CN110264545A - Picture Generation Method, device, electronic equipment and storage medium - Google Patents
Picture Generation Method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110264545A CN110264545A CN201910533231.1A CN201910533231A CN110264545A CN 110264545 A CN110264545 A CN 110264545A CN 201910533231 A CN201910533231 A CN 201910533231A CN 110264545 A CN110264545 A CN 110264545A
- Authority
- CN
- China
- Prior art keywords
- correspondence
- official documents
- picture
- added
- rectangle
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the present disclosure discloses a kind of Picture Generation Method, device, electronic equipment and storage medium.This method comprises: obtaining picture and official documents and correspondence information to be edited;Wherein, official documents and correspondence information includes official documents and correspondence to be added;It treats editing picture and carries out conspicuousness detection, obtain the characteristic value of each pixel, form notable figure corresponding with picture to be edited;According to characteristic value each in notable figure and official documents and correspondence to be added in the overlay area of the notable figure, the target area that official documents and correspondence to be added is added in picture to be edited is determined;Official documents and correspondence to be added is added to target area, to generate picture to be presented.The embodiment of the present disclosure is by introducing the corresponding notable figure of picture to be edited, and combine overlay area of the text to be added in notable figure, realize automatically determining for target area when carrying out official documents and correspondence addition in picture to be edited, and then official documents and correspondence addition is carried out in determining target area, the efficiency for carrying out official documents and correspondence typesetting in picture is improved, the generation time of exhibiting pictures is reduced.
Description
Technical field
The embodiment of the present disclosure is related to technical field of data processing more particularly to a kind of Picture Generation Method, device, electronics are set
Standby and storage medium.
Background technique
When carrying out promotional activities or content is shown, generallys use and added in picture relevant to activity or shown content
The mode of text information generates the exhibiting pictures such as poster.
The prior art usually provides picture and text information by user during generating exhibiting pictures, and passes through people
Work means add corresponding text on picture.Also, the information such as position of added text in picture, also usually by grasping
Make user artificially to select, so that picture official documents and correspondence typesetting process efficiency is lower.
Summary of the invention
The disclosure provides a kind of Picture Generation Method, device, electronic equipment and storage medium, to improve the official documents and correspondence in picture
Typesetting efficiency.
In a first aspect, the embodiment of the present disclosure provides a kind of Picture Generation Method, comprising:
Obtain picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence information includes official documents and correspondence to be added;
Conspicuousness detection is carried out to the picture to be edited, obtains the characteristic value of each pixel, formed with it is described to be edited
The corresponding notable figure of picture;
According to the characteristic value each in the notable figure and the official documents and correspondence to be added in the overlay area of the notable figure, really
It is scheduled on the target area that the official documents and correspondence to be added is added in the picture to be edited;
The official documents and correspondence to be added is added to the target area, to generate picture to be presented.
Second aspect, the embodiment of the present disclosure additionally provide a kind of photograph creation device, comprising:
Picture obtains module, for obtaining picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence information includes to be added
Official documents and correspondence;
Notable figure forms module, for carrying out conspicuousness detection to the picture to be edited, obtains the feature of each pixel
Value forms notable figure corresponding with the picture to be edited;
Target area determining module is used for according to the characteristic value each in the notable figure and the official documents and correspondence to be added in institute
The overlay area of notable figure is stated, determines the target area for adding the official documents and correspondence to be added in the picture to be edited;
Official documents and correspondence adding module, for the official documents and correspondence to be added to be added to the target area, to generate picture to be presented.
The third aspect, the embodiment of the present disclosure additionally provide a kind of electronic equipment, comprising:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes a kind of Picture Generation Method provided such as first aspect embodiment.
Fourth aspect, the embodiment of the present disclosure additionally provide a kind of computer readable storage medium, are stored thereon with computer
Program realizes a kind of Picture Generation Method provided such as first aspect embodiment when the program is executed by processor.
The embodiment of the present disclosure is by obtaining picture to be edited and the official documents and correspondence information including official documents and correspondence to be added;To figure to be edited
Piece carries out conspicuousness detection, obtains the characteristic value of each pixel, forms notable figure corresponding with picture to be edited;According to notable figure
In each characteristic value and official documents and correspondence to be added in the overlay area of notable figure, determine the mesh that official documents and correspondence to be added is added in picture to be edited
Mark region;Official documents and correspondence to be added is added to target area, has generated picture to be presented.Above-mentioned technical proposal is to be edited by introducing
The corresponding notable figure of picture, and overlay area of the text to be added in notable figure is combined, it realizes and carries out text in picture to be edited
Target area when case is added automatically determines, and then official documents and correspondence addition is carried out in determining target area, improves in picture
The middle efficiency for carrying out official documents and correspondence typesetting, reduces the generation time of exhibiting pictures.
Detailed description of the invention
Fig. 1 is the flow chart of one of the embodiment of the present disclosure one Picture Generation Method;
Fig. 2 is the flow chart of one of the embodiment of the present disclosure two Picture Generation Method;
Fig. 3 is the flow chart of one of the embodiment of the present disclosure three Picture Generation Method;
Fig. 4 is the structure chart of one of the embodiment of the present disclosure four photograph creation device;
Fig. 5 is the structure chart of one of the embodiment of the present disclosure five electronic equipment.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the disclosure, rather than the restriction to the disclosure.It also should be noted that in order to just
Part relevant to the disclosure is illustrated only in description, attached drawing rather than entire infrastructure.
In following each embodiments, optional feature and example are provided simultaneously in each embodiment, that records in embodiment is each
A feature can be combined, and form multiple optinal plans, and the embodiment of each number should not be considered merely as to a technical solution.
Embodiment one
Fig. 1 is the flow chart of one of the embodiment of the present disclosure one Picture Generation Method, and the embodiment of the present disclosure is suitable for
Official documents and correspondence is added in picture to generate the process of new picture, this method is executed by photograph creation device, the device by software and/
Or hardware realization, and concrete configuration is in the electronic equipment for having certain data-handling capacity.
A kind of Picture Generation Method as shown in Figure 1, comprising:
S110, picture to be edited and official documents and correspondence information are obtained;Wherein, the official documents and correspondence information includes official documents and correspondence to be added.
