CN109615585A - Posture antidote and device, electronic equipment, the storage medium of human body image - Google Patents
Posture antidote and device, electronic equipment, the storage medium of human body image Download PDFInfo
- Publication number
- CN109615585A CN109615585A CN201811271289.5A CN201811271289A CN109615585A CN 109615585 A CN109615585 A CN 109615585A CN 201811271289 A CN201811271289 A CN 201811271289A CN 109615585 A CN109615585 A CN 109615585A
- Authority
- CN
- China
- Prior art keywords
- human body
- image
- body image
- value
- posture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000729 antidote Substances 0.000 title claims abstract description 28
- 238000003709 image segmentation Methods 0.000 claims abstract description 23
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 9
- 229940075522 antidotes Drugs 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 30
- 238000000034 method Methods 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of posture antidotes of human body image, comprising: carries out image segmentation to human body image collected, human body image is divided into background area and human region；Human body image is placed in preset rectangular coordinate system, coordinate value of the pixel of human region in rectangular coordinate system is obtained；According to coordinate value, human region corresponding human body center line in rectangular coordinate system is determined；Straight line fitting is carried out to human body center line, obtains human body central line；Human body central line is calculated in the tilt angle of vertical direction；Rotation map transformation is carried out to human body image in rectangular coordinate system according to tilt angle, the first human body image after obtaining posture correction.The invention also discloses posture apparatus for correcting, electronic equipment, the storage mediums of a kind of human body image.The posture antidote and device of human body image of the invention, realize the model not positive to collected posture the correction of clothing image, and then ensure model the bandwagon effect of clothing image.
Description
Technical field
The present invention relates to the posture antidote and device of technical field of image processing more particularly to a kind of human body image,
Electronic equipment, storage medium.
Background technique
Virtual fitting refers to allows virtual model that real user is replaced to try the clothes sold on the net on using computer technology, leads to
It crosses virtual model and tries the effect of presentation on online clothes are chosen to user and form reference, buy suitable clothes convenient for user.
Existing virtual fitting system need to store a large amount of filmed model in advance clothing image, however model clothing
Due to extraneous various disturbing factors in shooting process, be easy to appear shoot the model come clothing image posture not just, Jin Erying
Ring model the bandwagon effect of clothing image.
Summary of the invention
It is a primary object of the present invention to solve in the prior art model clothing image because of posture not just, influence bandwagon effect
The technical issues of.
To achieve the above object, the present invention provides a kind of posture antidote of human body image, comprising:
Image segmentation is carried out to human body image collected, the human body image is divided into background area and human body area
Domain；
The human body image is placed in preset rectangular coordinate system, obtains the pixel of the human region described straight
Coordinate value in angular coordinate system；
According to the coordinate value, the human region corresponding human body center line in the rectangular coordinate system is determined；
Straight line fitting is carried out to the human body center line, obtains human body central line；
The human body central line is calculated in the tilt angle of vertical direction；
Rotation map transformation is carried out to the human body image in the rectangular coordinate system according to the tilt angle, is obtained
The first human body image after posture correction.
Preferably, described that image is carried out to human body image collected in the posture antidote of the human body image
Segmentation, is divided into background area for the human body image and human region specifically includes:
The human body image is split using K-means clustering algorithm, background color is determined according to segmentation result；
Single channel image is created, the single channel image of background color corresponding region is assigned a value of the first value, to background color
Single channel image other than corresponding region is assigned a value of second value, obtains the bianry image of the human body image；
According to the bianry image, the background area and the human region are determined in the human body image.
Preferably, described according to the coordinate value in the posture antidote of the human body image, determine the human body
Region corresponding human body center line in the rectangular coordinate system specifically includes:
According to the coordinate value, the identical pixel of ordinate value is divided into one group, and calculate all pixels in each group
The average value of the abscissa value of point；
For each group, being searched in the rectangular coordinate system with the ordinate value of pixel in respective sets is the first vertical seat
Scale value take the average value as the first coordinate points of the first abscissa value；
Definition is the human body center line by the line that first coordinate points are formed.
Preferably, in the posture antidote of the human body image, it is described according to the tilt angle at the right angle
Rotation map transformation is carried out to the human body image in coordinate system, after the human body image after obtaining posture correction further include:
The human body image is handled using bilinear interpolation algorithm, first human body image that obtains that treated.
In addition, to achieve the above object, the present invention also provides a kind of posture apparatus for correcting of human body image, comprising:
The human body image is divided by image segmentation module for carrying out image segmentation to human body image collected
Background area and human region；
Coordinate obtaining module obtains the human body area for the human body image to be placed in preset rectangular coordinate system
Coordinate value of the pixel in domain in the rectangular coordinate system；
Center line determining module, for determining the human region in the rectangular coordinate system according to the coordinate value
Corresponding human body center line；
Straight line fitting module obtains human body central line for carrying out straight line fitting to the human body center line；
Computing module is tilted, for calculating the human body central line in the tilt angle of vertical direction；
Rotation transform module, for being carried out in the rectangular coordinate system to the human body image according to the tilt angle
Rotation map transformation, the first human body image after obtaining posture correction.
Preferably, in the posture apparatus for correcting of the human body image, described image segmentation module includes:
Image segmentation unit is tied for being split using K-means clustering algorithm to the human body image according to segmentation
Fruit determines background color；
The single channel image of background color corresponding region is assigned a value of by image assignment unit for creating single channel image
First value is assigned a value of second value to the single channel image other than background color corresponding region, obtains the two-value of the human body image
Image；
Area determination unit, for according to the bianry image, determined in the human body image background area and
The human region.
Preferably, in the posture apparatus for correcting of the human body image, the center line determining module includes:
Pixel grouped element, for according to the coordinate value, the identical pixel of ordinate value to be divided into one group；
Average calculation unit, for calculating the average value of the abscissa value of all pixels point in each group；
Coordinate points searching unit is searched for being directed to each group in the rectangular coordinate system with pixel in respective sets
Ordinate value be the first ordinate value, with the average value be the first abscissa value the first coordinate points；
Centreline definition unit, for defining the line formed by first coordinate points as the human body center line.
Preferably, the posture apparatus for correcting of the human body image further include:
Image processing module, for being handled using bilinear interpolation algorithm the human body image, after obtaining processing
The first human body image.
In addition, to achieve the above object, it is described the present invention also provides a kind of electronic equipment, including memory and processor
Memory is stored with the computer program that can be run on a processor, and the processor is realized such as when executing the computer program
The step of posture antidote of the upper human body image.
In addition, to achieve the above object, the present invention also provides a kind of storage mediums, it is stored thereon with computer program, institute
State the step in the posture antidote for realizing human body image as described above when computer program is executed by processor.
The posture antidote and device of human body image provided by the present invention, by being carried out to human body image collected
The human body image is divided into background area and human region by image segmentation；The human body image is placed in preset right angle
In coordinate system, coordinate value of the pixel of the human region in the rectangular coordinate system is obtained；According to the coordinate value, really
The fixed human region corresponding human body center line in the rectangular coordinate system；It is quasi- that straight line is carried out to the human body center line
It closes, obtains human body central line；The human body central line is calculated in the tilt angle of vertical direction；According to the tilt angle
Rotation map transformation is carried out to the human body image in the rectangular coordinate system, the first human body image after obtaining posture correction
Mode, realize the model not positive to collected posture the correction of clothing image, and then ensure model the exhibition of clothing image
Show effect.
Detailed description of the invention
Fig. 1 is the flow diagram of the posture antidote first embodiment of human body image of the invention；
Fig. 2 is the present invention human body image schematic diagram collected for needing posture to correct；
Fig. 3 is the specific refinement flow diagram of step S10 in Fig. 1；
Fig. 4 is the bianry image schematic diagrames of human body image in Fig. 2；
Fig. 5 is the specific refinement flow diagram of step S30 in Fig. 1；
Fig. 6 is the corresponding human body center line schematic diagram of human body image in Fig. 4；
Fig. 7 is the corresponding human body central line schematic diagram of human body center line in Fig. 6；
Fig. 8 is that human body image obtains the first human body image schematic diagram after posture correction in Fig. 2；
Fig. 9 is the program module schematic diagram of the posture apparatus for correcting first embodiment of human body image of the invention；
Figure 10 is the specific elaborator module diagram of image segmentation module in Fig. 9；
Figure 11 is the specific elaborator module diagram of the center line determining module of Fig. 9；
Figure 12 is another program module schematic diagram of posture apparatus for correcting of human body image of the invention；
Figure 13 is the hardware entities schematic diagram of one embodiment of a kind of electronic equipment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Below in conjunction with Figure of description, preferred embodiment of the present invention will be described, it should be understood that described herein
Preferred embodiment only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention, and in the absence of conflict, this hair
The feature in embodiment and embodiment in bright can be combined with each other.
The present invention proposes a kind of posture antidote first embodiment of human body image.Referring to Fig.1, Fig. 1 is of the invention
The flow diagram of the posture antidote first embodiment of human body image.In the first embodiment, the appearance of the human body image
State antidote includes:
Step S10: to human body image collected carry out image segmentation, by the human body image be divided into background area and
Human region.
Referring to fig. 2, Fig. 2 is the present invention human body image schematic diagram collected for needing posture to correct.
Referring to Fig. 3, Fig. 3 is the specific refinement flow diagram of step S10 in Fig. 1.Step S10 is to being adopted in the present embodiment
The human body image of collection carries out image segmentation, and the human body image is divided into background area and human region specifically includes:
Step S11: being split the human body image using K-means clustering algorithm, is determined and is carried on the back according to segmentation result
Scape color.
Step S12: the single channel image of background color corresponding region is assigned a value of the first value by creation single channel image, right
Single channel image other than background color corresponding region is assigned a value of second value, obtains the bianry image of the human body image.
Referring to fig. 4, Fig. 4 is the bianry image schematic diagrames of human body image in Fig. 2.First value described in the present embodiment is 0, institute
Stating second value is 255.
Step S13: according to the bianry image, the background area and the human body area are determined in the human body image
Domain.
After the present embodiment obtains the bianry image of the human body image, human body wheel can be determined in the human body image
Wide edge, and then the background area and the human region are determined in the human body image according to human body contour outline edge.
Step S20: the human body image is placed in preset rectangular coordinate system, obtains the pixel of the human region
Coordinate value in the rectangular coordinate system.
Step S30: according to the coordinate value, determine the human region in the rectangular coordinate system in corresponding human body
Heart line.
Referring to Fig. 5, Fig. 5 is the specific refinement flow diagram of step S30 in Fig. 1.Step is according in the present embodiment
Coordinate value determines that the human region corresponding human body center line in the rectangular coordinate system specifically includes:
Step S31: according to the coordinate value, the identical pixel of ordinate value is divided into one group, and calculate in each group
The average value of the abscissa value of all pixels point.
Step S32: for each group, lookup is in the rectangular coordinate system with the ordinate value of pixel in respective sets
First ordinate value take the average value as the first coordinate points of the first abscissa value.
Step S33: definition is the human body center line by the line that first coordinate points are formed.
Referring to Fig. 6, Fig. 6 is the corresponding human body center line schematic diagram of human body image in Fig. 4.The present embodiment need to be in the step
The first all coordinate points from top to bottom are linked in sequence before S33, the line for connecting formation is regarded as by first coordinate
The line that point is formed.
Step S40: straight line fitting is carried out to the human body center line, obtains human body central line.
Referring to Fig. 7, Fig. 7 is the corresponding human body central line schematic diagram of human body center line in Fig. 6.This step S40 is specifically adopted
Straight line fitting is carried out to the human body center line with least square method, obtains the human body central line.
Step S50: the human body central line is calculated in the tilt angle of vertical direction.
Step S60: rotation map is carried out to the human body image in the rectangular coordinate system according to the tilt angle
Transformation, the first human body image after obtaining posture correction.
Referring to Fig. 8, Fig. 8 is that human body image obtains the first human body image schematic diagram after posture correction in Fig. 2.
Further, above-described embodiment is right in the rectangular coordinate system according to the tilt angle in the step S60
The human body image carries out rotation map transformation, further includes handling as follows after the human body image after obtaining posture correction: using
Bilinear interpolation algorithm handles the human body image, first human body image that obtains that treated.
Due to carrying out meeting in rotation map conversion process to the human body image so that human body image distortion, the present embodiment
The human body image is handled by using bilinear interpolation algorithm, leads to human figure to make up rotation map conversion process
The distortion of picture, and then can ensure the subsequent bandwagon effect of human body image.
The posture antidote of human body image provided by above-described embodiment, by carrying out figure to human body image collected
As segmentation, the human body image is divided into background area and human region；The human body image is placed in preset right angle to sit
In mark system, coordinate value of the pixel of the human region in the rectangular coordinate system is obtained；According to the coordinate value, determine
The human region corresponding human body center line in the rectangular coordinate system；Straight line fitting is carried out to the human body center line,
Obtain human body central line；The human body central line is calculated in the tilt angle of vertical direction；Existed according to the tilt angle
Rotation map transformation is carried out to the human body image in the rectangular coordinate system, the first human body image after obtaining posture correction
Mode, realize the model not positive to collected posture the correction of clothing image, and then ensure model the displaying of clothing image
Effect.
The present invention further provides a kind of posture apparatus for correcting first embodiments of human body image.It is this referring to Fig. 9, Fig. 9
The program module schematic diagram of the posture apparatus for correcting first embodiment of the human body image of invention.In the first embodiment, the people
The posture apparatus for correcting 100 of body image includes: image segmentation module 110, coordinate obtaining module 120, center line determining module
130, straight line fitting module 140, inclination computing module 150, rotation transform module 160.Wherein, described image divides module 110,
For carrying out image segmentation to human body image collected, the human body image is divided into background area and human region, is joined
See that Fig. 2, Fig. 2 are the present invention human body image schematic diagram collected for needing posture to correct.The coordinate obtaining module 120,
For the human body image to be placed in preset rectangular coordinate system, the pixel for obtaining the human region is sat at the right angle
Coordinate value in mark system.The center line determining module 130, for determining the human region in institute according to the coordinate value
State corresponding human body center line in rectangular coordinate system.The straight line fitting module 140 is straight for carrying out to the human body center line
Line fitting, obtains human body central line.The inclination computing module 150, for calculating the human body central line in vertical side
To tilt angle.The rotation transform module 160, for according to the tilt angle in the rectangular coordinate system to described
Human body image carries out rotation map transformation, the first human body image after obtaining posture correction.
Referring to Figure 10, Figure 10 is the specific elaborator module diagram of image segmentation module in Fig. 9.Institute in the present embodiment
Stating image segmentation module 110 includes: image segmentation unit 111, image assignment unit 112, area determination unit 113.Wherein, institute
Image segmentation unit 111 is stated, for being split using K-means clustering algorithm to the human body image, according to segmentation result
Determine background color.Described image assignment unit 112, for creating single channel image, by the single-pass of background color corresponding region
Road image is assigned a value of the first value, is assigned a value of second value to the single channel image other than background color corresponding region, obtains the people
The bianry image of body image.The area determination unit 113 is used for according to the bianry image, in the human body image really
The fixed background area and the human region.
Referring to fig. 4, Fig. 4 is the bianry image schematic diagrames of human body image in Fig. 2.First value described in the present embodiment is 0, institute
Stating second value is 255.After the present embodiment obtains the bianry image of the human body image, it can be determined in the human body image
Human body contour outline edge, and then the background area and the human body area are determined in the human body image according to human body contour outline edge
Domain.
Referring to Figure 11, Figure 11 is the specific elaborator module diagram of the center line determining module of Fig. 9.In the present embodiment
The center line determining module 130 includes: pixel grouped element 131, average calculation unit 132, coordinate points searching unit
133, centreline definition unit 134.Wherein, the pixel grouped element 131 is used for according to the coordinate value, by ordinate
It is worth identical pixel and is divided into one group.Average calculation unit 132, for calculating the abscissa value of all pixels point in each group
Average value.Coordinate points searching unit 133 is searched for being directed to each group in the rectangular coordinate system with picture in respective sets
The ordinate value of vegetarian refreshments is the first ordinate value, take the average value as the first coordinate points of the first abscissa value.Center line is fixed
Adopted unit 134, for defining the line formed by first coordinate points as the human body center line.
Referring to Fig. 6, Fig. 6 is the corresponding human body center line schematic diagram of human body image in Fig. 4.The present embodiment need to be by all
One coordinate points from top to bottom are linked in sequence, and the line for connecting formation regards the line formed by first coordinate points as.
Referring to Fig. 7, Fig. 7 is the corresponding human body central line schematic diagram of human body center line in Fig. 6.The straight line fitting module
140 specifically carry out straight line fitting to the human body center line using least square method, obtain the human body central line.
Referring to Fig. 8, Fig. 8 is that human body image obtains the first human body image schematic diagram after posture correction in Fig. 2.
Referring to Figure 12, Figure 12 is another program module schematic diagram of posture apparatus for correcting of human body image of the invention.It is above-mentioned
The posture apparatus for correcting 100 of human body image described in embodiment further include: image processing module 170.Wherein, described image is handled
Module 170, for being handled the human body image using bilinear interpolation algorithm, first human figure that obtains that treated
Picture.
Due to carrying out meeting in rotation map conversion process to the human body image so that human body image distortion, the present embodiment
The human body image is handled by using bilinear interpolation algorithm, leads to human figure to make up rotation map conversion process
The distortion of picture, and then can ensure the subsequent bandwagon effect of human body image.
The posture apparatus for correcting 100 of human body image provided by above-described embodiment, by human body image collected into
The human body image is divided into background area and human region by row image segmentation；The human body image is placed in preset straight
In angular coordinate system, coordinate value of the pixel of the human region in the rectangular coordinate system is obtained；According to the coordinate value,
Determine the human region corresponding human body center line in the rectangular coordinate system；It is quasi- that straight line is carried out to the human body center line
It closes, obtains human body central line；The human body central line is calculated in the tilt angle of vertical direction；According to the tilt angle
Rotation map transformation is carried out to the human body image in the rectangular coordinate system, the first human body image after obtaining posture correction
Mode, realize the model not positive to collected posture the correction of clothing image, and then ensure model the exhibition of clothing image
Show effect.
The present invention also proposes a kind of electronic equipment, including memory and processor, and the memory, which is stored with, to be handled
The computer program run on device, the processor realize the appearance of human body image as described above when executing the computer program
The step of state antidote.
The present invention also proposes a kind of storage medium, is stored thereon with computer program, the computer program is by processor
The step in the posture antidote of human body image as described above is realized when execution.
It need to be noted that: the description of the embodiment of storage medium described above and the electronic equipment, and it is above-mentioned
The description of the posture antidote embodiment of human body image be it is similar, have the posture antidote with the human body image real
Apply the similar beneficial effect of example.For undisclosed skill in the embodiment of the storage medium and the electronic equipment of the invention
Art details please refers to the description of the posture antidote embodiment of the above-mentioned human body image of the present invention and understands.
It should be noted that Figure 13 is that the hardware entities of one embodiment of a kind of electronic equipment of the invention are shown referring to Figure 13
It is intended to.The hardware entities of the electronic equipment 1300 include: processor 1301, communication interface 1302 and storage in one embodiment
Device 1303.Wherein, the overall operation of the usual controlling electronic devices 1300 of processor 1301.The communication interface 1302 can make electricity
Sub- equipment 1300 passes through network and other terminals or server communication.The memory 1303 is configured to storage by processor 1301
It is to be processed or can also to cache each module in device 1301 and electronic equipment 1300 to be processed for executable instruction and application
The data of processing can be realized by flash memory (FLASH) or random access storage device (Random Access Memory, RAM).
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of posture antidote of human body image characterized by comprising
Image segmentation is carried out to human body image collected, the human body image is divided into background area and human region；
The human body image is placed in preset rectangular coordinate system, the pixel for obtaining the human region is sat at the right angle
Coordinate value in mark system；
According to the coordinate value, the human region corresponding human body center line in the rectangular coordinate system is determined；
Straight line fitting is carried out to the human body center line, obtains human body central line；
The human body central line is calculated in the tilt angle of vertical direction；
Rotation map transformation is carried out to the human body image in the rectangular coordinate system according to the tilt angle, obtains posture
The first human body image after correction.
2. the posture antidote of human body image according to claim 1, which is characterized in that described to human body collected
Image carries out image segmentation, and the human body image is divided into background area and human region specifically includes:
The human body image is split using K-means clustering algorithm, background color is determined according to segmentation result；
Single channel image is created, the single channel image of background color corresponding region is assigned a value of the first value, it is corresponding to background color
Single channel image other than region is assigned a value of second value, obtains the bianry image of the human body image；
According to the bianry image, the background area and the human region are determined in the human body image.
3. the posture antidote of human body image according to claim 1 or 2, which is characterized in that described according to the seat
Scale value determines that the human region corresponding human body center line in the rectangular coordinate system specifically includes:
According to the coordinate value, the identical pixel of ordinate value is divided into one group, and calculates all pixels point in each group
The average value of abscissa value；
For each group, search in the rectangular coordinate system with the ordinate value of pixel in respective sets as the first ordinate
Value take the average value as the first coordinate points of the first abscissa value；
Definition is the human body center line by the line that first coordinate points are formed.
4. the posture antidote of human body image according to claim 3, which is characterized in that described according to the inclination angle
Degree in the rectangular coordinate system to the human body image carry out rotation map transformation, obtain posture correction after human body image it
Afterwards further include:
The human body image is handled using bilinear interpolation algorithm, first human body image that obtains that treated.
5. a kind of posture apparatus for correcting of human body image characterized by comprising
The human body image is divided into background for carrying out image segmentation to human body image collected by image segmentation module
Region and human region；
Coordinate obtaining module obtains the human region for the human body image to be placed in preset rectangular coordinate system
Coordinate value of the pixel in the rectangular coordinate system；
Center line determining module, for determining that the human region is corresponding in the rectangular coordinate system according to the coordinate value
Human body center line；
Straight line fitting module obtains human body central line for carrying out straight line fitting to the human body center line；
Computing module is tilted, for calculating the human body central line in the tilt angle of vertical direction；
Rotation transform module, for being rotated in the rectangular coordinate system to the human body image according to the tilt angle
Mapping transformation, the first human body image after obtaining posture correction.
6. the posture apparatus for correcting of human body image according to claim 5, which is characterized in that described image divides module packet
It includes:
Image segmentation unit, it is true according to segmentation result for being split using K-means clustering algorithm to the human body image
Determine background color；
The single channel image of background color corresponding region is assigned a value of first for creating single channel image by image assignment unit
Value, is assigned a value of second value to the single channel image other than background color corresponding region, obtains the bianry image of the human body image；
Area determination unit, for according to the bianry image, determining the background area and described in the human body image
Human region.
7. the posture apparatus for correcting of human body image according to claim 5 or 6, which is characterized in that the center line determines
Module includes:
Pixel grouped element, for according to the coordinate value, the identical pixel of ordinate value to be divided into one group；
Average calculation unit, for calculating the average value of the abscissa value of all pixels point in each group；
Coordinate points searching unit, for being directed to each group, searched in the rectangular coordinate system in respective sets pixel it is vertical
Coordinate value is the first ordinate value, take the average value as the first coordinate points of the first abscissa value；
Centreline definition unit, for defining the line formed by first coordinate points as the human body center line.
8. the posture apparatus for correcting of human body image according to claim 7, which is characterized in that further include:
Image processing module obtains that treated for handling the human body image using bilinear interpolation algorithm
One human body image.
9. a kind of electronic equipment, including memory and processor, the memory are stored with the calculating that can be run on a processor
Machine program, which is characterized in that the processor realizes that Claims 1-4 is described in any item when executing the computer program
The step of posture antidote of human body image.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is held by processor
The step in the posture antidote of the described in any item human body images of Claims 1-4 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811271289.5A CN109615585A (en) | 2018-10-29 | 2018-10-29 | Posture antidote and device, electronic equipment, the storage medium of human body image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811271289.5A CN109615585A (en) | 2018-10-29 | 2018-10-29 | Posture antidote and device, electronic equipment, the storage medium of human body image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109615585A true CN109615585A (en) | 2019-04-12 |
Family
ID=66002553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811271289.5A Pending CN109615585A (en) | 2018-10-29 | 2018-10-29 | Posture antidote and device, electronic equipment, the storage medium of human body image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615585A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111156948A (en) * | 2019-12-29 | 2020-05-15 | 苏州赛腾精密电子股份有限公司 | Three-dimensional data coordinate correction method and device for 3C glass panel detection |
| CN112085782A (en) * | 2020-09-08 | 2020-12-15 | 广州医软智能科技有限公司 | Amplification factor detection method and detection device |
| CN112258269A (en) * | 2020-10-19 | 2021-01-22 | 武汉纺织大学 | Virtual fitting method and device based on 2D image |
| CN114511468A (en) * | 2022-03-31 | 2022-05-17 | 西北民族大学 | Distorted bone image correction method and system |
| CN114519666A (en) * | 2022-02-18 | 2022-05-20 | 广州方硅信息技术有限公司 | Live broadcast image correction method, device, equipment and storage medium |
-
2018
- 2018-10-29 CN CN201811271289.5A patent/CN109615585A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111156948A (en) * | 2019-12-29 | 2020-05-15 | 苏州赛腾精密电子股份有限公司 | Three-dimensional data coordinate correction method and device for 3C glass panel detection |
| CN112085782A (en) * | 2020-09-08 | 2020-12-15 | 广州医软智能科技有限公司 | Amplification factor detection method and detection device |
| CN112258269A (en) * | 2020-10-19 | 2021-01-22 | 武汉纺织大学 | Virtual fitting method and device based on 2D image |
| CN112258269B (en) * | 2020-10-19 | 2024-05-28 | 武汉纺织大学 | Virtual fitting method and device based on 2D image |
| CN114519666A (en) * | 2022-02-18 | 2022-05-20 | 广州方硅信息技术有限公司 | Live broadcast image correction method, device, equipment and storage medium |
| CN114519666B (en) * | 2022-02-18 | 2023-09-19 | 广州方硅信息技术有限公司 | Live image correction method, device, equipment and storage medium |
| CN114511468A (en) * | 2022-03-31 | 2022-05-17 | 西北民族大学 | Distorted bone image correction method and system |
| CN114511468B (en) * | 2022-03-31 | 2022-11-11 | 西北民族大学 | Distorted bone image correction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615585A (en) | Posture antidote and device, electronic equipment, the storage medium of human body image | |
| CN108198141B (en) | Image processing method and device for realizing face thinning special effect and computing equipment | |
| CN106548179B (en) | The detection method of object and dress ornament key point, device and electronic equipment | |
| CN104346612B (en) | Information processing unit and display methods | |
| CN107452028B (en) | Method and device for determining position information of target image | |
| CN111127623B (en) | Model rendering method and device, storage medium and terminal | |
| CN110503681B (en) | Human body model automatic creation method and three-dimensional fitting system | |
| CN110084236A (en) | A kind of antidote and device of image | |
| WO2022042304A1 (en) | Method and apparatus for identifying scene contour, and computer-readable medium and electronic device | |
| CN109584168B (en) | Image processing method and apparatus, electronic device, and computer storage medium | |
| WO2018040480A1 (en) | Method and device for adjusting scanning state | |
| CN109711472B (en) | Training data generation method and device | |
| WO2015188767A1 (en) | Method and device for acquiring clothing image attribute points | |
| CN109636890B (en) | Texture fusion method and device, electronic equipment, storage medium and product | |
| CN106095294B (en) | The method and its system of synchronous stroke between different platform | |
| CN111198975B (en) | Grid-based space-time big data visualization method and system | |
| CN104881526A (en) | Article wearing method and glasses try wearing method based on 3D (three dimensional) technology | |
| CN113469929B (en) | Training data generation method and device, electronic equipment and computer readable storage medium | |
| CN106909213A (en) | A kind of control instruction generation method and electronic equipment based on recognition of face | |
| CN104599297A (en) | Image processing method for automatically blushing human face | |
| CN109165571B (en) | Method and apparatus for inserting image | |
| CN112509117A (en) | Hand three-dimensional model reconstruction method and device, electronic equipment and storage medium | |
| US20200118333A1 (en) | Automated costume augmentation using shape estimation | |
| CN106709870A (en) | Close-range image straight-line segment matching method | |
| CN104899917A (en) | Image storage and sharing method of virtual item wear based on 3D |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190412 |