CN109840928A - It is knitted generation method, device, electronic equipment and the storage medium of image - Google Patents
It is knitted generation method, device, electronic equipment and the storage medium of image Download PDFInfo
- Publication number
- CN109840928A CN109840928A CN201910100730.1A CN201910100730A CN109840928A CN 109840928 A CN109840928 A CN 109840928A CN 201910100730 A CN201910100730 A CN 201910100730A CN 109840928 A CN109840928 A CN 109840928A
- Authority
- CN
- China
- Prior art keywords
- image
- coordinate points
- module
- line
- threading
- 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
Landscapes
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
Present disclose provides a kind of generation method, device, electronic equipment and storage mediums for being knitted image, which comprises obtains the image of user's input；Described image is pre-processed, multiple coordinate points on the blank outer edge tangent with pretreated image border one week are obtained；The threading path of image after pretreatment is determined according to the line between the multiple coordinate points；According to the threading path drawing described image, knitting image is generated.By the generation method of the knitting image of the disclosure, after multiple coordinate points on determining and tangent image border blank outer edge one week, threading path automatically is determined according to the line between coordinate points, reduces calculation amount, improves operation efficiency.
Description
Technical field
This disclosure relates to which technical field of image processing more particularly to a kind of generation method for being knitted image, device, electronics are set
Standby and non-transitorycomputer readable storage medium.
Background technique
With the improvement of people's living standards, the requirement for quality of the life is also higher and higher, also increasingly to decoration painting
Pay attention to.Traditional decoration painting makes based on craft, and manufacturing speed is very slow, inefficiency；And time-consuming, higher cost,
The needs of social and economic development are not adapted to.
In recent years, with the development of computer image processing technology, existing the relevant technologies can be by computer picture at
The generation decoration painting of reason automatically or semi-automatically.For example, passing through Computer Image Processing using the method that sketch and tone combine
Pencil drawing can be generated, or can be generated one by Computer Image Processing using the style and abstract method of portrait sketch
The decoration painting of model with different artist's styles and different abstraction hierarchies.But the side combined using sketch and tone
Method is to directly generate pencil drawing, during making pencil drawing, cannot carry out adaptation according to the wish of user, reduce
The satisfaction of user；For another example, using the style of portrait sketch and abstract method, the edge contour of image is converted to certain skill
The stroke of astrologist's style copies on image, distortion is be easy to cause, especially in chin, mouth, the key positions such as tooth, strong
Under the irradiation of light and dark light, image is integrally excessive lightness or darkness often to cannot get clear image, and the image outline presented is also
Fuzzy, therefore, it is necessary to spend a large amount of operation to extract the profile of image, to reduce operation efficiency.
Summary of the invention
To overcome the problems in correlation technique, the disclosure provides a kind of generation method of knitting image, device, electronics
Equipment and non-transitorycomputer readable storage medium.
According to the first aspect of the embodiments of the present disclosure, a kind of generation method being knitted image is provided, which comprises
Obtain the image of user's input；
Described image is pre-processed, is obtained on the blank outer edge tangent with pretreated image border one week
Multiple coordinate points；
The threading path of image after pretreatment is determined according to the line between the multiple coordinate points；
According to the threading path drawing described image, knitting image is generated.
Optionally, before being pre-processed to described image, the method also includes:
Described image degree of comparing enhancing to input；
Detect the key position of object in described image after enhancing；
The key position is adjusted；
It is described that described image is pre-processed, obtain the blank outer edge tangent with pretreated image border one week
On multiple coordinate points, specifically include:
The image adjusted is pre-processed, is obtained outside the blank tangent with pretreated described image edge
Multiple coordinate points on edge one week.
Optionally, described that described image is pre-processed, after obtaining and pre-processing outside the tangent blank of image border
Multiple coordinate points on edge one week, comprising:
Described image is cut to the image of predetermined shape；
Choose an equal amount of blank of image with the predetermined shape；
The determining blank outer edge one week upper equally distributed multiple nails tangent with described image edge；
Coordinate points of each nail in described image are calculated, the coordinate points of all nails are obtained.
Optionally, the line according between multiple coordinate points determines the threading path of pretreated image, comprising:
Select a coordinate points as origin coordinates point from the multiple coordinate points；
Calculate the origin coordinates point respectively between each remaining coordinate points line difference set；
Select the line of maximum difference as a threading path from the difference set；
With the corresponding coordinate points of the threading path tail end for new origin coordinates point, continue to calculate described new rise
Beginning coordinate points respectively between each remaining coordinate points line difference set, until there is one in the difference set of all lines
Difference is less than setting revenue threshold or line sum is more than or equal to until presetting line threshold value.
Optionally, it is described calculate the origin coordinates point respectively between each remaining coordinate points line difference set,
Include:
Calculate before threading the origin coordinates point multiple mean square errors between each remaining coordinate points respectively, and by institute
Multiple mean square errors are stated as the first mean square error difference set；
Calculate after threading the origin coordinates point multiple mean square errors between each remaining coordinate points respectively, and by institute
Multiple mean square errors are stated as the second mean square error difference set；
First mean square error concentrates the second mean square error difference set after each mean square error and threading before calculating threading
In corresponding mean square error difference set.
Optionally, the line that maximum difference is selected from the difference set is as a threading path, comprising:
Compare the difference in the difference set, determines maximum difference；
Select the line of the maximum difference as a threading path.
Optionally, described according to the threading path drawing described image, generate knitting image, comprising:
Using super sampling anti-aliasing algorithm according to the threading path drawing described image, the knitting image is generated
According to the second aspect of an embodiment of the present disclosure, a kind of generating means being knitted image are provided, comprising:
Module is obtained, is configured as obtaining the image of user's input；
Preprocessing module is configured as pre-processing described image, obtains tangent with pretreated image border
Multiple coordinate points on blank outer edge one week；
First determining module is configured as determining pretreated image according to the line between the multiple coordinate points
Thread path；
Drafting module is configured as generating knitting image according to the threading path drawing described image.