Wherein, picture to be edited is to need to add the picture of official documents and correspondence, such as can be poster material figure.Official documents and correspondence information includes
The text information of official documents and correspondence to be added, including text quantity and word content.Certainly, official documents and correspondence information can also include it as needed
At least one of his text attribute information, such as font size, font classification and font color etc..
S120, conspicuousness detection is carried out to the picture to be edited, obtains the characteristic value of each pixel, formed with it is described to
The corresponding notable figure of editing picture.
Illustratively, editing picture can be treated using conspicuousness detection algorithm and carry out significant characteristics analysis, obtain each
The characteristic value of pixel, and form corresponding with picture to be edited notable figure, to show the only of each pixel in picture to be edited
Characteristic.Wherein, conspicuousness detection algorithm can be at least one of AC algorithm, HC algorithm, LC algorithm and FT algorithm etc..Its
In, for the range of characteristic value between [0,255], saliency value is smaller, shows that the content of the respective pixel point in image to be edited is got over
It is important, the important informations such as key person e.g. in poster;Saliency value is bigger, shows the respective pixel point in image to be edited
Content it is more inessential, such as picture background.
S130, according to the characteristic value each in the notable figure and the official documents and correspondence to be added the notable figure the area of coverage
Domain determines the target area that the official documents and correspondence to be added is added in the picture to be edited.
In this step, at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added can be determined according to official documents and correspondence information,
Namely the corresponding rectangular area of text box;According to each characteristic value that overlay area of the official documents and correspondence rectangle in notable figure is covered, really
Surely the target area of official documents and correspondence rectangle is placed;Wherein, the content that the target area in picture to be edited is covered is corresponding significant
Characteristic value in figure is as big as possible, so that target area institute overlay area only includes insignificant information, such as picture background, and keeps away
The important content exempted from picture to be edited is capped.
Optionally, at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added is determined according to official documents and correspondence information, can be and obtains
The information such as font size, official documents and correspondence line number and the line space in official documents and correspondence information are taken, and are determined according to the information got to be added
At least one corresponding official documents and correspondence rectangle of official documents and correspondence.
Or it is optional, at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added is determined according to official documents and correspondence information, may be used also
Being segmented to the official documents and correspondence to be added, the candidate text line number of the official documents and correspondence to be added is determined according to word segmentation result;Root
According to each candidate text line number, at least one official documents and correspondence rectangle is determined.Specifically, by being segmented to official documents and correspondence to be added, and will be same
One vocabulary is placed in one text row, is determined the candidate text line number of official documents and correspondence to be added, is treated editing picture to realize
Carry out line feed function when official documents and correspondence addition.Under normal conditions, when making poster or commodity details page, candidate text line number is general
For a line or two rows.
Illustratively, it according to each candidate text line number, determines at least one official documents and correspondence rectangle, can be according to each candidate text
Line number determines the length-width ratio of at least one official documents and correspondence rectangle;According to default font height, official documents and correspondence rectangle corresponding to different length-width ratios
It is adjusted, to increase the quantity of the official documents and correspondence rectangle.
Specifically, determining that every style of writing originally includes according to the text quantity in each candidate text line number and official documents and correspondence to be added
Text quantity, and determine according to maximum text quantity the length-width ratio of official documents and correspondence rectangle;It is corresponding default according to different fonts size
Font height is adjusted the corresponding official documents and correspondence rectangle of different length-width ratios, and is made according to the official documents and correspondence rectangle generated after each adjustment
For new official documents and correspondence rectangle, the determination of target area is carried out.Wherein, font size can be have picture generation user according to
Family demand is added at least one font size numerical value in official documents and correspondence information;It can also be according to picture to be edited and official documents and correspondence to be added
It is determined.
In one optional embodiment of the disclosure, font size is determined according to picture to be edited and official documents and correspondence to be added, it can
To be the area of determining picture to be edited;According to the text quantity for including in official documents and correspondence to be added, waited for when calculating different fonts size
Add the text area occupied of official documents and correspondence;The ratio for screening text area occupied and picture area to be edited meets when setting accounting
The numerical value of font size, to carry out the adjustment of official documents and correspondence rectangle according to the font size after screening.Wherein, setting accounting can be by skill
Art personnel are as needed or empirical value is determined, such as the ratio of text area occupied Yu picture area to be edited is indicated with x,
Setting accounting can be 15% < x < 30%.
S140, the official documents and correspondence to be added is added to the target area, to generate picture to be presented.
Specifically, the text box of target area setting and target area same size in official documents and correspondence to be added, and in text
Official documents and correspondence to be added is added in this frame, to generate picture to be presented.Correspondingly, can also be opened up to the picture to be presented of generation
Show.
Illustratively, official documents and correspondence to be added is added in text box, can be the font size for being included according to official documents and correspondence information,
The information such as font type and font color carry out the addition operation of official documents and correspondence to be added in text box.
The embodiment of the present disclosure is by obtaining picture to be edited and the official documents and correspondence information including official documents and correspondence to be added;To figure to be edited
Piece carries out conspicuousness detection, obtains the characteristic value of each pixel, forms notable figure corresponding with picture to be edited;According to notable figure
In each characteristic value and official documents and correspondence to be added in the overlay area of notable figure, determine the mesh that official documents and correspondence to be added is added in picture to be edited
Mark region;Official documents and correspondence to be added is added to target area, has generated picture to be presented.Above-mentioned technical proposal is to be edited by introducing
The corresponding notable figure of picture, and overlay area of the text to be added in notable figure is combined, it realizes and carries out text in picture to be edited
Target area when case is added automatically determines, and then official documents and correspondence addition is carried out in determining target area, improves in picture
The middle efficiency for carrying out official documents and correspondence typesetting, reduces the generation time of exhibiting pictures.
Embodiment two
Fig. 2 is the flow chart of one of the embodiment of the present disclosure two Picture Generation Method, and the present embodiment is with above-described embodiment
In improvement is optimized based on each optinal plan.
Further, by operation " according to the characteristic value each in the notable figure and the official documents and correspondence to be added described aobvious
The overlay area of figure is write, determines the target area for adding the official documents and correspondence to be added in the picture to be edited " be refined as " according to
The official documents and correspondence information determines at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added;For each official documents and correspondence rectangle, successively time
Go through the different zones of the notable figure, and each characteristic value in the notable figure covered according to the official documents and correspondence rectangle, determine described in
Covering score of the official documents and correspondence rectangle in different zones;According to each official documents and correspondence rectangle in different zones corresponding covering score,
Determine the target area that the official documents and correspondence to be added is added in the picture to be edited ", to improve the determination mechanism of target area.
A kind of Picture Generation Method as shown in Figure 2, comprising:
S210, picture to be edited and official documents and correspondence information are obtained;Wherein, the official documents and correspondence information includes official documents and correspondence to be added.
S220, conspicuousness detection is carried out to the picture to be edited, obtains the characteristic value of each pixel, formed with it is described to
The corresponding notable figure of editing picture.
S230, according to the official documents and correspondence information, determine at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added.
According to the text quantity of official documents and correspondence to be added, official documents and correspondence to be added corresponding at least one is determined by way of permutation and combination
A official documents and correspondence rectangle;Official documents and correspondence rectangle is adjusted according to font size, with the quantity of more official documents and correspondence rectangle.
Wherein, font size can be at least one font size of default, can also carry in official documents and correspondence information, may be used also
To determine font size according to picture to be edited and official documents and correspondence to be added.Wherein, it is determined according to picture to be edited and official documents and correspondence to be added
The specific method of determination of font size with it is consistent above, details are not described herein.
S240, it is directed to each official documents and correspondence rectangle, successively traverses the different zones of the notable figure, and according to the official documents and correspondence rectangle
Each characteristic value in the notable figure is covered, determines covering score of the official documents and correspondence rectangle in different zones.
Since characteristic value is smaller, the important information for showing that corresponding pixel points include in picture to be edited is more;Characteristic value is got over
Greatly, the important information for showing that the content of corresponding pixel points in picture to be edited includes is fewer.So being covered by official documents and correspondence rectangle aobvious
Write and cover score determined by each characteristic value of figure, in the notable figure for being covered as official documents and correspondence rectangle the reference of important information because
Son.
In this step, for each official documents and correspondence rectangle, the different zones of notable figure are successively traversed, and determine that official documents and correspondence rectangle covers
Each characteristic value in lid notable figure;According to the determining corresponding each characteristic value in overlay area, determine official documents and correspondence rectangle in different zones
When covering score.Illustratively, according to the characteristic value of determining overlay area, official documents and correspondence rectangle covering in different zones is determined
Lid score can be weighted sum, product or quadratic sum etc. according to the determining corresponding each characteristic value in overlay area;It will be literary
Case rectangle is each overlay area is corresponding and value, product or quadratic sum etc., as official documents and correspondence rectangle covering in respective coverage areas domain
Lid score.
Wherein, it is being directed to each official documents and correspondence rectangle, is successively traversing the different zones of notable figure, can be according to preset
Official documents and correspondence rectangle is covered movement by traverse path in notable figure.Such as can be according to from left to right, sequence from top to bottom, with
One pixel is step-length mobile official documents and correspondence rectangle in notable figure.
S250, according to each official documents and correspondence rectangle in different zones corresponding covering score, determine in the figure to be edited
The target area of the official documents and correspondence to be added is added in piece.
Since characteristic value is smaller, the important information for showing that corresponding pixel points include in picture to be edited is more;Characteristic value is got over
Greatly, the important information for showing that the content of corresponding pixel points in picture to be edited includes is fewer.And score is covered according to official documents and correspondence rectangle
The corresponding characteristic value in institute overlay area is weighted in picture to be edited and the modes such as product or quadratic sum carry out operation
It obtains, then covering score is bigger, shows that the important information of official documents and correspondence rectangle covering is fewer.Therefore, existed according to different official documents and correspondence rectangles
Corresponding covering score when different zones, corresponding overlay area is as target area when selecting covering score maximum.
S260, the official documents and correspondence to be added is added to the target area, to generate picture to be presented.
The embodiment of the present disclosure is by determining that operation is refined as determining official documents and correspondence to be added according to official documents and correspondence information for target area
At least one corresponding official documents and correspondence rectangle;For each official documents and correspondence rectangle, the different zones of notable figure are successively traversed, and according to official documents and correspondence square
Shape covers each characteristic value in notable figure, determines covering score of the official documents and correspondence rectangle in different zones;Existed according to each official documents and correspondence rectangle
Corresponding covering score, determines the target area that official documents and correspondence to be added is added in picture to be edited when different zones.Using above-mentioned skill
Art scheme is quantified by introducing the covering Score Lists corresponding important information in case rectangle institute overlay area of soliciting articles, and then realizes mesh
Mark the determination in region, the perfect determination mechanism of target area.Meanwhile target area is carried out by the covering score after quantization
It determines, keeps identified target area more accurate, and then reduce the weight for adding in picture to be edited and being covered after official documents and correspondence
Want the information content of information.
It, may in the target area according to determined by covering score since official documents and correspondence rectangle is after font size is adjusted
It is more likely to target area determined by the official documents and correspondence rectangle using font when smaller.In order to avoid the generation of above situation, true
When covering score surely, it may be incorporated into other parameters and inhibit influence of the font size to covering score.
In an optional embodiment of the embodiment of the present disclosure, according to the official documents and correspondence information, determine described to be added
After at least one corresponding official documents and correspondence rectangle of official documents and correspondence, following steps can also be added: determine each official documents and correspondence rectangle described aobvious
The quantity for the background pixel point that the different zones of work figure are covered;The background pixel point is characterized the picture that value is greater than given threshold
Vegetarian refreshments.
Wherein, given threshold such as can be 200 by technical staff as needed or empirical value is set.
Correspondingly, after determining covering score of the official documents and correspondence rectangle in different zones when, according to each official documents and correspondence
Rectangle corresponding covering score in different zones, determination are added before the target area of the official documents and correspondence to be added, further includes: needle
To each official documents and correspondence rectangle, according to the official documents and correspondence rectangle background pixel point that the same area is covered in the notable figure
Quantity updates the official documents and correspondence rectangle in the covering score of described the same area.
Illustratively, according to the number of the official documents and correspondence rectangle background pixel point that the same area is covered in the notable figure
Amount updates the official documents and correspondence rectangle in the covering score of described the same area, can be and obtains the official documents and correspondence rectangle described same
The current covering score in region;By the quantity of the background pixel point covered in described the same area and described current cover
Split-phase multiplies, and obtains the official documents and correspondence rectangle in the covering score of described the same area.
Illustratively, according to the number of the official documents and correspondence rectangle background pixel point that the same area is covered in the notable figure
Amount updates the official documents and correspondence rectangle in the covering score of described the same area, can be and obtains the official documents and correspondence rectangle described same
The current covering score in region;It quantity to the background pixel point covered in described the same area and described current covers
Divide weighted sum, obtains the official documents and correspondence rectangle in the covering score of described the same area.Wherein, to same official documents and correspondence rectangle same
Weight set by both quantity of the corresponding current covering score in region and background pixel point can be the same or different, and have
Body can be as needed by technical staff or empirical value is set.
It is understood that in order to improve the practicability of identified target area, typical case is currently covering for setting
The weight divided is greater than the weight of the quantity of background pixel point.
The embodiment of the present disclosure passes through the determination of amount step of additional background pixel point, and according to the quantity of background pixel point
The covering score of the same area is updated, font size is effectively inhibited to avoid and determine the influence of covering score
The too small situation in target area generation, further improve determined by target area practicability.
Embodiment three
Fig. 3 is the flow chart of one of the embodiment of the present disclosure three Picture Generation Method, and the present embodiment is with above-described embodiment
In improvement is optimized based on each optinal plan.
Further, additional " according to described before operation " official documents and correspondence to be added is added to the target area "
Picture to be edited determines the word attribute of the official documents and correspondence to be added;Wherein, the word attribute includes font classification and/or word
Body color " to realize automatically determining to the word attribute of official documents and correspondence to be added, and then improves the determination mechanism of word attribute.
A kind of Picture Generation Method as shown in Figure 3, comprising:
S310, picture to be edited and official documents and correspondence information are obtained;Wherein, the official documents and correspondence information includes official documents and correspondence to be added.
S320, conspicuousness detection is carried out to the picture to be edited, obtains the characteristic value of each pixel, formed with it is described to
The corresponding notable figure of editing picture.
S330, according to the characteristic value each in the notable figure and the official documents and correspondence to be added the notable figure the area of coverage
Domain determines the target area that the official documents and correspondence to be added is added in the picture to be edited.
S340, according to the picture to be edited, determine the word attribute of the official documents and correspondence to be added.
Wherein, the word attribute includes font classification and/or font color.
In one optional embodiment of the disclosure, according to picture to be edited, the font class of the official documents and correspondence to be added is determined
Not, it can be;It is input to picture to be edited as input data in preparatory trained font class models;Output and input
The corresponding font classification of data.
Illustratively, trained font class models can be with a large amount of picture to be edited and figure to be edited in advance
The corresponding font classification of piece is training sample, and training known models obtain the first font class models.Typically, it is known that model can
To be neural network model.Correspondingly, input data when using the first font class models is picture to be edited.
In one optional embodiment of the disclosure, according to the picture to be edited, the word of the official documents and correspondence to be added is determined
Body color may is that the picture background color that the picture to be edited is determined according to the picture to be edited;Search obtain with
The corresponding font color of the picture background color.
Illustratively, it according to the picture to be edited, determines the picture background color of the picture to be edited, can be and adopt
The pixel in editing picture is treated with K mean cluster algorithm to classify, and selects candidate color classification according to setting rule,
And the determination of picture background color is carried out according to the pixel value of each pixel in candidate color classification.Wherein, the selection of K value can
With as needed by technical staff or empirical value is set, it can also be tested and be determined according to a large amount of limited times.
Illustratively, setting rule can be determined according to the pixel quantity that the category includes, such as can be selection packet
At most or secondary more colour type is as candidate color classification containing pixel quantity.
Illustratively, the determination of picture background color is carried out according to the pixel value of each pixel in candidate color classification,
It can be and select the pixel value of one of pixel in candidate color classification as picture background color;Or to candidate face
The pixel value weighted sum of each pixel included in color classification, and using obtained result as picture background color.
Illustratively, it searches and obtains font color corresponding with the picture background color, can be picture background
Lookup acquisition is corresponding with picture background color as font color, or in the preset font color table of comparisons for color
Font color.
S350, the official documents and correspondence to be added is added to the target area, to generate picture to be presented.
The embodiment of the present disclosure is by adding according to the figure to be edited before official documents and correspondence to be added is added to target area
Piece determines the word attribute of the official documents and correspondence to be added;Wherein, the word attribute includes font classification and/or font color, reality
Show to the font classification of official documents and correspondence to be added and/or automatically determining for font color, and then the perfect determination machine of word attribute
System.
It is understood that determining target area is located at the region comprising insignificant information under normal conditions, such as scheme
The background area of piece, when the color of target area mismatches to the picture background color determined, (such as identical, similar or vision is imitated
Fruit is bad) when, it will the serious quality for reducing the picture to be presented generated.
In order to overcome the above problem, in another optional embodiment of the disclosure, obtained and the picture background searching
Before the corresponding font color of color, following steps can also be added: determine the corresponding text box background in the target area
Color;Font color corresponding with the picture background color is obtained correspondingly, searching, comprising: by the picture background face
Color and the text box background color combination, search with combine after the corresponding font color of background color;Alternatively, according to described
Picture background color and the text box background color are searched and obtain corresponding font color.
Illustratively, it determines the corresponding text box background color in the target area, can be using K mean cluster algorithm
The pixel treated in the target area of editing picture is classified, and according to setting rule selection candidate color classification;According to
The pixel value of each pixel in candidate color classification carries out the determination of text box background color.Wherein, the selection of K value can be by
Technical staff is as needed or empirical value is set, and can also be tested and be determined according to a large amount of limited times.Wherein, setting rule
It can then be determined according to the pixel quantity that the category includes, such as can be selection includes that pixel quantity is at most or secondary more
Colour type as candidate color classification.
Illustratively, the picture background color and the text box background color are combined, is can be determining figure
The corresponding pixel value of piece background color and the corresponding pixel value of text box background color is weighted summation, after obtaining combination
The corresponding pixel value of background color.
Illustratively, it according to the picture background color and the text box background color, searches and obtains corresponding font
Color can be and search acquisition and picture background color and text box background face in the preset font color table of comparisons
Font color corresponding to color.
The embodiment of the present disclosure is by introducing text box background color when determining font color, so that identified font face
Color can preferably be adapted to picture to be edited, and then improve the quality for generating picture to be presented, and it is to be presented to promote user's viewing
Visual experience when picture.
Example IV
Fig. 4 is the structure chart of one of the embodiment of the present disclosure four photograph creation device, and the embodiment of the present disclosure is suitable for
Official documents and correspondence is added in picture to generate the process of new picture, the device is by software and or hardware realization, and concrete configuration is in tool
In the electronic equipment of standby certain data-handling capacity.
A kind of photograph creation device as shown in Figure 4, comprising: picture obtains module 410, and notable figure forms module 420, mesh
Mark area determination module 430 and official documents and correspondence adding module 440.
Wherein, picture obtains module 410, for obtaining picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence packet
Include official documents and correspondence to be added;
Notable figure forms module 420, for carrying out conspicuousness detection to the picture to be edited, obtains the spy of each pixel
Value indicative forms notable figure corresponding with the picture to be edited;
Target area determining module 430, for according to the characteristic value each in the notable figure and the official documents and correspondence to be added
In the overlay area of the notable figure, the target area that the official documents and correspondence to be added is added in the picture to be edited is determined;
Official documents and correspondence adding module 440, for the official documents and correspondence to be added to be added to the target area, to generate figure to be presented
Piece.
The embodiment of the present disclosure obtains that module obtains picture to be edited and official documents and correspondence including official documents and correspondence to be added is believed by picture
Breath;Form module by notable figure and treat editing picture and carry out conspicuousness detection, obtain the characteristic value of each pixel, formed with to
The corresponding notable figure of editing picture;By target area determining module according to characteristic value each in notable figure and official documents and correspondence to be added aobvious
The overlay area of figure is write, determines the target area for adding official documents and correspondence to be added in picture to be edited;It will by official documents and correspondence adding module
Official documents and correspondence to be added is added to target area, has generated picture to be presented.Above-mentioned technical proposal is corresponding by introducing picture to be edited
Notable figure, and combine overlay area of the text to be added in notable figure, realize when carrying out official documents and correspondence addition in picture to be edited
Target area automatically determine, and then carry out official documents and correspondence addition in determining target area, improve and carry out text in picture
The efficiency of case typesetting reduces the generation time of exhibiting pictures.
Further, target area determining module 430, comprising:
Official documents and correspondence rectangle determination unit, for determining the official documents and correspondence to be added corresponding at least one according to the official documents and correspondence information
A official documents and correspondence rectangle;
Score determination unit is covered, for successively traversing the different zones of the notable figure for each official documents and correspondence rectangle, and
Each characteristic value in the notable figure is covered according to the official documents and correspondence rectangle, determines covering of the official documents and correspondence rectangle in different zones
Score;
Target area determination unit, for according to each official documents and correspondence rectangle in different zones corresponding covering score, really
It is scheduled on the target area that the official documents and correspondence to be added is added in the picture to be edited.
Further, target area determining module 430, further includes:
Quantity statistics unit, for according to the official documents and correspondence information, determine the official documents and correspondence to be added it is corresponding at least one
After official documents and correspondence rectangle, the number for the background pixel point that each official documents and correspondence rectangle is covered in the different zones of the notable figure is determined
Amount;The background pixel point is characterized the pixel that value is greater than given threshold;
Score updating unit is covered, for after determining covering score of the official documents and correspondence rectangle in different zones when,
According to each official documents and correspondence rectangle, in different zones, the target area of the official documents and correspondence to be added is added in corresponding covering score, determination
Before, for each official documents and correspondence rectangle, according to the official documents and correspondence rectangle background that the same area is covered in the notable figure
The quantity of pixel updates the official documents and correspondence rectangle in the covering score of described the same area.
Further, score determination unit is covered, is specifically used for:
The different zones of the notable figure are successively traversed, and determine that the official documents and correspondence rectangle covers each spy in the notable figure
Value indicative and value;
By the official documents and correspondence rectangle each overlay area it is corresponding and value, as the official documents and correspondence rectangle in respective coverage areas domain
Cover score.
Further, score updating unit is covered, is specifically used for:
The official documents and correspondence rectangle is obtained in the current covering score of described the same area;
Quantity and the current covering score weighted sum to the background pixel point covered in described the same area,
The official documents and correspondence rectangle is obtained in the covering score of described the same area.
Further, official documents and correspondence rectangle determination unit, is specifically used for:
The official documents and correspondence to be added is segmented, the candidate line of text of the official documents and correspondence to be added is determined according to word segmentation result
Number;
According to each candidate text line number, at least one official documents and correspondence rectangle is determined.
Further, official documents and correspondence rectangle determination unit is executing according to each candidate text line number, is determining at least one official documents and correspondence square
When shape, it is specifically used for:
According to each candidate text line number, the length-width ratio of at least one official documents and correspondence rectangle is determined;
According to default font height, the corresponding official documents and correspondence rectangle of different length-width ratios is adjusted, to increase the official documents and correspondence square
The quantity of shape.
Further, which further includes text, and word attribute determination module is used for:
Before the official documents and correspondence to be added is added to the target area, according to the picture to be edited, determine described in
The word attribute of official documents and correspondence to be added;
Wherein, the word attribute includes font classification and/or font color.
Further, word attribute determining module, including font color determination unit, for executing according to described wait compile
Picture is collected to be specifically used for when determining the word attribute of the official documents and correspondence to be added:
According to the notable figure of the picture to be edited and/or the picture to be edited, the figure of the picture to be edited is determined
Piece background color;
It searches and obtains font color corresponding with the picture background color.
Further, font color determination unit obtains font face corresponding with the picture background color searching
Before color, it is also used to:
Determine the corresponding text box background color in the target area;
Correspondingly, font color determination unit, obtains font corresponding with the picture background color executing to search
When color, it is specifically used for:
The picture background color and the text box background color are combined, is searched corresponding with the background color after combining
Font color;Alternatively,
According to the picture background color and the text box background color, searches and obtain corresponding font color.
Picture Generation Method provided by disclosure any embodiment can be performed in above-mentioned photograph creation device, has execution figure
The corresponding functional module of piece generation method and beneficial effect.
Embodiment five
Below with reference to Fig. 5, it illustrates the structural representations for the electronic equipment 500 for being suitable for being used to realize the embodiment of the present disclosure
Figure.Terminal device in the embodiment of the present disclosure can include but is not limited to such as mobile phone, laptop, digital broadcasting and connect
Receive device, PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player), car-mounted terminal (such as vehicle
Carry navigation terminal) etc. mobile terminal and such as number TV, desktop computer etc. fixed terminal.Electricity shown in Fig. 5
Sub- equipment is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 5, electronic equipment 500 may include processing unit (such as central processing unit, graphics processor etc.)
501, random access can be loaded into according to the program being stored in read-only memory (ROM) 502 or from storage device 505
Program in memory (RAM) 503 and execute various movements appropriate and processing.In RAM 503, it is also stored with electronic equipment
Various programs and data needed for 500 operations.Processing unit 501, ROM 502 and RAM 503 pass through the phase each other of bus 504
Even.Input/output (I/O) interface 505 is also connected to bus 504.
In general, following device can connect to I/O interface 505: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 506 of head, microphone, accelerometer, gyroscope etc.;Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 507 of dynamic device etc.;Storage device 505 including such as tape, hard disk etc.;And communication device 509.Communication device
509, which can permit electronic equipment 500, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 5 shows tool
There is the electronic equipment 500 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 509, or from storage device 505
It is mounted, or is mounted from ROM 502.When the computer program is executed by processing unit 501, the embodiment of the present disclosure is executed
Method in the above-mentioned function that limits.
It should be noted that the above-mentioned computer-readable medium of the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.
In the disclosure, computer readable storage medium can be any tangible medium for including or store program, the journey
Sequence can be commanded execution system, device or device use or in connection.And in the disclosure, it is computer-readable
Signal media may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying computer-readable
Program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal, optical signal or on
Any appropriate combination stated.Computer-readable signal media can also be any calculating other than computer readable storage medium
Machine readable medium, the computer-readable signal media can send, propagate or transmit for by instruction execution system, device or
Person's device uses or program in connection.The program code for including on computer-readable medium can be with any appropriate
Medium transmission, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment;It is also possible to individualism, and not
It is fitted into the electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the electricity
When sub- equipment executes, so that the electronic equipment: obtaining picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence information include to
Add official documents and correspondence;Conspicuousness detection is carried out to the picture to be edited, obtains the characteristic value of each pixel, formed with it is described to be edited
The corresponding notable figure of picture;According to the characteristic value each in the notable figure and official documents and correspondence to be added the covering in the notable figure
Cover area determines the target area that the official documents and correspondence to be added is added in the picture to be edited;The official documents and correspondence to be added is added
The target area is added to, to generate picture to be presented.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard
The mode of part is realized.Wherein, the title of unit does not constitute the restriction to the unit itself under certain conditions, for example, figure
Piece obtains module and is also described as " obtaining the module of picture and official documents and correspondence information to be edited ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Note that above are only the preferred embodiment and institute's application technology principle of the disclosure.It will be appreciated by those skilled in the art that
The present disclosure is not limited to specific embodiments described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the disclosure.Therefore, although being carried out by above embodiments to the disclosure
It is described in further detail, but the disclosure is not limited only to above embodiments, in the case where not departing from disclosure design, also
It may include more other equivalent embodiments, and the scope of the present disclosure is determined by the scope of the appended claims.
Claims (13)
1. a kind of Picture Generation Method characterized by comprising
Obtain picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence information includes official documents and correspondence to be added;
Conspicuousness detection is carried out to the picture to be edited, the characteristic value of each pixel is obtained, is formed and the picture to be edited
Corresponding notable figure;
According to the characteristic value each in the notable figure and the official documents and correspondence to be added in the overlay area of the notable figure, determine
The target area of the official documents and correspondence to be added is added in the picture to be edited;
The official documents and correspondence to be added is added to the target area, to generate picture to be presented.
2. according to the method described in claim 1, being existed according to the characteristic value each in the notable figure and the official documents and correspondence to be added
The overlay area of the notable figure determines the target area that the official documents and correspondence to be added is added in the picture to be edited, comprising:
According to the official documents and correspondence information, at least one corresponding official documents and correspondence rectangle of the official documents and correspondence to be added is determined;
For each official documents and correspondence rectangle, the different zones of the notable figure are successively traversed, and according to official documents and correspondence rectangle covering
Each characteristic value in notable figure determines covering score of the official documents and correspondence rectangle in different zones;
According to each official documents and correspondence rectangle, in different zones, corresponding covering score, determination add institute in the picture to be edited
State the target area of official documents and correspondence to be added.
3. according to the method described in claim 2, it is characterized in that, determining the text to be added according to the official documents and correspondence information
After at least one corresponding official documents and correspondence rectangle of case, further includes:
Determine the quantity for the background pixel point that each official documents and correspondence rectangle is covered in the different zones of the notable figure;The background
Pixel is characterized the pixel that value is greater than given threshold;
Correspondingly, after determining covering score of the official documents and correspondence rectangle in different zones when, according to each official documents and correspondence rectangle
The corresponding covering score in different zones, determination are added before the target area of the official documents and correspondence to be added, further includes:
For each official documents and correspondence rectangle, the background picture that the same area is covered in the notable figure according to the official documents and correspondence rectangle
The quantity of vegetarian refreshments updates the official documents and correspondence rectangle in the covering score of described the same area.
4. according to the method described in claim 2, it is characterized in that, successively traverse the different zones of the notable figure, and according to
The official documents and correspondence rectangle covers each characteristic value in the notable figure, determines official documents and correspondence rectangle the covering in different zones
Point, comprising:
The different zones of the notable figure are successively traversed, and determine that the official documents and correspondence rectangle covers each characteristic value in the notable figure
And value;
By the official documents and correspondence rectangle each overlay area is corresponding and value, covering as the official documents and correspondence rectangle in respective coverage areas domain
Score.
5. according to the method described in claim 3, it is characterized in that, according to the official documents and correspondence rectangle in the notable figure same area
The quantity for the background pixel point that domain is covered updates the official documents and correspondence rectangle in the covering score of described the same area, comprising:
The official documents and correspondence rectangle is obtained in the current covering score of described the same area;
Quantity and the current covering score weighted sum to the background pixel point covered in described the same area, obtain
Covering score of the official documents and correspondence rectangle in described the same area.
6. according to the method described in claim 2, it is characterized in that, determining the official documents and correspondence to be added according to the official documents and correspondence information
At least one corresponding official documents and correspondence rectangle, comprising:
The official documents and correspondence to be added is segmented, the candidate text line number of the official documents and correspondence to be added is determined according to word segmentation result;
According to each candidate text line number, at least one official documents and correspondence rectangle is determined.
7. according to the method described in claim 6, it is characterized in that, determining at least one official documents and correspondence according to each candidate text line number
Rectangle, comprising:
According to each candidate text line number, the length-width ratio of at least one official documents and correspondence rectangle is determined;
According to default font height, the corresponding official documents and correspondence rectangle of different length-width ratios is adjusted, to increase the official documents and correspondence rectangle
Quantity.
8. method according to claim 1-7, which is characterized in that described the official documents and correspondence to be added to be added to
Before target area, further includes:
According to the picture to be edited, the word attribute of the official documents and correspondence to be added is determined;
Wherein, the word attribute includes font classification and/or font color.
9. according to the method described in claim 8, it is characterized in that, determining the text to be added according to the picture to be edited
The word attribute of case, comprising:
According to the picture to be edited, the picture background color of the picture to be edited is determined;
It searches and obtains font color corresponding with the picture background color.
10. according to the method described in claim 9, it is characterized in that, corresponding with the picture background color searching acquisition
Font color before, further includes:
Determine the corresponding text box background color in the target area;
Font color corresponding with the picture background color is obtained correspondingly, searching, comprising:
Combine the picture background color and the text box background color, search with combine after the corresponding word of background color
Body color;Alternatively,
According to the picture background color and the text box background color, searches and obtain corresponding font color.
11. a kind of photograph creation device characterized by comprising
Picture obtains module, for obtaining picture and official documents and correspondence information to be edited;Wherein, the official documents and correspondence information includes text to be added
Case;
Notable figure forms module, for carrying out conspicuousness detection to the picture to be edited, obtains the characteristic value of each pixel, shape
At notable figure corresponding with the picture to be edited;
Target area determining module, for being shown according to the characteristic value each in the notable figure and the official documents and correspondence to be added described
The overlay area of figure is write, determines the target area for adding the official documents and correspondence to be added in the picture to be edited;
Official documents and correspondence adding module, for the official documents and correspondence to be added to be added to the target area, to generate picture to be presented.
12. a kind of electronic equipment characterized by comprising
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as a kind of Picture Generation Method of any of claims 1-10.
13. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of such as Picture Generation Method of any of claims 1-10 is realized when execution.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910533231.1A CN110264545A (en) | 2019-06-19 | 2019-06-19 | Picture Generation Method, device, electronic equipment and storage medium |
PCT/CN2020/096762 WO2020253766A1 (en) | 2019-06-19 | 2020-06-18 | Picture generation method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910533231.1A CN110264545A (en) | 2019-06-19 | 2019-06-19 | Picture Generation Method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110264545A true CN110264545A (en) | 2019-09-20 |
Family
ID=67919483
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910533231.1A Pending CN110264545A (en) | 2019-06-19 | 2019-06-19 | Picture Generation Method, device, electronic equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110264545A (en) |
WO (1) | WO2020253766A1 (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110889267A (en) * | 2019-11-29 | 2020-03-17 | 北京金山安全软件有限公司 | Method and device for editing characters in picture, electronic equipment and storage medium |
CN111580909A (en) * | 2020-05-08 | 2020-08-25 | 广州市百果园信息技术有限公司 | Picture generation method, device, equipment and storage medium |
CN111581926A (en) * | 2020-05-15 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Method, device and equipment for generating file and computer readable storage medium |
CN111768471A (en) * | 2019-09-29 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for editing characters in picture |
WO2020253766A1 (en) * | 2019-06-19 | 2020-12-24 | 北京字节跳动网络技术有限公司 | Picture generation method and apparatus, electronic device, and storage medium |
CN112862926A (en) * | 2021-01-29 | 2021-05-28 | 成都环宇知了科技有限公司 | Swoole framework-based intelligent picture synthesis method and system |
CN113537487A (en) * | 2021-06-25 | 2021-10-22 | 北京百度网讯科技有限公司 | Model training method, picture generating method and device |
CN113744365A (en) * | 2021-07-19 | 2021-12-03 | 稿定(厦门)科技有限公司 | Intelligent document layout method, system and storage medium based on significance perception |
CN113989404A (en) * | 2021-11-05 | 2022-01-28 | 北京字节跳动网络技术有限公司 | Picture processing method, device, equipment, storage medium and program product |
CN114529635A (en) * | 2022-02-15 | 2022-05-24 | 腾讯科技(深圳)有限公司 | Image generation method, device, storage medium and equipment |
US11934766B2 (en) | 2020-07-28 | 2024-03-19 | Huawei Technologies Co., Ltd. | Always on display method and electronic device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106775747A (en) * | 2016-12-28 | 2017-05-31 | Tcl集团股份有限公司 | A kind of method and apparatus of color configuration |
CN107103635A (en) * | 2017-03-20 | 2017-08-29 | 中国科学院自动化研究所 | Image layout color matching method |
CN109522908A (en) * | 2018-11-16 | 2019-03-26 | 董静 | Image significance detection method based on area label fusion |
CN109543701A (en) * | 2018-11-30 | 2019-03-29 | 长沙理工大学 | Vision significance method for detecting area and device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9298980B1 (en) * | 2013-03-07 | 2016-03-29 | Amazon Technologies, Inc. | Image preprocessing for character recognition |
CN105320391A (en) * | 2014-07-31 | 2016-02-10 | 宇龙计算机通信科技(深圳)有限公司 | Method for adjusting display effect of standby interface and terminal |
CN107517303A (en) * | 2016-06-17 | 2017-12-26 | 中兴通讯股份有限公司 | Wallpaper treatment method and device |
CN106973324A (en) * | 2017-03-28 | 2017-07-21 | 深圳市茁壮网络股份有限公司 | A kind of poster generation method and device |
CN108960247B (en) * | 2017-05-22 | 2022-02-25 | 阿里巴巴集团控股有限公司 | Image significance detection method and device and electronic equipment |
CN110264545A (en) * | 2019-06-19 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Picture Generation Method, device, electronic equipment and storage medium |
-
2019
- 2019-06-19 CN CN201910533231.1A patent/CN110264545A/en active Pending
-
2020
- 2020-06-18 WO PCT/CN2020/096762 patent/WO2020253766A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106775747A (en) * | 2016-12-28 | 2017-05-31 | Tcl集团股份有限公司 | A kind of method and apparatus of color configuration |
CN107103635A (en) * | 2017-03-20 | 2017-08-29 | 中国科学院自动化研究所 | Image layout color matching method |
CN109522908A (en) * | 2018-11-16 | 2019-03-26 | 董静 | Image significance detection method based on area label fusion |
CN109543701A (en) * | 2018-11-30 | 2019-03-29 | 长沙理工大学 | Vision significance method for detecting area and device |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253766A1 (en) * | 2019-06-19 | 2020-12-24 | 北京字节跳动网络技术有限公司 | Picture generation method and apparatus, electronic device, and storage medium |
CN111768471A (en) * | 2019-09-29 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for editing characters in picture |
CN110889267A (en) * | 2019-11-29 | 2020-03-17 | 北京金山安全软件有限公司 | Method and device for editing characters in picture, electronic equipment and storage medium |
CN111580909A (en) * | 2020-05-08 | 2020-08-25 | 广州市百果园信息技术有限公司 | Picture generation method, device, equipment and storage medium |
CN111581926A (en) * | 2020-05-15 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Method, device and equipment for generating file and computer readable storage medium |
CN111581926B (en) * | 2020-05-15 | 2023-09-01 | 抖音视界有限公司 | Document generation method, device, equipment and computer readable storage medium |
US11934766B2 (en) | 2020-07-28 | 2024-03-19 | Huawei Technologies Co., Ltd. | Always on display method and electronic device |
CN112862926B (en) * | 2021-01-29 | 2023-08-01 | 成都环宇知了科技有限公司 | Intelligent picture synthesis method and system based on Swoole framework |
CN112862926A (en) * | 2021-01-29 | 2021-05-28 | 成都环宇知了科技有限公司 | Swoole framework-based intelligent picture synthesis method and system |
CN113537487A (en) * | 2021-06-25 | 2021-10-22 | 北京百度网讯科技有限公司 | Model training method, picture generating method and device |
CN113537487B (en) * | 2021-06-25 | 2023-08-04 | 北京百度网讯科技有限公司 | Model training method, picture generating method and device |
CN113744365A (en) * | 2021-07-19 | 2021-12-03 | 稿定(厦门)科技有限公司 | Intelligent document layout method, system and storage medium based on significance perception |
CN113744365B (en) * | 2021-07-19 | 2024-04-26 | 稿定(厦门)科技有限公司 | Text intelligent layout method, system and storage medium based on significance perception |
CN113989404A (en) * | 2021-11-05 | 2022-01-28 | 北京字节跳动网络技术有限公司 | Picture processing method, device, equipment, storage medium and program product |
CN114529635A (en) * | 2022-02-15 | 2022-05-24 | 腾讯科技(深圳)有限公司 | Image generation method, device, storage medium and equipment |
Also Published As
Publication number | Publication date |
---|---|
WO2020253766A1 (en) | 2020-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110264545A (en) | Picture Generation Method, device, electronic equipment and storage medium | |
CN109618222B (en) | A kind of splicing video generation method, device, terminal device and storage medium | |
CN109688463A (en) | A kind of editing video generation method, device, terminal device and storage medium | |
US20200050632A1 (en) | Method and apparatus for generating knowledge graph, device and computer readable storage medium | |
CN110399848A (en) | Video cover generation method, device and electronic equipment | |
CN109522483A (en) | Method and apparatus for pushed information | |
CN110321958A (en) | Training method, the video similarity of neural network model determine method | |
JP2013003597A (en) | Information processor, information processing method and program | |
CN109919244A (en) | Method and apparatus for generating scene Recognition model | |
CN109598304B (en) | Disaggregated model calibration method, device, equipment and readable medium | |
CN105874449A (en) | Systems and methods for extracting and generating images for display content | |
CN110096655A (en) | Sort method, device, equipment and the storage medium of search result | |
CN115080816B (en) | Summary information generation and search result display method, device, equipment and medium | |
CN108897853A (en) | The method and apparatus for generating pushed information | |
CN113886707B (en) | Encyclopedia information determining method, encyclopedia information displaying method, encyclopedia information determining device, encyclopedia information displaying device, encyclopedia information determining equipment and encyclopedia information medium | |
CN108960110A (en) | Method and apparatus for generating information | |
CN108446658A (en) | The method and apparatus of facial image for identification | |
CN108182240A (en) | The new gaining rate prediction model training of point of interest and Forecasting Methodology, device and storage medium | |
CN109389660A (en) | Image generating method and device | |
CN109873756A (en) | Method and apparatus for sending information | |
CN111538852A (en) | Multimedia resource processing method, device, storage medium and equipment | |
CN108111603A (en) | Information recommendation method, device, terminal device and storage medium | |
CN107895004A (en) | Method, device, terminal device and storage medium | |
US11449662B2 (en) | Automatic generation of layout variations based on visual flow | |
CN104093010B (en) | A kind of image processing method and device |
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 |