CN110210283A - A kind of image processing method and system based on the application that changes the outfit - Google Patents
A kind of image processing method and system based on the application that changes the outfit Download PDFInfo
- Publication number
- CN110210283A CN110210283A CN201910282682.2A CN201910282682A CN110210283A CN 110210283 A CN110210283 A CN 110210283A CN 201910282682 A CN201910282682 A CN 201910282682A CN 110210283 A CN110210283 A CN 110210283A
- Authority
- CN
- China
- Prior art keywords
- outfit
- region
- changes
- application
- block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present invention proposes a kind of image processing method and system based on the application that changes the outfit.The neck length that the method for the present invention needs to keep using the ratio-dependent of face carries out neck area according to clothes neck portion height and changes the outfit, to promote the visual effect to change the outfit.
Description
Technical field
The present invention relates to processing technology field more particularly to a kind of image processing methods and system based on the application that changes the outfit.
Background technique
The prior art is in the practical application to change the outfit, and people keep good person's face when being often merely observed that replacement clothes, suddenly
The ratio of neck is omited, to generate very poor visual experience.
Summary of the invention
The purpose of the embodiment of the present invention is to propose a kind of image processing method based on the application that changes the outfit, it is intended to which solution changes the outfit
The ratio of neck, the problem of visual effect difference are had ignored in.
The embodiments of the present invention are implemented as follows, a kind of image processing method based on the application that changes the outfit, which comprises
Divide the neck holding area in face;
Skin color location detection is carried out to neck holding area;Whether full setting identifier carrys out mark in Skin color location detection
Sufficient colour of skin condition;
It is changed the outfit according to identifier and clothes neck portion height.
Further, before the neck holding area divided in face further include:
Face datection and facial feature localization are carried out according to the acquisition equipment rotatability for the application that changes the outfit;
Whether succeeded according to Face datection or facial feature localization, determines whether to start the application that changes the outfit.
Further, the basis change the outfit application acquisition equipment rotatability carry out Face datection and facial feature localization before
Further include:
Further, if judgement MB of prediction frame does not occur intra-frame prediction block, judgement changes the outfit without effective coverage incision
Camera, without starting the application that changes the outfit;If there is intra-frame prediction block in MB of prediction frame,
According to the stay time in new incision region, determine whether that there are effective coverages to cut the camera to change the outfit.
The another object of the embodiment of the present invention is to propose a kind of image processing system based on the application that changes the outfit, the system
Including
Neck holding area dividing device, for dividing the neck holding area in face;
Skin color location detection module, for carrying out Skin color location detection to neck holding area;In Skin color location detection
Setting identifier comes whether mark meets colour of skin condition;
Change the outfit module, for being changed the outfit according to identifier and clothes neck portion height.
Further, the system also includes
Face datection and facial feature localization device, for carrying out Face datection according to the acquisition equipment rotatability for the application that changes the outfit
And facial feature localization;
Whether starting changes the outfit using determination module, for being succeeded according to Face datection or facial feature localization, determine whether to open
Move dress application.
Further, the system also includes
First determination processing module, if determining for judging that MB of prediction frame does not occur intra-frame prediction block without effective district
The camera to change the outfit is cut in domain, without starting the application that changes the outfit;If intra-frame prediction block occurs in MB of prediction frame, sentence into effective coverage
Determine device;
Effective coverage decision maker determines whether that there are effective coverages to cut for the stay time according to new incision region
Enter the camera to change the outfit.
The new incision region fingering enters the new object area of camera pickup area.
Beneficial effects of the present invention
The present invention proposes a kind of image processing method and system based on the application that changes the outfit.The method of the present invention utilizes the ratio of face
Example determines the neck length for needing to keep, and carries out neck area according to clothes neck portion height and changes the outfit, to promote the vision effect to change the outfit
Fruit.