Optionally, described device further include:
Enhance module, is configured as before the preprocessing module pre-processes described image, to described in input
The enhancing of image degree of comparing；
Detection module is configured as detecting the key position of objects in images after the enhancing；
Module is adjusted, is configured as being adjusted the key position；
The preprocessing module is specifically configured to pre-process adjustment module image adjusted, obtain
Multiple coordinate points on blank outer edge one week tangent with pretreated image border.
Optionally, the preprocessing module includes:
Module is cut, is configured as described image being cut to the image of predetermined shape；
Module is chosen, is configured as choosing an equal amount of blank of image with the predetermined shape；
Second determining module is configured as equally distributed more on the blank outer edge tangent with described image edge one week
A nail；
First computing module is configured as calculating coordinate points information of each nail in described image, obtains all nails
The coordinate points of son.
Optionally, first determining module includes:
First choice module is configured as selecting a coordinate points as origin coordinates point from the multiple coordinate points；
Second computing module is configured as calculating the origin coordinates point line between each remaining coordinate points respectively
Difference set；
Second selecting module is configured as selecting the line of maximum difference as a threading road from the difference set
Diameter；
Module is iterated to calculate, is configured as with described being new rise with the corresponding coordinate points of the threading path tail end
Beginning coordinate points, continue to calculate the new origin coordinates point respectively between each remaining coordinate points line difference set, directly
There is a difference to be less than setting revenue threshold or line sum more than or equal to default line threshold into the difference set of all lines
Until value.
Optionally, second computing module includes:
First error computing module, be configured as calculating thread before the origin coordinates point respectively with each remaining coordinate points
Between multiple mean square errors, and using the multiple mean square error as the first mean square error difference set；
Second error calculating module, be configured as calculating after threading the origin coordinates point respectively with each remaining coordinate points
Between multiple mean square errors, and using the multiple mean square error as the second mean square error difference set；
Difference calculating module is configured as first mean square error before calculating threading and concentrates each mean square error and threading
Second mean square error concentrates the difference set of corresponding mean square error afterwards.
Optionally, second selecting module includes:
Maximum difference determining module, the difference being configured as in difference set described in comparison, determines maximum difference；
Path selection module is configured as selecting the line of the maximum difference as a threading path.
Optionally, the drafting module is specifically configured to using super sampling anti-aliasing algorithm according to the threading road
Diameter draws described image, generates the knitting image.
According to the third aspect of an embodiment of the present disclosure, a kind of electronic equipment is provided, comprising:
Processor；
For storing the memory of the processor-executable instruction；
Wherein, the processor is configured to executing the generation method of above-mentioned knitting image.
According to a fourth aspect of embodiments of the present disclosure, a kind of non-transitorycomputer readable storage medium is provided, when described
When instruction in storage medium is executed by the processor of mobile terminal, the mobile terminal is enabled to hold above-mentioned knitting image
Generation method
According to a fifth aspect of the embodiments of the present disclosure, it provides according to a kind of computer program product, when the computer journey
When instruction in sequence product is executed by the processor of electronic equipment, so that electronic equipment executes the generation side of above-mentioned knitting image
Method.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Shown in the present exemplary embodiment knitting image generation method, using get user input image as standard,
First described image is pre-processed, obtains multiple seats on the blank outer edge tangent with pretreated image border one week
Punctuate；Then, the threading path of pretreated image is determined according to the line between the multiple coordinate points；And according to described
Path drawing described image is threaded, knitting image is generated.As it can be seen that the generation method for the knitting image that the embodiment of the present disclosure provides,
Multiple coordinate points using the input picture received as standard, on determining and tangent image border blank outer edge one week
Afterwards, threading path automatically is determined according to the line between coordinate points, reduce calculation amount, improve operation efficiency.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of generation method for being knitted image shown according to an exemplary embodiment.
Fig. 2 is a kind of schematic diagram of image shown according to an exemplary embodiment.
Fig. 3 is a kind of schematic diagram that knitting image is generated by standard of Fig. 2 shown according to an exemplary embodiment.
Fig. 4 is a kind of another flow chart of generation method for being knitted image shown according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of generating means for being knitted image shown according to an exemplary embodiment.
Fig. 6 is a kind of another block diagram of generating means for being knitted image shown according to an exemplary embodiment.
Fig. 7 is the block diagram of preprocessing module shown according to an exemplary embodiment.
Fig. 8 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 9 is another block diagram of structure of a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is a kind of flow chart of generation method for being knitted image shown according to an exemplary embodiment, such as Fig. 1 institute
Show, be knitted the generation method of image in terminal, comprising the following steps:
In a step 101, the image of user's input is obtained.
In the step, user inputs an image into terminal, i.e. terminal detects the image that user inputs, wherein the figure
Picture, pencil drawing picture as can be the decoration painting of a hand-made knitting type, it is of course also possible to which other are with skill
Picture, photo of the decoration painting of art style etc., the embodiment of the present disclosure is with no restriction.
In a step 102, described image is pre-processed, is obtained outside the blank tangent with pretreated image border
Multiple coordinate points on edge one week.
Pretreatment mode in the step can be handled according to actual needs by those skilled in the art.Specific packet
It includes:
Firstly, the described image of input or described image adjusted to be cut to the image of predetermined shape；
That is, terminal receive user input operational order when, according to user input operational order, by institute
State the image that image cropping is predetermined shape, wherein predetermined shape can be round, square, rectangle, or just more
Side shape etc..For example, by the image cropping at the image etc. of square or rectangular.Its cut process be for this field
Known technology, details are not described herein.
In order to make it easy to understand, also referring to Fig. 2, a kind of Fig. 2 schematic diagram of image shown according to an exemplary embodiment.
The Fig. 2 is by taking original image as an example, it is of course also possible to be degree of comparing enhancing and modulated image.In selection and the image
After the identical blank of shape size, if, as needed, determining and tangent one Zhou Shangjun of blank outer edge in described image edge
It is even that N number of nail is distributed with, if N is 256.That is, the quantity of the blank outer edge one week upper nail is more, generation
The difference of image and original image is knitted with regard to smaller, just more like original image；Conversely, the quantity of blank outer edge one week upper nail is got over
Few, the knitting image of generation and the difference of original image are bigger, with original image more unlike.
It should be noted that the nail in the present embodiment assumed that, it is to assume for subsequent determining threading path
Anchor point.And blank outer edge one week, if blank outer edge one week is exactly circumference by image cropping at circle, if will
Image cropping squarely, then blank outer edge one week is exactly rectangular four sides etc., and other shapes are similar, no longer go to live in the household of one's in-laws on getting married one by one herein
It states.
Secondly, an equal amount of blank of image of selection and the predetermined shape；
Blank in the step is the template for the blank that can be handled by computer software, what which assumed that, white
The shapes and sizes of plate will be identical with the shapes and sizes of original image.
In other words, terminal is previously stored with the blank of various shapes, for example, square, rectangle, regular polygon etc..
It then can be according to the blank of the image selection correspondingly-shaped of predetermined shape.
Again, it is determining it is tangent with the edge of the image (i.e. original image) go up within blank outer edge one week it is equally distributed multiple
Nail determines that the quantity of nail on blank, the nail quantity can be 100,256,300 or 500 etc., tool
Body can rule of thumb be set, for example, nail quantity can be set between 50 to 500.Under normal conditions, nail quantity can
To be set as 256, it is of course also possible to the quantity appropriate for increasing or decreasing nail according to actual needs.Because outside blank
As soon as the quantity of upper nail is more on edge week, the knitting image of generation and the difference of original image are smaller, just more like original image；Instead
It, the quantity of upper nail is fewer on blank outer edge one week, and the knitting image of generation and the difference of original image are bigger, with original image
More unlike.Under normal conditions, the quantity of nail can be 150,280,350 or 456 etc., can specifically be predefined in
Any amount between 50 to 500, it is of course also possible to appropriate according to actual needs decrease or increase nail quantity, this
Embodiment is with no restriction.
Finally, calculating coordinate points of each nail in described image, the coordinate points of all nails are obtained.
First method is: assuming that being evenly distributed with N number of nail on blank outer edge one week tangent with described image edge
Son, the corresponding angle of each nail are divided into α, and α is 0~2 π, radius r, and central coordinate of circle is (xo, yo), (c in blanki, ri) be with
Coordinate points on tangent blank outer edge one week in the image border, coordinate can specifically be obtained by following formula:
ci=xo+cos (αi)*r
ri=yo+sin (αi)*r
That is, can calculate the coordinate information of each nail in the picture by above-mentioned formula, (r can be usedi,
ci) indicate, wherein i is less than or equal to N, and N is natural number, riFor the abscissa of i-th of nail in the picture, ciFor i-th of nail
Ordinate in the picture, αiFor the straight line angle of the nail and the line of centres, and αi=360 × i/N.
Second method are as follows: if being above uniformly to divide for rectangular and rectangular one week with the tangent blank in described image edge
It is furnished with N number of nail, i.e., is evenly distributed with N number of nail on four sides up and down of image, it is European between two neighboring nail
It is equidistant, the calculating process of coordinate points is above-mentioned similar to being specifically detailed in, and details are not described herein.
It should be noted that original image can be cut into different shapes by the embodiment of the present invention, for example, it is round, it is rectangular
Deng, if being cut into circle, the calculation method of coordinate points is suitable for first method, if cutting squarely, coordinate points
Calculation method be suitable for second method etc..
In step 103, the threading path of image after pretreatment is determined according to the line between the multiple coordinate points.
In above-mentioned steps, one and an equal amount of blank of image are chosen, and determine the image and blank phase
It cuts and is equipped with multiple nails on blank outer edge one week of image border, pass through line between each nail and remaining each nail
Difference set determine corresponding threading path.Wherein, when determining threading path every time, it is all made of greedy algorithm, that is, is assumed
There is N number of nail, currently from i-th of nail (as origin coordinates point), compares from i-th of nail, arrive respectively other
Wiring path between N-1 nail can be obtained income, that line of maximum difference is selected from the difference set
Path is as a threading path, later, using the corresponding coordinate points of the threading path tail end as new origin coordinates point, after
It is continuous calculate the new origin coordinates point respectively between each remaining coordinate points line difference set, until determining all seats
The threading path of punctuate；Either, until there is a difference to be less than setting revenue threshold or company in the difference set of all lines
Until line sum is more than or equal to default line threshold value.Wherein, it sets revenue threshold and line threshold value is all rule of thumb to set in advance
Fixed, for example, the revenue threshold of setting is more than or equal to 0；If the quantity of nail is 256, then line threshold value can be set as
4000 or so etc..
It should be noted that the income in the present embodiment be before threading with the mean square error of original image, with after threading with original
The difference of the mean square error of image, is shown below:
Gain=mseb-msea。
The present embodiment measures the phase between knitting image and original image by the mean square error MSE of knitting image and original image
Like degree, the value of mean square error is smaller, and similarity is bigger, and vice versa.Therefore, that line of the present embodiment selection Income Maximum
As threading path.
The pixel value on only line changed due to threading front and back reduces calculation amount, this public affairs to improve computational efficiency
The knitting image I generated can will be calculated by openingD(i.e. target image) and original image IGMean square error can be reduced to pixel on line
Mean square error between value calculates the process of the mean square error on line between pixel value, has been known technology for this field,
This is repeated no more.
Wherein, determine that the threading path of image after pre-processing is specifically included according to the line between the multiple coordinate points:
1) select a coordinate points as origin coordinates point from the multiple coordinate points；
2) calculate the origin coordinates point respectively between each remaining coordinate points line difference set；
In the step, it is multiple square between each remaining coordinate points respectively first to calculate the origin coordinates point before threading
Error, and using the multiple mean square error as the first mean square error difference set；Then, the origin coordinates point is distinguished after calculating threading
With multiple mean square errors between each remaining coordinate points, and using the multiple mean square error as the second mean square error difference set；Most
Afterwards, first mean square error concentrates second mean square error after each first mean square error and threading to concentrate before calculating threading
The difference set of corresponding second mean square error, and using the difference set as the origin coordinates point respectively with each residue
The income of line between coordinate points.
3) select the line of maximum difference as a threading path from the difference set；
In the step, the first difference in the difference set determines maximum difference, the corresponding company of the maximum difference
Line income is maximum return；Then, select the line of the maximum difference as a threading path.This is because difference is got over
Greatly, illustrate that threading is preceding bigger with the income after threading, the image and original image after threading are more like；Difference is smaller, illustrates to thread
Income after preceding and threading is smaller.
That is, for the determination for threading path, it is assumed that have one and original image IGAn equal amount of blank ID, and it is white
Plate has N number of nail on tangent blank outer edge one week, is drawn original image by the line two-by-two between nail, and the disclosure will
An optimization problem is regarded in the calculating in threading path as.Make to be knitted picture to the greatest extent and original image is alike, when original image is people
When head portrait, the line between nail is made more to pass through the eyebrow and pupil region of black, and makes the eye of smooth face and white
White region has less line to pass through.Every time when threading, the disclosure uses greedy algorithm.Assume currently to go out from i-th of nail
Hair, compares from i-th of nail, and arriving other N-1 nails respectively terminates, and N-1 threading can be obtained income, and selection is most
That line of big income is as threading path.
4) with it is described with the corresponding coordinate points of the threading path tail end be new origin coordinates point, continue calculate institute
State new origin coordinates point respectively between each remaining coordinate points line difference set, until the difference set of all lines
In there is a difference to be less than setting revenue threshold or until line sum is more than or equal to default line threshold value.
In order to make it easy to understand, please referring to following examples.
It is assumed that blank outer edge has N number of nail on one week, a starting point S is selected from N number of nail at random；Then, it counts
The difference set since S point between other N-1 point lines is calculated, then the difference set of more every line, selection have
The line of maximum difference, is denoted as (i1,j1), and by (i1,j1) as threading path；
Later, it calculates from j1Point starts the difference set of the line between other N-1 point, then the difference of more every line
Value set, and the line with maximum difference is selected, it is denoted as (i2,j2)；And by (i2,j2) as threading path；
It repeats the above steps, until there is a difference to be less than setting revenue threshold th in the difference set of all lines1Or
Line sum is greater than default line threshold value th2Until.Set revenue threshold th1With default line threshold value th2It is empirically to come
It is arranged.That is, newly-increased line income obtained becomes very little, in some instances it may even be possible to be negative value with the increase of line.This
When, increasing line newly influences very little to final knitting effects, or even has damage.Therefore, threshold value th is arranged in the disclosure1And th2,
When meeting the above-mentioned condition rule of thumb set, algorithm is terminated.
At step 104, according to the threading path drawing described image, knitting image is generated.
In the step, since image is on computers that rasterizing indicates, and if directly drawing straight line meeting on the image
There is sawtooth effect, therefore, in the disclosure, super sampling anti-aliasing (SSAA, Super SamplingAnti- can be used
Aliasing) algorithm generates knitting image according to the threading path drawing described image.Wherein, the knitting image is exactly
It is knitted the decoration painting of type.
Wherein, the knitting image of generation is black white image, and the knitting image generated is as shown in figure 4, Fig. 3 is according to one
A kind of schematic diagram of knitting image generated using Fig. 2 as standard shown in exemplary embodiment.Wherein, the cross shown in the image
The perpendicular a plurality of straight line intersected, the threading path exactly selected.
Wherein, the disclosure uses super sampling anti-aliasing (SSAA) algorithm, and maximum feature is from sampling process.And
For the existing algorithm when needing the picture with the pixel rendering of M*N to one, SSAA can render one having a size of (M*S) * first
(N*S) caching of pixel, then sampled on picture of this length and width all multiplied by S.It is obvious that this method consumption is very
Greatly, cost is very high.Based on this, the disclosure and the existing algorithm the difference is that, need to one with the pixel of M*N
When the picture of rendering, the value changed after super sampling is estimated directly on the picture of original size, greatly reduces calculation amount,
Improve operation efficiency.Due to just fixed after the position initialization of each nail, on the nail and original graph on large scale image
Nail be it is one-to-one, be mapped on original size figure between disclosure record every two nail in large scale image line
Pixel value on the original image when line, directly reads corresponding pixel value, to improve computational efficiency, saves and calculates the time.
Shown in the present exemplary embodiment knitting image generation method, using get user input image as standard,
First described image is pre-processed, obtains multiple seats on the blank outer edge tangent with pretreated image border one week
Punctuate；Then, the threading path of pretreated image is determined according to the line between the multiple coordinate points；And according to described
Path drawing described image is threaded, knitting image is generated.As it can be seen that the generation method for the knitting image that the embodiment of the present disclosure provides,
Multiple coordinate points using the input picture received as standard, on determining and tangent image border blank outer edge one week
Afterwards, threading path automatically is determined according to the line between multiple coordinate points, reduce calculation amount, improve operation efficiency.
Further, enhance to described image degree of comparing, and the key position in image is adjusted, i.e., originally
The open human face detection tech that combines carrys out key component, and the adjustment of whole enhancing and key position has been carried out to image, makes to give birth to
At knitting image solid more it is vivid, it is more true to nature.
Further, the disclosure automatically can determine threading road according to the line between blank outer edge one week upper nail
Diameter, and select the line of maximum difference as a threading path, that is to say, that the disclosure sees the select permeability for threading path
At the mean square error income problem for being greed, and the difference set for whole image income problem will be calculated being reduced to related line
It solves, improves operation efficiency.
Further, the disclosure draws described image according to threading path using super sampling anti-aliasing algorithm, not only
Sawtooth effect is reduced, calculation amount is also reduced, improves operation efficiency.
Fig. 4 is a kind of flow chart of generation method for being knitted image shown according to an exemplary embodiment, such as Fig. 4 institute
Show, be knitted the generation method of image in terminal, comprising the following steps:
In step 401, the image of user's input is obtained.
The step and step 101 are same, are specifically detailed in above-mentioned, and details are not described herein.
In step 402, the described image degree of comparing of input is enhanced.
Since the image in natural scene is often influenced by different illumination and seem excessive lightness or darkness, so as to cause
Fogging image.For this purpose, whole enhancing can be carried out to image in the disclosure.Wherein, whole enhancing are as follows: receiving user
After the image of input, first the whole pixel degree of comparing of the image is enhanced, for example, the pixel value of general image is stretched to
In certain section, so that image be made to be more clear.
In step 403, the key position of object in described image after enhancing is detected.
In the step, if the object in image is face, key position can be detected by human face detection tech.
Wherein key position can be with eyes, nose, the features such as mouth.Its specific human face detection tech has been well-known technique, herein not
It repeats again.
In step 404, the key position is adjusted；
Adjustment in the step, be to one of size, shape and color of key position or it is a variety of be adjusted, when
So, it also can according to need to the otherwise adjustment of key position, the disclosure is with no restriction.
For example, often eyes are not clear enough when handling the head portrait in image, especially for eyes compared with
It is small or narrow the head portrait having in mind.Based on this, can size to eyes alternatively, the color to lower eyelid on eyes carries out adaptability tune
It is whole etc., for example deepen the color of upper lower eyelid, to obtain more three-dimensional knitting picture picture.Locate if do not done to eyes in image
Reason, it is likely that the white of the eye and pupil region can not be identified in eyes in final knitting picture, the problem of blind person occurs.So eye
It is white to have preferable contrast with pupil region.Based on this, in the disclosure, the pixel value of the white of the eye and pupil region is adjusted, is made
Two-part pixel value mean value such as makes the pixel mean value 170 in white of the eye region in reasonable range, and the pixel of pupil region is equal
Value is 9.To keep last knitting picture more vivid, the pupil region of eyes is detected, and in the line at size canthus and upper and lower eye
The point of intersection of the line of skin central point increases a high bright spot, so as to be more preferably knitted picture result.Increase by image
Qiang Hou, knitted yarn more concentrate on the pupil position of eyes, as far as possible avoid the white of the eye and Gao Liangdian, make final knitting painter's paraphernalia
There is more preferably visual effect.
In step 405, described image adjusted is pre-processed, is obtained tangent with pretreated image border
Blank outer edge one week on multiple coordinate points；
In a step 406, the threading path of image after pretreatment is determined according to the line between the multiple coordinate points；
In step 407, according to the threading path drawing described image, knitting image is generated.
Wherein, step 405 is identical to step 104 as above-mentioned steps 102 to step 407, be specifically detailed in it is above-mentioned, herein no longer
It repeats.
Shown in the present exemplary embodiment knitting image generation method, using get user input image as standard,
First the image degree of comparing of input is enhanced, the key position of object in described image after enhancing is detected, to the key portion
Position is adjusted, and is then pre-processed, is obtained outside the blank tangent with pretreated image border to image adjusted
Multiple coordinate points on edge one week；And wearing for pretreated image is determined according to the line between the multiple coordinate points
Thread path；And according to the threading path drawing described image, knitting image is generated.As it can be seen that the needle that the embodiment of the present disclosure provides
The generation method of image is knitted, first input picture degree of comparing is enhanced, reduces the influence of illumination, it is then detected that after going out to enhance
Key position in image, and key position is adjusted, keep the solid of the knitting image generated more vivid, it is more true to nature；
And after multiple coordinate points on determining and tangent image border blank outer edge one week, automatically according between coordinate points
Line determine threading path, not only present the intermediate result for generating knitting picture, and also reduce calculation amount, improve fortune
Calculate efficiency.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to
According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented
Necessary to example.
Fig. 5 is a kind of generating means block diagram for being knitted image shown according to an exemplary embodiment.Referring to Fig. 5, the dress
Set includes: to obtain module 501, preprocessing module 502, the first determining module 503 and drafting module 504.
The acquisition module 501 is configured as obtaining the image of user's input；
The preprocessing module 502, is configured as pre-processing described image, obtains and pretreated image border
Multiple coordinate points on tangent blank outer edge one week；
First determining module 503 is configured as being determined according to the line between the multiple coordinate points pretreated
The threading path of image, wherein the key position of object in described image is passed through in the threading path；
The drafting module 504 is configured as generating knitting image according to the threading path drawing described image.
Optionally, in another embodiment, on the basis of the above embodiments, described device can also wrap the embodiment
Include: enhancing module 601, detection module 602 and adjustment module 603, structural block diagram as shown in fig. 6, Fig. 6 with block diagram shown in Fig. 5
On the basis of for, wherein
The enhancing module 601, is configured as before the preprocessing module pre-processes described image, to input
The enhancing of described image degree of comparing；
The detection module 602 is configured as the key position of object in described image after detection enhancing；
The adjustment module 603 is configured as being adjusted the key position；
The preprocessing module 502 is specifically configured to locate the adjustment module 602 image adjusted in advance
Reason, obtains multiple coordinate points on the blank outer edge tangent with pretreated image border one week.
Optionally, in another embodiment, the embodiment on the basis of the above embodiments, the preprocessing module 502
Include: to cut module 701, chooses module 702, the second determining module 703 and the first computing module 704, structural block diagram such as Fig. 7
It is shown, wherein
The cutting module 701 is configured as described image being cut to the image of predetermined shape；
The selection module 702 is configured as choosing an equal amount of blank of image with the predetermined shape；
Second determining module 703, is configured as above uniformly dividing for the blank outer edge tangent with described image edge one week
Multiple nails of cloth, wherein the multiple nail is the nail of predetermined quantity；
First computing module 704 is configured as calculating coordinate points information of each nail in described image, obtains institute
There are the coordinate points of nail.
Optionally, in another embodiment, the embodiment on the basis of the above embodiments, the first determining module packet
It includes: first choice module, the second computing module, the second selecting module and iterative calculation module (not shown), wherein
The first choice module is configured as selecting a coordinate points as origin coordinates from the multiple coordinate points
Point；
Second computing module is configured as calculating the origin coordinates point line between each remaining coordinate points respectively
Difference set；
Second selecting module is configured as that the line of maximum difference is selected to thread as one from the difference set
Path；
The iterative calculation module is configured as with described being new with the corresponding coordinate points of the threading path tail end
Origin coordinates point, continue to calculate the new origin coordinates point respectively between each remaining coordinate points line difference set,
Until having in the difference set of all lines, a difference is less than setting revenue threshold or line sum is more than or equal to default line
Until threshold value.
Optionally, in another embodiment, the embodiment on the basis of the above embodiments, the second computing module packet
It includes: first error computing module, the second error calculating module and difference calculating module (not shown), wherein
The first error computing module, be configured as calculating thread before the origin coordinates point respectively with each remaining coordinate
Multiple mean square errors between point, and using the multiple mean square error as the first mean square error difference set；
Second error calculating module, be configured as calculating after threading the origin coordinates point respectively with each remaining coordinate
Multiple mean square errors between point, and using the multiple mean square error as the second mean square error difference set；
The difference calculating module is configured as first mean square error before calculating threading and concentrates each mean square error and wear
Second mean square error concentrates the difference set of corresponding mean square error after line, and using the difference set as the starting
Coordinate points respectively between each remaining coordinate points line income.
Optionally, in another embodiment, the embodiment on the basis of the above embodiments, the second selecting module packet
It includes: maximum difference determination and path selection module (not shown), wherein
Maximum difference determining module, the difference being configured as in difference set described in comparison, determines maximum difference；Wherein,
The corresponding line income of the maximum difference is maximum return.
Path selection module is configured as selecting the line of the maximum difference as a threading path.
Optionally, in another embodiment, the embodiment on the basis of the above embodiments, the drafting module, specifically
It is configured as generating the knitting image according to the threading path drawing described image using super sampling anti-aliasing algorithm.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
The generating means of knitting image shown in the present exemplary embodiment get input picture to obtain module as mark
Standard enhances described image degree of comparing, and is adjusted to the key position in image, i.e., the disclosure combines face
Detection technique carrys out key component, and the adjustment of whole enhancing and key position has been carried out to image, makes the knitting image generated more
For solid it is vivid, it is more true to nature.Further, the disclosure can be automatically according to the line between blank outer edge one week upper nail
It determines threading path, and selects the line of maximum difference as a threading path, that is to say, that the disclosure will thread path
Select permeability regards the mean square error income problem of greed as, and is reduced to related line for whole image income problem is calculated
Difference set solve, improve operation efficiency.Further, the disclosure is using super sampling anti-aliasing algorithm according to threading path
Described image is drawn, sawtooth effect is not only reduced, also reduces calculation amount, improve operation efficiency.
Fig. 8 is the block diagram of a kind of electronic equipment 800 shown according to an exemplary embodiment.Electronic equipment can be movement
Terminal may be server, be illustrated so that electronic equipment is mobile terminal as an example in the embodiment of the present disclosure.For example, electronics is set
Standby 800 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical treatment
Equipment, body-building equipment, personal digital assistant etc..
Referring to Fig. 8, electronic equipment 800 may include following one or more components: processing component 802, memory 804,
Electric power assembly 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814,
And communication component 816.
The integrated operation of the usual controlling electronic devices 800 of processing component 802, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing component 802 may include one or more processors 820 to hold
Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more moulds
Block, convenient for the interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, with
Facilitate the interaction between multimedia component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown
Example includes the instruction of any application or method for operating on electronic equipment 800, contact data, telephone directory number
According to, message, picture, video etc..Memory 804 can by any kind of volatibility or non-volatile memory device or they
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing
Memory, disk or CD.
Power supply module 806 provides electric power for the various assemblies of electronic equipment 800.Power supply module 806 may include power supply pipe
Reason system, one or more power supplys and other with for electronic equipment 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between the electronic equipment 800 and user.
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface
Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments,
Multimedia component 808 includes a front camera and/or rear camera.When equipment 800 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when electronic equipment 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone
It is configured as receiving external audio signal.The received audio signal can be further stored in memory 804 or via logical
Believe that component 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, for providing the state of various aspects for electronic equipment 800
Assessment.For example, sensor module 814 can detecte the state that opens/closes of equipment 800, the relative positioning of component, such as institute
The display and keypad that component is electronic equipment 800 are stated, sensor module 814 can also detect electronic equipment 800 or electronics
The position change of 800 1 components of equipment, the existence or non-existence that user contacts with electronic equipment 800,800 orientation of electronic equipment
Or the temperature change of acceleration/deceleration and electronic equipment 800.Sensor module 814 may include proximity sensor, be configured to
It detects the presence of nearby objects without any physical contact.Sensor module 814 can also include optical sensor, such as
CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with
Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between electronic equipment 800 and other equipment.
Electronic equipment 800 can access the wireless network based on communication standard, such as WiFi, carrier network (such as 2G, 3G, 4G or 5G),
Or their combination.In one exemplary embodiment, communication component 816 receives via broadcast channel and comes from external broadcasting management
The broadcast singal or broadcast related information of system.In one exemplary embodiment, the communication component 816 further includes that near field is logical
(NFC) module is believed, to promote short range communication.For example, radio frequency identification (RFID) technology, infrared data association can be based in NFC module
Meeting (IrDA) technology, ultra wide band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 800 can be by one or more application specific integrated circuit (ASIC), number
Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing above-mentioned Fig. 1, shown in Fig. 2
It is knitted the generation method of image.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 804 of instruction, above-metioned instruction can be executed by the processor 820 of electronic equipment 800 to complete above-mentioned Fig. 1, Fig. 2
Shown in be knitted image generation method.For example, the non-transitorycomputer readable storage medium can be ROM, random
Access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
In the exemplary embodiment, a kind of computer program product is additionally provided, when the instruction in computer program product
When being executed by the processor 820 of electronic equipment 800, so that electronic equipment 800 executes above-mentioned Fig. 1, knitting image shown in Fig. 2
Generation method.
Fig. 9 is the block diagram of a kind of electronic equipment 900 shown according to an exemplary embodiment.For example, electronic equipment 900 can
To be provided as a server.Referring to Fig. 9, it further comprises one or more that electronic equipment 900, which includes processing component 1922,
Processor, and the memory resource as representated by memory 932, for store can by the instruction of the execution of processing component 922,
Such as application program.The application program stored in memory 932 may include it is one or more each correspond to one
The module of group instruction.In addition, processing component 922 is configured as executing instruction, to execute above-mentioned Fig. 1, knitting figure shown in Fig. 2
The generation method of picture.
Electronic equipment 900 can also include that a power supply module 926 is configured as executing the power supply pipe of electronic equipment 900
Reason, a wired or wireless network interface 950 are configured as electronic equipment 900 being connected to network and an input and output (I/
O) interface 958.Electronic equipment 900 can be operated based on the operating system for being stored in memory 932, such as Windows
ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
Claims (10)
1. a kind of generation method for being knitted image characterized by comprising
Obtain the image of user's input；
Described image is pre-processed, is obtained multiple on the blank outer edge tangent with pretreated image border one week
Coordinate points；
The threading path of image after pretreatment is determined according to the line between the multiple coordinate points；
According to the threading path drawing described image, knitting image is generated.
2. being knitted the generation method of image according to claim 1, which is characterized in that pre-processed to described image
Before, the method also includes:
Described image degree of comparing enhancing to input；
Detect the key position of object in described image after enhancing；
The key position is adjusted；
It is described that described image is pre-processed, it obtains on the blank outer edge tangent with pretreated image border one week
Multiple coordinate points, specifically include:
The image adjusted is pre-processed, the blank outer edge tangent with pretreated described image edge is obtained
Multiple coordinate points on one week.
3. the generation method of knitting image according to claim 1 or claim 2, which is characterized in that described to be carried out in advance to described image
Processing obtains and multiple coordinate points on tangent blank outer edge one week of image border after pretreatment, comprising:
Described image is cut to the image of predetermined shape；
Choose an equal amount of blank of image with the predetermined shape；
The determining blank outer edge one week upper equally distributed multiple nails tangent with described image edge；
Coordinate points of each nail in described image are calculated, the coordinate points of all nails are obtained.
4. being knitted the generation method of image according to claim 3, which is characterized in that described according between multiple coordinate points
Line determines the threading path of pretreated image, comprising:
Select a coordinate points as origin coordinates point from the multiple coordinate points；
Calculate the origin coordinates point respectively between each remaining coordinate points line difference set；
Select the line of maximum difference as a threading path from the difference set；
With the corresponding coordinate points of the threading path tail end for new origin coordinates point, continue to calculate the new starting seat
Punctuate respectively between each remaining coordinate points line difference set, until there is a difference in the difference set of all lines
Until being more than or equal to default line threshold value less than setting revenue threshold or line sum.
5. being knitted the generation method of image according to claim 4, which is characterized in that described to calculate the origin coordinates point minute
The difference set of line not between each remaining coordinate points, comprising:
The multiple mean square errors for threading the preceding origin coordinates point respectively between each remaining coordinate points are calculated, and will be described more
A mean square error is as the first mean square error difference set；
The origin coordinates point multiple mean square errors between each remaining coordinate points respectively are calculated after threading, and will be described more
A mean square error is as the second mean square error difference set；
It calculates first mean square error before threading and concentrates the second mean square error concentration pair after each mean square error and threading
The difference set for the mean square error answered.
6. a kind of generating means for being knitted image characterized by comprising
Module is obtained, is configured as obtaining the image of user's input；
Preprocessing module is configured as pre-processing described image, obtains and the tangent blank in pretreated image border
Multiple coordinate points on outer edge one week；
First determining module is configured as determining the threading of pretreated image according to the line between the multiple coordinate points
Path；
Drafting module is configured as generating knitting image according to the threading path drawing described image.
7. being knitted the generating means of image according to claim 6, which is characterized in that described device further include:
Enhance module, is configured as before the preprocessing module pre-processes described image, to the described image of input
Degree of comparing enhancing；
Detection module is configured as detecting the key position of objects in images after the enhancing；
Module is adjusted, is configured as being adjusted the key position；
The preprocessing module is specifically configured to pre-process adjustment module image adjusted, obtain in advance
Multiple coordinate points on tangent blank outer edge one week in treated described image edge.
8. being knitted the generating means of image described according to claim 6 or 7, which is characterized in that the preprocessing module includes:
Module is cut, is configured as described image being cut to the image of predetermined shape；
Module is chosen, is configured as choosing an equal amount of blank of image with the predetermined shape；
Second determining module is configured as the blank outer edge tangent with described image edge one week upper equally distributed multiple nails
Son；
First computing module is configured as calculating coordinate points information of each nail in described image, obtains all nails
Coordinate points.
9. a kind of electronic equipment characterized by comprising
Processor；
For storing the memory of the processor-executable instruction；
Wherein, the processor is configured to the generation method of knitting image described in any one of perform claim requirement 1 to 5.
10. a kind of non-transitorycomputer readable storage medium, which is characterized in that when the instruction in the storage medium is by moving
When the processor of terminal executes, so that the mobile terminal is able to carry out knitting image described in any one of claims 1 to 5
Generation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910100730.1A CN109840928B (en) | 2019-01-31 | 2019-01-31 | Knitting image generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910100730.1A CN109840928B (en) | 2019-01-31 | 2019-01-31 | Knitting image generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109840928A true CN109840928A (en) | 2019-06-04 |
| CN109840928B CN109840928B (en) | 2023-10-17 |
Family
ID=66884413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910100730.1A Active CN109840928B (en) | 2019-01-31 | 2019-01-31 | Knitting image generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109840928B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0999187A (en) * | 1995-10-06 | 1997-04-15 | Tsudakoma Corp | Method for detecting knitted loop and device therefor |
| KR20000049960A (en) * | 1999-06-02 | 2000-08-05 | 홍건표 | System and method for purchasing clothes by using picture compound and recognition on network |
| CN101419706A (en) * | 2008-12-11 | 2009-04-29 | 天津工业大学 | Jersey wear flokkit and balling up grading method based on image analysis |
| US20090301371A1 (en) * | 2006-05-19 | 2009-12-10 | Nerino Grassi | Method and device to discriminate two ends of an article from each other |
| CN106709964A (en) * | 2016-12-06 | 2017-05-24 | 河南工业大学 | Gradient correction and multi-direction texture extraction-based sketch generation method and device |
| CN108734706A (en) * | 2018-05-21 | 2018-11-02 | 东南大学 | A kind of rotor winding image detecting method of integration region distribution character and edge scale angle information |
-
2019
- 2019-01-31 CN CN201910100730.1A patent/CN109840928B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0999187A (en) * | 1995-10-06 | 1997-04-15 | Tsudakoma Corp | Method for detecting knitted loop and device therefor |
| KR20000049960A (en) * | 1999-06-02 | 2000-08-05 | 홍건표 | System and method for purchasing clothes by using picture compound and recognition on network |
| US20090301371A1 (en) * | 2006-05-19 | 2009-12-10 | Nerino Grassi | Method and device to discriminate two ends of an article from each other |
| CN101419706A (en) * | 2008-12-11 | 2009-04-29 | 天津工业大学 | Jersey wear flokkit and balling up grading method based on image analysis |
| CN106709964A (en) * | 2016-12-06 | 2017-05-24 | 河南工业大学 | Gradient correction and multi-direction texture extraction-based sketch generation method and device |
| CN108734706A (en) * | 2018-05-21 | 2018-11-02 | 东南大学 | A kind of rotor winding image detecting method of integration region distribution character and edge scale angle information |
Non-Patent Citations (2)
| Title |
|---|
| 环球网科技综合报道: "纱线画", 《HTTPS://BAIJIAHAO.BAIDU.COM/S?ID=1611541070753283635&WFR=SPIDER&FOR=PC》 * |
| 环球网科技综合报道: "纱线画", 《HTTPS://BAIJIAHAO.BAIDU.COM/S?ID=1611541070753283635&WFR=SPIDER&FOR=PC》, 14 September 2018 (2018-09-14) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109840928B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929651B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US11443462B2 (en) | Method and apparatus for generating cartoon face image, and computer storage medium | |
| CN110675310B (en) | Video processing method and device, electronic equipment and storage medium | |
| EP3338217B1 (en) | Feature detection and masking in images based on color distributions | |
| EP3125158B1 (en) | Method and device for displaying images | |
| US10007841B2 (en) | Human face recognition method, apparatus and terminal | |
| US8233789B2 (en) | Dynamic exposure metering based on face detection | |
| CN107680033B (en) | Picture processing method and device | |
| CN105469356B (en) | Face image processing process and device | |
| CN109003224B (en) | Face-based deformation image generation method and device | |
| US20200312022A1 (en) | Method and device for processing image, and storage medium | |
| CN107958439B (en) | Image processing method and device | |
| KR101944112B1 (en) | Method and apparatus for creating user-created sticker, system for sharing user-created sticker | |
| CN107368810A (en) | Method for detecting human face and device | |
| CN108921856B (en) | Image cropping method and device, electronic equipment and computer readable storage medium | |
| CN114007099A (en) | Video processing method and device for video processing | |
| CN110580733A (en) | Data processing method and device and data processing device | |
| CN113409342A (en) | Training method and device for image style migration model and electronic equipment | |
| CN112099639A (en) | Display attribute adjusting method and device, display equipment and storage medium | |
| CN110286813A (en) | Picture mark position determines method and apparatus | |
| CN111373409B (en) | Method and terminal for obtaining color value change | |
| CN107578382A (en) | Image processing method and device | |
| CN109840928A (en) | It is knitted generation method, device, electronic equipment and the storage medium of image | |
| CN114998115A (en) | Image beautification processing method and device and electronic equipment | |
| CN115601316A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |