium, for example including The memory 32 of computer program, above-mentioned computer program can be executed by the processor 31 of image processing apparatus, aforementioned to complete Step described in method.Computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, The memories such as magnetic surface storage, CD or CD-ROM；It is also possible to include the various of one of above-mentioned memory or any combination Equipment, such as mobile phone, computer, tablet device, personal digital assistant.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, this refers to Aforementioned any one described image processing method of the embodiment of the present invention is realized when order is executed by processor.
The embodiment of the invention also provides a kind of computer program product, the computer program product includes that computer can It executes instruction, after which is performed, can be realized the aforementioned described in any item images of the embodiment of the present invention The step of processing method.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only A kind of logical function partition, there may be another division manner in actual implementation, such as：Multiple units or components can combine, or It is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each composition portion Mutual coupling or direct-coupling or communication connection is divided to can be through some interfaces, the INDIRECT COUPLING of equipment or unit Or communication connection, it can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit The component shown can be or may not be physical unit, it can and it is in one place, it may be distributed over multiple network lists In member；Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated in one processing unit, it can also To be each unit individually as a unit, can also be integrated in one unit with two or more units；It is above-mentioned Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
Those of ordinary skill in the art will appreciate that：Realize that all or part of the steps of above method embodiment can pass through The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes：Movable storage device, ROM, The various media that can store program code such as RAM, magnetic or disk.
If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented Substantially the part that contributes to existing technology can be embodied in the form of software products the technical solution of example in other words, The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention. And storage medium above-mentioned includes：Movable storage device, ROM, RAM, magnetic or disk etc. are various to can store program code Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.

Claims (10)

1. a kind of image processing method, which is characterized in that the method includes：
The first image is obtained, the target object in the first image is identified, obtains the limbs detection information of the target object；
Image procossing is carried out to the corresponding limbs region of the limbs detection information, generates the second image.
2. the method according to claim 1, wherein the limbs detection information includes limbs key point information And/or limbs contour point information；
The limbs key point information includes the coordinate information of limbs key point；
The limbs contour point information includes the coordinate information of limbs profile point.
3. according to the method described in claim 2, it is characterized in that, the limbs profile point comprises at least one of the following：Arm Profile point, hand profile point, shoulder contour point, leg profile point, foot's profile point, waist profile point, contouring head point, buttocks Profile point, thoracic contours point；
The limbs key point comprises at least one of the following：Arm key point, hand key point, shoulder key point, leg are crucial Point, foot's key point, waist key point, header key point, buttocks key point, chest key point.
4. according to the method in claim 2 or 3, which is characterized in that described to the corresponding limbs of the limbs detection information Region carries out image procossing, including：
Anamorphose processing is carried out to the limbs key point information and/or the corresponding limbs region of limbs contour point information；
Wherein, the limbs region includes at least one of following region：Head zone, shoulder regions, chest area, waist area Domain, seat area, arm regions, hand region, leg area, foot areas.
5. method according to any one of claims 1 to 4, which is characterized in that described corresponding to the limbs detection information Limbs region carry out image procossing, including：Following anamorphose is carried out to the corresponding limbs region of the limbs detection information At least one of processing：Stretch processing, compression processing, enhancing processing.
6. method according to any one of claims 1 to 5, which is characterized in that described corresponding to the limbs detection information Limbs region carry out image procossing, generate the second image, including：
The first kind deformation parameter answered based on each pair of point in the limbs region is corresponding to the limbs contour point information Limbs region carries out anamorphose processing, obtains the first processing result；
Anamorphose is carried out at least partly background area in the first image, in addition to the target object region Processing, image covering treatment or the processing that respective image is generated according to the feature of at least partly background area, obtain second Processing result；
The second image is generated based on first processing result and the second processing result.
7. a kind of image processing apparatus, which is characterized in that described device includes acquiring unit and image processing unit；Wherein,
The acquiring unit identifies the target object in the first image, obtains the target pair for obtaining the first image The limbs detection information of elephant；
Described image processing unit, the corresponding limbs region of the limbs detection information for being obtained to the acquiring unit into Row image procossing generates the second image.
8. a kind of computer readable storage medium, is stored thereon with computer instruction, which is characterized in that the instruction is held by processor The step of any one of claim 1 to 6 described image processing method is realized when row.
9. a kind of image processing apparatus, can run on a memory and on a processor including memory, processor and storage Computer program, which is characterized in that the processor realizes any one of claim 1 to 6 described image when executing described program The step of processing method.
10. a kind of computer program product, which is characterized in that the computer program product includes computer executable instructions, After the computer executable instructions are performed, the step of can be realized any one of claim 1 to 6 described image processing method.
CN201810553761.8A 2018-05-31 2018-05-31 A kind of image processing method, device and computer storage medium Pending CN108830784A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810553761.8A CN108830784A (en) 2018-05-31 2018-05-31 A kind of image processing method, device and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810553761.8A CN108830784A (en) 2018-05-31 2018-05-31 A kind of image processing method, device and computer storage medium

Publications (1)

Publication Number Publication Date
CN108830784A true CN108830784A (en) 2018-11-16

Family

ID=64146642

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810553761.8A Pending CN108830784A (en) 2018-05-31 2018-05-31 A kind of image processing method, device and computer storage medium

Country Status (1)

Country Link
CN (1) CN108830784A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109712085A (en) * 2018-12-11 2019-05-03 维沃移动通信有限公司 A kind of image processing method and terminal device
CN109872283A (en) * 2019-01-18 2019-06-11 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN110264431A (en) * 2019-06-29 2019-09-20 北京字节跳动网络技术有限公司 Video beautification method, device and electronic equipment
CN110288520A (en) * 2019-06-29 2019-09-27 北京字节跳动网络技术有限公司 Image beautification method, device and electronic equipment
CN110348335A (en) * 2019-06-25 2019-10-18 平安科技（深圳）有限公司 Method, apparatus, terminal device and the storage medium of Activity recognition
CN111415306A (en) * 2020-03-11 2020-07-14 北京字节跳动网络技术有限公司 Method and device for processing human chest body beautification in picture and electronic equipment
CN111415382A (en) * 2020-03-02 2020-07-14 北京字节跳动网络技术有限公司 Method and device for processing human body arm body beautification in picture and electronic equipment
CN111460870A (en) * 2019-01-18 2020-07-28 北京市商汤科技开发有限公司 Target orientation determination method and device, electronic equipment and storage medium
CN111507142A (en) * 2019-01-31 2020-08-07 北京字节跳动网络技术有限公司 Facial expression image processing method and device and electronic equipment
WO2020220679A1 (en) * 2019-04-30 2020-11-05 北京市商汤科技开发有限公司 Method and device for image processing, and computer storage medium
WO2021128730A1 (en) * 2019-12-25 2021-07-01 北京市商汤科技开发有限公司 Image processing method and apparatus, image processing device and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537608A (en) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 Image processing method and device
CN105956997A (en) * 2016-04-27 2016-09-21 腾讯科技（深圳）有限公司 Image deformation treatment method and device
CN107154030A (en) * 2017-05-17 2017-09-12 腾讯科技（上海）有限公司 Image processing method and device, electronic equipment and storage medium
CN107203963A (en) * 2016-03-17 2017-09-26 腾讯科技（深圳）有限公司 A kind of image processing method and device, electronic equipment
CN107808137A (en) * 2017-10-31 2018-03-16 广东欧珀移动通信有限公司 Image processing method, device, electronic equipment and computer-readable recording medium
CN107909540A (en) * 2017-10-26 2018-04-13 深圳天珑无线科技有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN108062740A (en) * 2017-12-12 2018-05-22 深圳天珑无线科技有限公司 A kind of mobile terminal and its U.S. face method and system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537608A (en) * 2014-12-31 2015-04-22 深圳市中兴移动通信有限公司 Image processing method and device
CN107203963A (en) * 2016-03-17 2017-09-26 腾讯科技（深圳）有限公司 A kind of image processing method and device, electronic equipment
CN105956997A (en) * 2016-04-27 2016-09-21 腾讯科技（深圳）有限公司 Image deformation treatment method and device
CN107154030A (en) * 2017-05-17 2017-09-12 腾讯科技（上海）有限公司 Image processing method and device, electronic equipment and storage medium
CN107909540A (en) * 2017-10-26 2018-04-13 深圳天珑无线科技有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN107808137A (en) * 2017-10-31 2018-03-16 广东欧珀移动通信有限公司 Image processing method, device, electronic equipment and computer-readable recording medium
CN108062740A (en) * 2017-12-12 2018-05-22 深圳天珑无线科技有限公司 A kind of mobile terminal and its U.S. face method and system

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109712085A (en) * 2018-12-11 2019-05-03 维沃移动通信有限公司 A kind of image processing method and terminal device
CN111460870A (en) * 2019-01-18 2020-07-28 北京市商汤科技开发有限公司 Target orientation determination method and device, electronic equipment and storage medium
CN109872283A (en) * 2019-01-18 2019-06-11 维沃移动通信有限公司 A kind of image processing method and mobile terminal
CN111507142A (en) * 2019-01-31 2020-08-07 北京字节跳动网络技术有限公司 Facial expression image processing method and device and electronic equipment
US11501407B2 (en) 2019-04-30 2022-11-15 Beijing Sensetime Technology Development Co., Ltd. Method and apparatus for image processing, and computer storage medium
WO2020220679A1 (en) * 2019-04-30 2020-11-05 北京市商汤科技开发有限公司 Method and device for image processing, and computer storage medium
CN110348335A (en) * 2019-06-25 2019-10-18 平安科技（深圳）有限公司 Method, apparatus, terminal device and the storage medium of Activity recognition
CN110348335B (en) * 2019-06-25 2022-07-12 平安科技（深圳）有限公司 Behavior recognition method and device, terminal equipment and storage medium
CN110288520A (en) * 2019-06-29 2019-09-27 北京字节跳动网络技术有限公司 Image beautification method, device and electronic equipment
CN110264431A (en) * 2019-06-29 2019-09-20 北京字节跳动网络技术有限公司 Video beautification method, device and electronic equipment
CN110288520B (en) * 2019-06-29 2023-03-31 北京字节跳动网络技术有限公司 Image beautifying method and device and electronic equipment
WO2021128730A1 (en) * 2019-12-25 2021-07-01 北京市商汤科技开发有限公司 Image processing method and apparatus, image processing device and storage medium
US11734829B2 (en) 2019-12-25 2023-08-22 Beijing Sensetime Technology Development Co., Ltd. Method and device for processing image, and storage medium
CN111415382A (en) * 2020-03-02 2020-07-14 北京字节跳动网络技术有限公司 Method and device for processing human body arm body beautification in picture and electronic equipment
CN111415382B (en) * 2020-03-02 2022-04-05 北京字节跳动网络技术有限公司 Method and device for processing human body arm body beautification in picture and electronic equipment
CN111415306A (en) * 2020-03-11 2020-07-14 北京字节跳动网络技术有限公司 Method and device for processing human chest body beautification in picture and electronic equipment

Similar Documents

Publication Publication Date Title
CN108830784A (en) A kind of image processing method, device and computer storage medium
CN108830783A (en) A kind of image processing method, device and computer storage medium
CN108830200A (en) A kind of image processing method, device and computer storage medium
US11893828B2 (en) System and method for image de-identification
CN108765274A (en) A kind of image processing method, device and computer storage media
CN110136051A (en) A kind of image processing method, device and computer storage medium
CN107507216B (en) Method and device for replacing local area in image and storage medium
WO2020177394A1 (en) Image processing method and apparatus
CN109377544A (en) A kind of face three-dimensional image generating method, device and readable medium
CN107564080B (en) Face image replacement system
CN110349081A (en) Generation method, device, storage medium and the electronic equipment of image
CN108198184A (en) The method and system of contrastographic picture medium vessels segmentation
CN108960020A (en) Information processing method and information processing equipment
US20210097268A1 (en) Image processing method and apparatus, and computer storage medium
CN109801380A (en) A kind of method, apparatus of virtual fitting, storage medium and computer equipment
CN110390632A (en) Image processing method, device, storage medium and terminal based on dressing template
CN109378068A (en) A kind of method for automatically evaluating and system of Therapeutic Effects of Nasopharyngeal
CN110942422A (en) Image processing method and device and computer storage medium
CN113658324A (en) Image processing method and related equipment, migration network training method and related equipment
CN111105348A (en) Image processing method and apparatus, image processing device, and storage medium
CN108564058A (en) A kind of image processing method, device and computer readable storage medium
WO2020085922A1 (en) Digital character blending and generation system and method
KR20230012091A (en) Method and program for modeling personalized breast implant
CN112169331B (en) Object control method and device
CN110111240A (en) A kind of image processing method based on strong structure, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20181116