Detailed description of the invention
Fig. 1 is a kind of image processing method flow chart based on the application that changes the outfit of the preferred embodiment of the present invention;
Fig. 2 is a kind of method flow diagram for dividing the neck holding area in face of the embodiment of the present invention;
Fig. 3 is a kind of method flow diagram for starting the application that changes the outfit of the embodiment of the present invention;
Fig. 4 is a kind of side for the method that face area to be tested is obtained using the acquisition equipment of property without spin of the embodiment of the present invention
Method flow chart;
Fig. 5 is a kind of method flow diagram for determining incision and changing the outfit using effective coverage of the embodiment of the present invention;
Fig. 6 is the stay time that a kind of basis of the embodiment of the present invention newly cuts region, determines whether that there are effective coverages to cut
Enter the method flow diagram of the camera to change the outfit;
Fig. 7 is a kind of image processing system figure based on the application that changes the outfit of the preferred embodiment of the present invention;
Fig. 8 is a kind of neck holding area dividing device structure chart of the embodiment of the present invention;
Fig. 9 is a kind of structure drawing of device for starting the application that changes the outfit of the embodiment of the present invention;
Figure 10 is that property acquisition equipment obtains face area to be tested without spin for a kind of utilization provided in an embodiment of the present invention
Structure drawing of device;
Figure 11 is a kind of structure drawing of device for determining incision and changing the outfit using effective coverage of the embodiment of the present invention;
Figure 12 is effective coverage of embodiment of the present invention decision maker structure chart.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, right below in conjunction with drawings and examples
The present invention is further elaborated, and for ease of description, only parts related to embodiments of the present invention are shown.It should manage
Solution, the specific embodiment that this place is described are used only for explaining the present invention, be not intended to limit the invention.
The present invention proposes a kind of image processing method and system based on the application that changes the outfit.The method of the present invention utilizes the ratio of face
Example determines the neck length for needing to keep, and carries out neck area according to clothes neck portion height and changes the outfit, to promote the vision effect to change the outfit
Fruit.
Embodiment one
Fig. 1 is a kind of image processing method based on the application that changes the outfit of the embodiment of the present invention, comprising the following steps:
S101 divides the neck holding area in face;
The embodiment of the present invention provides the method for the neck holding area in a kind of division face as shown in Figure 2, specific to wrap
Include following steps:
Step C1: eye, lip, mouth, human face region ranks parameter set are calculated;
In implementation column of the present invention, the parameter set includes eye lip line-spacing hec, eye distance de, lip centre row number cc, face area
Domain maximum line number lf;
Step C2: line number is belonged into the first value range section, row number belong to the second value range section region be divided into
Neck holding area;
In embodiments of the present invention, the first value range section is set as [lf, lf+hec*kk2], the second value range area
Between be set as [cc-de, cc+de];Wherein, kk2Indicate the second proportionality coefficient, general optional 3/5 < kk2≤1。
S102 carries out Skin color location detection to neck holding area;Identifier is set in Skin color location detection to indicate
Whether colour of skin condition is met;
The Skin color location detection method is the method for the art routine;In the embodiment of the present invention, if meeting the colour of skin
Condition, then it is 1 that identifier, which is arranged,;If being unsatisfactory for colour of skin condition, it is set as 0.It is appreciated that identifier may also set up other numbers
Value;
S103 changes the outfit according to identifier and clothes neck portion height;
The embodiment of the present invention provides a kind of method to change the outfit according to clothes neck portion height, specifically:
If replace clothes be it is polo-neck, be arranged clothes placement starting line number position be human face region maximum line number lf;
If replace clothes be it is non-polo-neck, first setting clothes place starting line number position be neck holding area line number take
It is worth the maximum value lf+hec*kk of range2;Then the brightness of the neck holding area of colour of skin condition, each chromatic component will be unsatisfactory for
The luminance mean value of unified human face region, corresponding each chromatic component mean value are replaced.
Further, the embodiment of the present invention is before step S101, also provides a kind of starting as shown in Figure 3 and changes the outfit application
Method, specifically includes the following steps:
S201 carries out Face datection and facial feature localization according to the acquisition equipment rotatability for the application that changes the outfit;
In embodiments of the present invention, if the acquisition equipment for the application that changes the outfit does not have rotatability, first with without spin
Property acquisition equipment obtain face area to be tested, then utilize conventional Face datection method progress Face datection and facial feature localization;It is no
Then, full images Face datection and facial feature localization directly are carried out using conventional Face datection method.
The application that changes the outfit of the acquisition of the property without spin equipment can be the application that changes the outfit of fixing camera or fixed scene;
The fixing camera applicating example such as game machine that changes the outfit changes the outfit, and game machine acquires user's head portrait using fixing camera;
As shown in Figure 4 a kind of, which is provided, in the embodiment of the present invention obtains face area to be detected using the acquisition equipment of property without spin
Domain specifically includes:
Step B1: the luminance difference of the respective pixel of front and back two field pictures is calculated;
Step B2: the region by difference not equal to 0 divides the new personage region for entering picture into;
Step B3: the line width hr in the new personage region into picture is calculated;
Step B4: the new personage region upper part region into picture is divided into face area to be tested;
Wherein, on the personage region that the new personage region upper part region into picture newly enters picture for upper end
Hold hr*kk1Region;kk1Indicate the first proportionality coefficient, general optional 1/7≤kk1≤1/5。
Whether S202 succeeds according to Face datection or facial feature localization, determines whether to start the application that changes the outfit.
In the embodiment of the present invention, if Face datection or facial feature localization are unsuccessful, determine to take the photograph without what face incision changed the outfit
As head, without the operation that changes the outfit;Otherwise, start the application that changes the outfit.
Further, the embodiment of the present invention also provides a kind of judgement incision as shown in Figure 5 before starting changes the outfit application
The method to change the outfit using effective coverage, specifically includes the following steps:
S301 determines to cut the camera to change the outfit, nothing without effective coverage if MB of prediction frame does not occur intra-frame prediction block
The application that changes the outfit need to be started;If intra-frame prediction block occurs in MB of prediction frame, the intra-frame prediction block for recording current MB of prediction frame is total
Number is N, remembers that the broadcasting sequence number of current MB of prediction frame is t, into S302;
S302 determines whether that there are effective coverages to cut the camera to change the outfit according to the stay time in new incision region;
Specifically: the camera to change the outfit is cut in effective coverage if it exists, then starts the application that changes the outfit;Otherwise, it is determined that without effective
The camera to change the outfit is cut in region, without the operation that changes the outfit.
The new incision region fingering enters the new object area of camera pickup area;
Wherein, the embodiment of the present invention provides the stay time that basis as shown in FIG. 6 newly cuts region, determines whether exist
The specific method is as follows for the camera that effective coverage incision changes the outfit:
Step A1: intra-frame prediction block is divided into first set;
Ω1={ blockT, 1, blockT, 2..., blockT, N}。
Step A2: it in subsequent frames, is obtained respectively with first set Ω1In in each piece of block for reference block, play sequence
Number maximum piece, it is divided into second set;
Ω2={ pblockT1,1, pblockT2,2..., pblockTN, N}。
Step A3: play time difference set is calculated;
Ω3={ (t1-t)/fps, (t2-t)/fps ..., (tN-t)/fps }.
Step A4: according to play time difference decision condition, determine whether that there are effective coverages to cut the camera to change the outfit;
In the embodiment of the present invention, play time difference decision condition is sum (sign (Ω3(i)|Ω3(i) > Thres1)) >
Thres2* N determines that there are effective coverages to cut the camera to change the outfit, starting changes the outfit if meeting play time difference decision condition
Using;Otherwise, it is determined that the camera to change the outfit is cut without effective coverage, without starting the application that changes the outfit.
Wherein, blockT, nIndicate n-th of intra-frame prediction block of t frame, 1≤n≤N;pblockTn, nIndicate it is all with
blockT, nTo have the block of maximum broadcasting sequence number, the broadcasting sequence of frame locating for the first representation in components of subscript block in reference block
Number;Ω3(i) i-th of element of the set, 1≤i≤N are indicated;Sum () indicates summation operation;Thres1、Thres2The first, second threshold value is respectively indicated, generally
Thres1≥5、Thres2> 0.9;Fps indicates sampling frame per second.
Embodiment two
Fig. 7 is a kind of image processing system figure based on the application that changes the outfit of the preferred embodiment of the present invention;The system packet
It includes:
Neck holding area dividing device, for dividing the neck holding area in face;
Skin color location detection module, for carrying out Skin color location detection to neck holding area;In Skin color location detection
Setting identifier comes whether mark meets colour of skin condition;
Change the outfit module, for being changed the outfit according to identifier and clothes neck portion height.
Fig. 8 is neck holding area dividing device structure chart of the embodiment of the present invention;The neck holding area dividing device
Including
Ranks parameter calculating module, for calculating eye, lip, mouth, human face region ranks parameter set;
In implementation column of the present invention, the parameter set includes eye lip line-spacing hec, eye distance de, lip centre row number cc, face area
Domain maximum line number lf;
Neck holding area delimit module, and for line number to be belonged to the first value range section, row number belongs to the second value
The region of range intervals is divided into neck holding area;
In embodiments of the present invention, the first value range section is set as [lf, lf+hec*kk2], the second value range area
Between be set as [cc-de, cc+de];Wherein, kk2Indicate the second proportionality coefficient, general optional 3/5 < kk2≤1。
Specifically, if the apparatus for changing for judge to replace clothes be it is polo-neck, the starting line number that clothes is placed is set
Position is human face region maximum line number lf;If replace clothes be it is non-polo-neck, first setting clothes place starting line number position be
The maximum value lf+hec*kk of neck holding area line number value range2;Then the neck holding area of colour of skin condition will be unsatisfactory for
Brightness, the luminance mean value of the unified human face region of each chromatic component, corresponding each chromatic component mean value replace.
Fig. 9 is a kind of structure drawing of device for starting the application that changes the outfit of the embodiment of the present invention;Described device includes
Face datection and facial feature localization device, for carrying out Face datection according to the acquisition equipment rotatability for the application that changes the outfit
And facial feature localization;
Specifically, if the acquisition equipment for the application that changes the outfit does not have rotatability, equipment is acquired first with property without spin
Face area to be tested is obtained, then carries out Face datection and facial feature localization using conventional Face datection method;Otherwise, it directly utilizes
Conventional Face datection method carries out full images Face datection and facial feature localization.
The application that changes the outfit of the acquisition of the property without spin equipment can be the application that changes the outfit of fixing camera or fixed scene;
The fixing camera applicating example such as game machine that changes the outfit changes the outfit, and game machine acquires user's head portrait using fixing camera;
Whether starting changes the outfit using determination module, for being succeeded according to Face datection or facial feature localization, determine whether to open
Move dress application.
Specifically, if Face datection or facial feature localization are unsuccessful, determine to cut the camera to change the outfit without face, be not necessarily to
Change the outfit operation;Otherwise, start the application that changes the outfit.
Further, Figure 10 is provided in an embodiment of the present invention a kind of to be checked using the acquisition equipment acquisition face of property without spin
Survey the structure drawing of device in region;Described device includes:
Luminance difference computing module, the luminance difference of the respective pixel for calculating front and back two field pictures;
New persona region division module divides the new personage region for entering picture into for the region by difference not equal to 0;
New persona region line width computing module, for calculating the line width hr in the new personage region into picture;
Face area to be tested delimit module, for the new personage region upper part region into picture to be divided into
Face area to be tested;
Wherein, on the personage region that the new personage region upper part region into picture newly enters picture for upper end
Hold hr*kk1Region;kk1Indicate the first proportionality coefficient, general optional 1/7≤kk1≤1/5。
Further, Figure 11 is a kind of device knot for determining incision and changing the outfit using effective coverage provided in an embodiment of the present invention
Composition;Described device includes
First determination processing module, if determining for judging that MB of prediction frame does not occur intra-frame prediction block without effective district
The camera to change the outfit is cut in domain, without starting the application that changes the outfit;If intra-frame prediction block occurs in MB of prediction frame, current interframe is recorded
The intra-frame prediction block sum for predicting frame is N, remembers that the broadcasting sequence number of current MB of prediction frame is t, determines subsequently into effective coverage
Device;
Effective coverage decision maker determines whether that there are effective coverages to cut for the stay time according to new incision region
Enter the camera to change the outfit;
Specifically, the camera to change the outfit is cut in effective coverage if it exists, then starts the application that changes the outfit;Otherwise, it is determined that without effective
The camera to change the outfit is cut in region, without the operation that changes the outfit.
The new incision region fingering enters the new object area of camera pickup area;
Further, Figure 12 is effective coverage of embodiment of the present invention decision maker detailed structure view.Described device
First set of blocks division module, for intra-frame prediction block to be divided into first set;
Ω1={ blockT, 1, blockT, 2..., blockT, N}。
Second set of blocks division module, in subsequent frames, being obtained respectively with first set Ω1In each piece for reference
In the block of block, maximum piece of broadcasting sequence number, it is divided into second set;
Ω2={ pblockT1,1, pblockT2,2..., pblockTN, N}。
Play time difference computing module, for calculating play time difference set;
Ω3={ (t1-t)/fps, (t2-t)/fps ..., (tN-t)/fps }.
Third effective coverage determination module, for determining whether that there are effective coverages according to play time difference decision condition
Cut the camera to change the outfit;
In the embodiment of the present invention, play time difference decision condition is sum (sign (Ω3(i)|Ω3(i) > Thres1)) >
Thres2* N, if meeting play time difference decision condition, there are effective coverages for judgement to cut the camera to change the outfit, and starting is changed
Dress application;Otherwise, it is determined that the camera to change the outfit is cut without effective coverage, without starting the application that changes the outfit.
Wherein, blockT, nIndicate n-th of intra-frame prediction block of t frame, 1≤n≤N;pblockTn, nIndicate it is all with
blockT, nTo have the block of maximum broadcasting sequence number, the broadcasting sequence of frame locating for the first representation in components of subscript block in reference block
Number;Ω3(i) i-th of element of the set, 1≤i≤N are indicated;Sum () indicates summation operation;Thres1、Thres2The first, second threshold value is respectively indicated, generally
Thres1≥5、Thres2> 0.9;Fps indicates sampling frame per second.
It will be understood by those skilled in the art that implement the method for the above embodiments be can
With what is completed by program instruction related hardware, the program be can be stored in a computer readable storage medium,
The storage medium can be ROM, RAM, disk, CD etc..
The size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, and the execution of each process is suitable
Sequence should be determined by its function and internal logic, and the implementation process of the embodiments of the invention shall not be constituted with any limitation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (15)
1. a kind of image processing method based on the application that changes the outfit, which is characterized in that the described method includes:
Divide the neck holding area in face;
Skin color location detection is carried out to neck holding area;Setting identifier comes whether mark meets skin in Skin color location detection
Vitta part;
It is changed the outfit according to identifier and clothes neck portion height.
2. the image processing method as described in claim 1 based on the application that changes the outfit, which is characterized in that in the division face
Before neck holding area further include:
Face datection and facial feature localization are carried out according to the acquisition equipment rotatability for the application that changes the outfit;
Whether succeeded according to Face datection or facial feature localization, determines whether to start the application that changes the outfit.
3. the image processing method as claimed in claim 2 based on the application that changes the outfit, which is characterized in that the basis changes the outfit application
Acquisition equipment rotatability carry out Face datection and facial feature localization before further include:
If judgement MB of prediction frame does not occur intra-frame prediction block, determine to cut the camera to change the outfit without effective coverage, without opening
Move dress application;If there is intra-frame prediction block in MB of prediction frame,
According to the stay time in new incision region, determine whether that there are effective coverages to cut the camera to change the outfit.
4. the image processing method as described in claim 1 based on the application that changes the outfit, which is characterized in that in the division face
Neck holding area includes
Step C1: eye, lip, mouth, human face region ranks parameter set are calculated;
The parameter set includes eye lip line-spacing hec, eye distance de, lip centre row number cc, human face region maximum line number lf;
Step C2: line number is belonged into the first value range section, row number belong to the second value range section region be divided into neck
Holding area;
First value range section is set as [lf, lf+hec*kk2], the second value range section is set as [cc-de, cc+de];
Wherein, kk2Indicate the second proportionality coefficient, 3/5 < kk2≤1。
5. the image processing method as described in claim 1 based on the application that changes the outfit, which is characterized in that
It is described to be changed the outfit according to clothes neck portion height progress neck area specifically:
If replace clothes be it is polo-neck, be arranged clothes placement starting line number position be human face region maximum line number lf;
If replace clothes be it is non-polo-neck, first setting clothes place starting line number position be neck holding area line number value model
The maximum value lf+hec*kk enclosed2;Then brightness, each chromatic component that the neck holding area of colour of skin condition will be unsatisfactory for are unified
It is replaced with the luminance mean value of human face region, corresponding each chromatic component mean value.
6. the image processing method as claimed in claim 2 based on the application that changes the outfit, which is characterized in that if the acquisition for the application that changes the outfit
Equipment does not have rotatability, then face area to be tested is obtained first with the acquisition equipment of property without spin, then using conventional
Face datection method carries out Face datection and facial feature localization;Otherwise, the inspection of full images face directly is carried out using conventional Face datection method
Survey and facial feature localization;
The method for obtaining face area to be tested using the acquisition equipment of property without spin, specifically includes:
Step B1: the luminance difference of the respective pixel of front and back two field pictures is calculated;
Step B2: the region by difference not equal to 0 divides the new personage region for entering picture into;
Step B3: the line width hr in the new personage region into picture is calculated;
Step B4: the new personage region upper part region into picture is divided into face area to be tested;
Wherein, the new personage region upper part region into picture is the personage region upper end that upper end newly enters picture
hr*kk1Region;kk1Indicate the first proportionality coefficient, 1/7≤kk1≤1/5。
7. the image processing method as claimed in claim 3 based on the application that changes the outfit, which is characterized in that
The new incision region fingering enters the new object area of camera pickup area.
8. the image processing method as claimed in claim 7 based on the application that changes the outfit, which is characterized in that
The basis newly cuts the stay time in region, determines whether that there are the specific sides that the camera to change the outfit is cut in effective coverage
Method is as follows:
Step A1: intra-frame prediction block is divided into first set;
Ω1={ blockT, 1, blockT, 2..., blockT, N};
Step A2: it in subsequent frames, is obtained respectively with first set Ω1In in each piece of block for reference block, broadcasting sequence number is maximum
Block, be divided into second set;
Ω2={ pblockT1,1, pblockT2,2..., pblockTN, N};
Step A3: play time difference set is calculated;
Ω3={ (t1-t)/fps, (t2-t)/fps ..., (tN-t)/fps };
Step A4: according to play time difference decision condition, determine whether that there are effective coverages to cut the camera to change the outfit;
Play time difference decision condition is sum (sign (Ω3(i)|Ω3(i) > Thres1)) > Thres2* N, if meet broadcasting
Between poor decision condition, then determine to cut the camera to change the outfit there are effective coverage, starting changes the outfit application;Otherwise, it is determined that without effective
The camera to change the outfit is cut in region, without starting the application that changes the outfit;
Wherein, blockT, nIndicate n-th of intra-frame prediction block of t frame, 1≤n≤N;pblockTn, nIndicate all with blockT, n
To have the block of maximum broadcasting sequence number, the broadcasting sequence number of frame locating for the first representation in components of subscript block in reference block;Ω3
(i) i-th of element of the set, 1≤i≤N are indicated;Sum () indicates summation operation;Thres1、Thres2Respectively indicate the first, second threshold value, Thres1≥
5、Thres2> 0.9;Fps indicates sampling frame per second, and the intra-frame prediction block sum of current MB of prediction frame is N, current inter-prediction
The broadcasting sequence number of frame is t.
9. a kind of image processing system based on the application that changes the outfit, which is characterized in that the system comprises
Neck holding area dividing device, for dividing the neck holding area in face;
Skin color location detection module, for carrying out Skin color location detection to neck holding area;It is arranged in Skin color location detection
Identifier comes whether mark meets colour of skin condition;
Change the outfit module, for being changed the outfit according to identifier and clothes neck portion height.
10. the image processing system as claimed in claim 8 based on the application that changes the outfit, which is characterized in that
The neck holding area dividing device includes
Ranks parameter calculating module, for calculating eye, lip, mouth, human face region ranks parameter set;
In implementation column of the present invention, the parameter set includes eye lip line-spacing hec, eye distance de, lip centre row number cc, and human face region is most
Big line number lf;
Neck holding area delimit module, and for line number to be belonged to the first value range section, row number belongs to the second value range
The region in section is divided into neck holding area;
First value range section is set as [lf, lf+hec*kk2], the second value range section is set as [cc-de, cc+de];
Wherein, kk2Indicate the second proportionality coefficient, 3/5 < kk2≤1。
11. the image processing system as claimed in claim 10 based on the application that changes the outfit, which is characterized in that
If the apparatus for changing for judge to replace clothes be it is polo-neck, the starting line number position that clothes placement is arranged is face area
Domain maximum line number lf;If replace clothes be it is non-polo-neck, first setting clothes place starting line number position be neck holding area
The maximum value lf+hec*kk of line number value range2;Then brightness, the colors of the neck holding area of colour of skin condition will be unsatisfactory for
Degree component unifies the luminance mean value of human face region, corresponding each chromatic component mean value to replace.
12. the image processing system as claimed in claim 9 based on the application that changes the outfit, which is characterized in that
The system also includes
Face datection and facial feature localization device, for carrying out Face datection and five according to the acquisition equipment rotatability for the application that changes the outfit
Official's positioning;
If the acquisition equipment for the application that changes the outfit does not have rotatability, it is to be checked that face is obtained first with the acquisition equipment of property without spin
Region is surveyed, then carries out Face datection and facial feature localization using conventional Face datection method;Otherwise, conventional Face datection is directly utilized
Method carries out full images Face datection and facial feature localization.
Whether starting changes the outfit using determination module, for being succeeded according to Face datection or facial feature localization, determine whether to start and change
Dress application.
13. the image processing system as claimed in claim 10 based on the application that changes the outfit, which is characterized in that the Face datection and
Facial feature localization device further includes face area to be tested acquisition device, including
Luminance difference computing module, the luminance difference of the respective pixel for calculating front and back two field pictures;
New persona region division module divides the new personage region for entering picture into for the region by difference not equal to 0;
New persona region line width computing module, for calculating the line width hr in the new personage region into picture;
Face area to be tested delimit module, for the new personage region upper part region into picture to be divided into face
Area to be tested;
Wherein, the new personage region upper part region into picture is the personage region upper end that upper end newly enters picture
hr*kk1Region;kk1Indicate the first proportionality coefficient, 1/7≤kk1≤1/5。
14. the image processing system as claimed in claim 9 based on the application that changes the outfit, which is characterized in that the system also includes
First determination processing module, if judgement is cut without effective coverage for judging that MB of prediction frame does not occur intra-frame prediction block
Enter the camera to change the outfit, without starting the application that changes the outfit;If intra-frame prediction block occurs in MB of prediction frame, determine to fill into effective coverage
It sets;
Effective coverage decision maker determines whether to cut there are effective coverage and change for the stay time according to new incision region
The camera of dress.
The new incision region fingering enters the new object area of camera pickup area.
15. the image processing system as claimed in claim 13 based on the application that changes the outfit, which is characterized in that
Effective coverage decision maker includes:
First set of blocks division module, for intra-frame prediction block to be divided into first set;
Ω1={ blockT, 1, blockT, 2..., blockT, N};
Second set of blocks division module, in subsequent frames, being obtained respectively with first set Ω1In each piece for reference block
In block, maximum piece of broadcasting sequence number, it is divided into second set;
Ω2={ pblockT1,1, pblockT2,2..., pblockTN, N};
Play time difference computing module, for calculating play time difference set;
Ω3={ (t1-t)/fps, (t2-t)/fps ..., (tN-t)/fps };
Third effective coverage determination module, for determining whether that there are effective coverage incisions according to play time difference decision condition
The camera to change the outfit;
Play time difference decision condition is sum (sign (Ω3(i)|Ω3(i) > Thres1)) > Thres2* N, if meet broadcasting
Between poor decision condition, then determine to cut the camera to change the outfit there are effective coverage, starting changes the outfit application;Otherwise, it is determined that without effective
The camera to change the outfit is cut in region, without starting the application that changes the outfit;
Wherein, blockT, nIndicate n-th of intra-frame prediction block of t frame, 1≤n≤N;pblockTn, nIndicate all with blockT, n
To have the block of maximum broadcasting sequence number, the broadcasting sequence number of frame locating for the first representation in components of subscript block in reference block;Ω3
(i) i-th of element of the set, 1≤i≤N are indicated;Sum () indicates summation operation;Thres1、Thres2Respectively indicate the first, second threshold value, Thres1≥
5、Thres2> 0.9;Fps indicates sampling frame per second, and the intra-frame prediction block sum of current MB of prediction frame is N, current inter-prediction
The broadcasting sequence number of frame is t.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910282682.2A CN110210283B (en) | 2019-04-09 | 2019-04-09 | Image processing method and system based on reloading application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910282682.2A CN110210283B (en) | 2019-04-09 | 2019-04-09 | Image processing method and system based on reloading application |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110210283A true CN110210283A (en) | 2019-09-06 |
CN110210283B CN110210283B (en) | 2021-05-14 |
Family
ID=67785176
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910282682.2A Active CN110210283B (en) | 2019-04-09 | 2019-04-09 | Image processing method and system based on reloading application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110210283B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114468973A (en) * | 2022-01-21 | 2022-05-13 | 广州视域光学科技股份有限公司 | Intelligent vision detection system |
CN114565521A (en) * | 2022-01-17 | 2022-05-31 | 北京新氧科技有限公司 | Image restoration method, device, equipment and storage medium based on virtual reloading |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090115777A1 (en) * | 2005-11-15 | 2009-05-07 | Reyes Infográfica S.L. | Method of Generating and Using a Virtual Fitting Room and Corresponding System |
CN102497556A (en) * | 2011-12-26 | 2012-06-13 | 深圳市融创天下科技股份有限公司 | Time-variation-degree-based scene switching detection method, device and equipment |
CN103020580A (en) * | 2011-09-23 | 2013-04-03 | 无锡中星微电子有限公司 | Rapid human face detection method |
CN103870797A (en) * | 2012-12-14 | 2014-06-18 | 联想(北京)有限公司 | Information processing method and electronic apparatus |
CN106998470A (en) * | 2016-01-25 | 2017-08-01 | 华为技术有限公司 | Coding/decoding method, coding method, decoding device and encoding device |
CN107048890A (en) * | 2017-05-25 | 2017-08-18 | 美的集团股份有限公司 | Automatic defogging method, controller, Intelligent mirror and computer-readable recording medium |
CN107851278A (en) * | 2015-07-15 | 2018-03-27 | 华为技术有限公司 | A kind of virtual fitting system and method being used for based on video source modeling reality in mobile phone |
CN107925759A (en) * | 2015-06-05 | 2018-04-17 | 英迪股份有限公司 | Method and apparatus for coding and decoding infra-frame prediction |
CN108230297A (en) * | 2017-11-30 | 2018-06-29 | 复旦大学 | A kind of collocation of colour appraisal procedure replaced based on clothes |
US20180240280A1 (en) * | 2015-08-14 | 2018-08-23 | Metail Limited | Method and system for generating an image file of a 3d garment model on a 3d body model |
CN109446967A (en) * | 2018-10-22 | 2019-03-08 | 深圳市梦网百科信息技术有限公司 | A kind of method for detecting human face and system based on compression information |
-
2019
- 2019-04-09 CN CN201910282682.2A patent/CN110210283B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090115777A1 (en) * | 2005-11-15 | 2009-05-07 | Reyes Infográfica S.L. | Method of Generating and Using a Virtual Fitting Room and Corresponding System |
CN103020580A (en) * | 2011-09-23 | 2013-04-03 | 无锡中星微电子有限公司 | Rapid human face detection method |
CN102497556A (en) * | 2011-12-26 | 2012-06-13 | 深圳市融创天下科技股份有限公司 | Time-variation-degree-based scene switching detection method, device and equipment |
CN103870797A (en) * | 2012-12-14 | 2014-06-18 | 联想(北京)有限公司 | Information processing method and electronic apparatus |
CN107925759A (en) * | 2015-06-05 | 2018-04-17 | 英迪股份有限公司 | Method and apparatus for coding and decoding infra-frame prediction |
CN107851278A (en) * | 2015-07-15 | 2018-03-27 | 华为技术有限公司 | A kind of virtual fitting system and method being used for based on video source modeling reality in mobile phone |
US20180240280A1 (en) * | 2015-08-14 | 2018-08-23 | Metail Limited | Method and system for generating an image file of a 3d garment model on a 3d body model |
CN106998470A (en) * | 2016-01-25 | 2017-08-01 | 华为技术有限公司 | Coding/decoding method, coding method, decoding device and encoding device |
CN107048890A (en) * | 2017-05-25 | 2017-08-18 | 美的集团股份有限公司 | Automatic defogging method, controller, Intelligent mirror and computer-readable recording medium |
CN108230297A (en) * | 2017-11-30 | 2018-06-29 | 复旦大学 | A kind of collocation of colour appraisal procedure replaced based on clothes |
CN109446967A (en) * | 2018-10-22 | 2019-03-08 | 深圳市梦网百科信息技术有限公司 | A kind of method for detecting human face and system based on compression information |
Non-Patent Citations (1)
Title |
---|
张艳丽: "人脸检测系统的算法研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114565521A (en) * | 2022-01-17 | 2022-05-31 | 北京新氧科技有限公司 | Image restoration method, device, equipment and storage medium based on virtual reloading |
CN114468973A (en) * | 2022-01-21 | 2022-05-13 | 广州视域光学科技股份有限公司 | Intelligent vision detection system |
CN114468973B (en) * | 2022-01-21 | 2023-08-11 | 广州视域光学科技股份有限公司 | Intelligent vision detection system |
Also Published As
Publication number | Publication date |
---|---|
CN110210283B (en) | 2021-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105654471B (en) | Augmented reality AR system and method applied to internet video live streaming | |
CN105243371B (en) | A kind of detection method, system and the camera terminal of face U.S. face degree | |
CN101609500B (en) | Quality estimation method of exit-entry digital portrait photos | |
WO2018103244A1 (en) | Live streaming video processing method, device, and electronic apparatus | |
CN108650524A (en) | Video cover generation method, device, computer equipment and storage medium | |
US20130079911A1 (en) | Method and device for generating morphing animation | |
TWI599221B (en) | Automatic advertisement inserting and displaying method implemented on the basis of computer vision | |
CN101390128B (en) | Detecting method and detecting system for positions of face parts | |
CN110210283A (en) | A kind of image processing method and system based on the application that changes the outfit | |
CN111013150A (en) | Game video editing method, device, equipment and storage medium | |
CN104581127B (en) | Method, terminal and head-worn display equipment for automatically adjusting screen brightness | |
US20140047457A1 (en) | Information notification apparatus that notifies information of data of motion | |
US7916902B2 (en) | Album creating apparatus, album creating method, and album creating program | |
CN108310766A (en) | Data processing method and device, storage medium, processor and terminal | |
CN108537026A (en) | application control method, device and server | |
CN107392883A (en) | The method and system that video display dramatic conflicts degree calculates | |
CN105872802A (en) | Video playing method and device | |
CN108304148A (en) | A kind of method and apparatus that multi-screen splicing is shown | |
CN110418148A (en) | Video generation method, video generating device and readable storage medium storing program for executing | |
CN110012284A (en) | A kind of video broadcasting method and device based on helmet | |
CN103391447A (en) | Safety depth guarantee and adjustment method in three-dimensional (3D) program shot switching | |
EP4198772A1 (en) | Method and device for making music recommendation | |
CN109788311B (en) | Character replacement method, electronic device, and storage medium | |
CN101075344B (en) | Method for merging image format based on index color | |
CN106231278A (en) | Method for processing video frequency and television system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant after: Shenzhen mengwang video Co.,Ltd. Address before: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant before: SHENZHEN MONTNETS ENCYCLOPEDIA INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |