CN105138732B - A kind of method for generating pattern and device - Google Patents
A kind of method for generating pattern and device Download PDFInfo
- Publication number
- CN105138732B CN105138732B CN201510447137.6A CN201510447137A CN105138732B CN 105138732 B CN105138732 B CN 105138732B CN 201510447137 A CN201510447137 A CN 201510447137A CN 105138732 B CN105138732 B CN 105138732B
- Authority
- CN
- China
- Prior art keywords
- pattern
- carpet
- feature value
- carpet pattern
- identification information
- 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.)
- Active
Links
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of method for generating pattern and device, this method generates carpet pattern according to the corner grain pattern gene, main body grain pattern gene and frame grain pattern gene selected from grain pattern gene pool；When the scoring is greater than given threshold, searched in feature database with the color of the carpet pattern, texture and the matched carpet pattern of shape feature value identification information and generate carpet pattern；When the scoring be not more than given threshold when, determine the corresponding raising amount of the scoring, in feature database search with characteristic value improve the amount of correspondingling increase after matched carpet pattern identification information and generate carpet pattern.Due to determining color, texture and the shape feature value of each carpet pattern generated in embodiments of the present invention, according to the scoring of user, generate the higher carpet pattern of user's scoring, the carpet pattern of generation to enable is met the needs of users as early as possible, the life for improving carpet pattern forms efficiency, and improves the experience of user.
Description
Technical field
The present invention relates to digital image processing techniques field, in particular to a kind of method for generating pattern and device.
Background technique
With the rapid development of society, people's substance and the horizontal of cultural life are continuously improved, China and the world
Requirement and taste to dress ornament are also constantly changing and are being promoted, by original keep warm, at present for beautiful fashion
It pursues, the following dress ornament will be a kind of displaying for representing the taste of self individual culture, and the development trend of the following dress ornament more will
It is the transmitting of Different Culture grade.
Currently, gradually becoming strong with China, more and more people have begun concern China, and one line of many worlds is famous
Designer also start favorite Chinese Elements, can be seen on the show field of the fashionable dress news conference of the representative international popular trend of every season
To the dress ornament with Chinese Elements design.The pattern of distinct Chinese characteristics is the product that the various nationalities people comply with the nature, and is both our people
The symbol carrier of race's traditional culture, while being also the image reflection of national spirit makings, social consciousness, aesthetic psychology etc..Pattern
The external forms such as grain pattern, color, style be not that we imagine so simple, they represent a kind of cultural representative
Class's characteristic in national culture.These patterns are not only simple pattern, usually represent a kind of national culture, even more a kind of
National spirit.
Image processing software is many kinds of both at home and abroad at present, mainly includes the large-scale image processing software towards professional user
With the simple image processing software towards public users.The image processing software of profession has the Photoshop series of Adobe, face
There are Meitu Xiu Xiu, nEO iMAGING etc. to the simple image processing software of public users, dynamic picture processing software has Ulead
GIF Animator, gif movie gear etc..
Although the pattern generation platform of the pattern generations software sharing such as Photoshop have been relatively mature, but still have
Their shortcoming, including：First is that specific aim is not strong, while most of pattern is voluntarily drawn and is repaired by designer
Change, the automatic generating calculation not comprising pattern；Second is that even if pattern can be generated using certain method, but it is not aware that life
At pattern user whether be satisfied with, can not also know the demand of user, so as to cause pattern generating process relatively blindly, also shadow
The efficiency of pattern generation is rung.
Summary of the invention
The embodiment of the invention discloses a kind of method for generating pattern and devices, to improve the efficiency of pattern generation.
In order to achieve the above objectives, the embodiment of the invention discloses a kind of method for generating pattern, it is applied to generate carpet pattern
Electronic equipment, this method includes：
Generate ground according to the corner grain pattern gene, main body grain pattern gene and frame grain pattern gene selected from grain pattern gene pool
Blanket pattern；
For the carpet pattern generated every time, scoring of the user to the carpet pattern is obtained, judges user to the carpet figure
When the scoring of case is greater than given threshold, according to the color feature value of the carpet pattern, texture eigenvalue and shape feature value, in spy
Levy the identification information searched in library with the color feature value, texture eigenvalue and the matched carpet pattern of shape feature value；According to
The identification information of the matched carpet pattern found determines each grain pattern gene of the carpet pattern of the identification information, root
Carpet pattern is generated according to each grain pattern gene；
When judging user to the scoring of the carpet pattern no more than given threshold, according to the scoring of the user, determining should
Score corresponding raising amount, this is respectively increased in the color feature value of the carpet pattern, texture eigenvalue and shape feature value and is mentioned
A large amount, and searched and the color feature value, texture eigenvalue and the matched carpet of shape feature value after raising in feature database
The identification information of pattern；According to the identification information of the matched carpet pattern found, the carpet figure of the identification information is determined
Each grain pattern gene of case generates carpet pattern according to each grain pattern gene.
Further, it is determined that the color feature value of the carpet pattern includes：
According to the number of the pixel of pixel value each in the carpet pattern, the color histogram of the carpet pattern is determined
Figure, using the color histogram as the color feature value of the carpet pattern.
Further, it is determined that the texture eigenvalue of the carpet pattern includes：
According to co-occurrence matrix, the texture eigenvalue of carpet pattern is determined.
Further, it is determined that the shape feature value of the carpet pattern includes：
Using small wave converting method, the shape feature value of carpet pattern is determined.
Further, described search in feature database matches with the color feature value, texture eigenvalue and shape feature value
The identification information of carpet pattern include：
For the color feature value, texture eigenvalue and shape of the carpet pattern of each identification information saved in feature database
Characteristic value judges that the difference of the color feature value and the color feature value of the carpet pattern of the identification information in the feature database is
In the no first threshold range for being located at setting, and the carpet pattern of the identification information in the texture eigenvalue and the feature database
Whether the difference of texture eigenvalue is located within the scope of the second threshold of setting, and the mark in shape feature value and the feature database
Whether the difference of the shape feature value of the carpet pattern of information is located in the third threshold range of setting；If it is judged that being all
It is, it is determined that the carpet pattern of the identification information and the color feature value, texture eigenvalue and shape feature value in feature database
Match.
The embodiment of the invention provides a kind of pattern generating apparatus, described applied to the electronic equipment for generating carpet pattern
Device includes：
Extract generation module, for according to selected from grain pattern gene pool corner grain pattern gene, main body grain pattern gene and
Frame grain pattern gene generates carpet pattern；
First matching generation module, for obtaining user and commenting the carpet pattern for the carpet pattern generated every time
Point, it is special according to the color feature value of the carpet pattern, texture when judging that user is greater than given threshold to the scoring of the carpet pattern
Value indicative and shape feature value are searched matched with the color feature value, texture eigenvalue and shape feature value in feature database
The identification information of blanket pattern；According to the identification information of the matched carpet pattern found, the carpet of the identification information is determined
Each grain pattern gene of pattern generates carpet pattern according to each grain pattern gene；
Second matching generation module, for obtaining user and commenting the carpet pattern for the carpet pattern generated every time
Point, it is when judging user to the scoring of the carpet pattern no more than given threshold, the color feature value of the carpet pattern, texture is special
The raising amount is respectively increased in value indicative and shape feature value, and searches and the color feature value after raising, texture in feature database
The identification information of characteristic value and the matched carpet pattern of shape feature value；According to the mark of the matched carpet pattern found
Information determines each grain pattern gene of the carpet pattern of the identification information, generates carpet pattern according to each grain pattern gene.
Further, the first matching determining module and the second matching determining module, are specifically used for according to the carpet
The number of the pixel of each pixel value in pattern, determines the color histogram of the carpet pattern, using the color histogram as
The color feature value of the carpet pattern.
Further, the first matching determining module and the second matching determining module, are specifically used for according to co-occurrence matrix,
Determine the texture eigenvalue of carpet pattern.
Further, the first matching determining module and the second matching determining module, are specifically used for using wavelet transformation
Method determines the shape feature value of carpet pattern.
Further, the first matching determining module and the second matching determining module, are specifically used for in feature database
Color feature value, texture eigenvalue and the shape feature value of the carpet pattern of each identification information saved judge color spy
Whether the difference of the color feature value of the carpet pattern of the identification information is located at the first threshold of setting in value indicative and the feature database
It is worth in range, and the difference of the texture eigenvalue and the texture eigenvalue of the carpet pattern of the identification information in the feature database is
Within the scope of the no second threshold for being located at setting, and the shape of shape feature value and the carpet pattern of the identification information in the feature database
Whether the difference of shape characteristic value is located in the third threshold range of setting；If it is judged that being all yes, it is determined that in feature database
The carpet pattern of the identification information is matched with the color feature value, texture eigenvalue and shape feature value.
The embodiment of the invention provides a kind of method for generating pattern and device, this method is selected according to from grain pattern gene pool
Corner grain pattern gene, main body grain pattern gene and frame grain pattern gene generate carpet pattern；According to each user to the ground of generation
The scoring of blanket pattern is searched and the color feature value of the carpet pattern, line when the scoring is greater than given threshold in feature database
The identification information for managing characteristic value and the matched carpet pattern of shape feature value, according to the identification information of the carpet pattern found,
The each grain pattern gene for determining the carpet pattern of identification information generates carpet pattern according to each grain pattern gene；When the scoring not
When greater than given threshold, the corresponding raising amount of the scoring is determined, each characteristic value is improved into the amount of being correspondingly improved, in feature database
The identification information with the matched carpet pattern of characteristic value after the raising is searched, is believed according to the mark of the carpet pattern found
Breath, determines each grain pattern gene of the carpet pattern of identification information, generates carpet pattern according to each grain pattern gene.Due at this
In inventive embodiments determine generate each carpet pattern color feature value, texture eigenvalue and shape feature value, according to
The scoring at family generates the higher carpet pattern of user's scoring, so that the carpet pattern of the generation enable meets user's as early as possible
Demand, improves the formation efficiency of carpet pattern, and improves the experience of user.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of pattern generation process provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram in region shared by each grain pattern gene in carpet pattern；
Fig. 3 is a kind of structural schematic diagram of pattern generating apparatus provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention provides a kind of method for generating pattern and device, this method is selected according to from grain pattern gene pool
Corner grain pattern gene, main body grain pattern gene and frame grain pattern gene generate carpet pattern；According to each user to the ground of generation
The scoring of blanket pattern is searched and the color feature value of the carpet pattern, line when the scoring is greater than given threshold in feature database
The identification information for managing characteristic value and the matched carpet pattern of shape feature value, according to the identification information of the carpet pattern found,
The each grain pattern gene for determining the carpet pattern of identification information generates carpet pattern according to each grain pattern gene；When the scoring not
When greater than given threshold, the corresponding raising amount of the scoring is determined, each characteristic value is improved into the amount of being correspondingly improved, in feature database
The identification information with the matched carpet pattern of characteristic value after the raising is searched, is believed according to the mark of the carpet pattern found
Breath, determines each grain pattern gene of the carpet pattern of identification information, generates carpet pattern according to each grain pattern gene.
Due to determining color feature value, texture eigenvalue and the shape of each carpet pattern generated in embodiments of the present invention
Shape characteristic value generates the higher carpet pattern of user's scoring, thus the carpet pattern of the generation enable according to the scoring of user
It meets the needs of users as early as possible, improves the formation efficiency of carpet pattern, and improve the experience of user.
Fig. 1 is a kind of pattern generation process provided in an embodiment of the present invention, which includes the following steps：
S101：According to the corner grain pattern gene, main body grain pattern gene and frame grain pattern gene selected from grain pattern gene pool
Generate carpet pattern.
As shown in Figure 2 is the schematic diagram in region shared by each grain pattern gene in carpet pattern.Constitute the line of carpet pattern
Sample gene includes：Corner grain pattern gene, main body grain pattern gene and frame grain pattern gene.
There are three word banks in grain pattern gene pool in embodiments of the present invention, preserve corner grain pattern gene, master respectively
Body grain pattern gene and frame grain pattern gene.Wherein corner grain pattern gene, main body grain pattern gene and frame grain pattern gene are to pass through figure
Case segmenting system is divided from carpet figure to be obtained, wherein segmentation obtains corner grain pattern gene, main body line from carpet figure
The process of sample gene and frame grain pattern gene belongs to the prior art, in embodiments of the present invention to the cutting procedure without superfluous
It states.
S102：For the carpet pattern generated every time, scoring of the user to the carpet pattern is obtained, judges user to the ground
Whether the scoring of blanket pattern is greater than given threshold, when the judgment result is yes, carries out S103, otherwise, carries out S104.
After generating carpet pattern every time, whether user can like according to itself, score the carpet pattern.Therefore
Input frame is provided in the generation interface in carpet pattern, user can comment the carpet pattern in the input frame
Point.The score value for user's selection, or the scoring for prompting user current can be provided in the generation interface using assorted
Marking system, such as 5 points of systems, ten point system or hundred-mark system etc. input correctly scoring so as to guide user.
The given threshold can be set according to the marking system of use, be made for example, if being currently 5 points, then the setting threshold
Value can be 4, if being currently ten point system, which can be 8 or 9, if being currently hundred-mark system, the setting threshold
Value can be 90 or 95 etc..
S103：According to the color feature value of the carpet pattern, texture eigenvalue and shape feature value, searched in feature database
With the identification information of the color feature value, texture eigenvalue and the matched carpet pattern of shape feature value；It should according to what is found
The identification information of matched carpet pattern determines each grain pattern gene of the carpet pattern of the identification information, according to each grain pattern
Gene generates carpet pattern.
Carpet pattern includes：Corner grain pattern gene, main body grain pattern gene and frame grain pattern gene, the collocation of these parts
Whether user is satisfied with together or which type of combining form user can just be satisfied with, and is the key that entire pattern generation.And one
As can reflect out the feature of a carpet pattern from features such as color, texture and shapes, therefore in embodiments of the present invention really
Color feature value, texture eigenvalue and the shape feature value of fixed each carpet pattern, comment each carpet pattern according to user
Point, determine the color feature value, texture eigenvalue and shape feature value of the carpet pattern that user likes, lookup meets corresponding face
The carpet pattern of color, texture and shape feature, to generate customer satisfaction system carpet pattern.
Each corner grain pattern gene, main body grain pattern gene and frame grain pattern gene are stored in feature database, each grain pattern
Gene all has corresponding identification information.It in embodiments of the present invention can be in advance by any three corner grain patterns gene, main body
Grain pattern gene and frame grain pattern gene generate carpet pattern, can be by corner grain pattern gene, main body grain pattern gene under limiting case
With any three combinations of frame grain pattern gene, all carpet patterns are generated.Determine that the color of each carpet pattern generated is special
Value indicative, texture eigenvalue and shape feature value, and it is special for its color of the identification information recording of the carpet pattern in feature database
Value indicative, texture eigenvalue and shape feature value, in addition, the identification information recording for the carpet pattern generates the carpet pattern
The identification information of corner grain pattern gene, main body grain pattern gene and frame grain pattern gene.
When user's scoring is relatively high, it has been more than given threshold, has illustrated that user is satisfied to the carpet pattern, so as to
To obtain the color feature value, texture eigenvalue and shape feature value of customer satisfaction system carpet pattern.Because being protected in feature database
There are the color feature value, texture eigenvalue and shape feature value of a large amount of carpet pattern, therefore the ground of the generation can be used
Color feature value, texture eigenvalue and the shape feature value of blanket pattern, with the color feature value of carpet pattern each in feature database,
Texture eigenvalue and shape feature value are matched, according to the color feature value, texture eigenvalue and shape feature of successful match
It is worth the identification information of corresponding carpet pattern, determines corner grain pattern gene, main body grain pattern gene and the side for generating the carpet pattern
Frame grain pattern gene generates corresponding carpet pattern according to determining each grain pattern gene.
Specifically, the lookup in feature database is matched with the color feature value, texture eigenvalue and shape feature value
The identification information of carpet pattern includes：
For the color feature value, texture eigenvalue and shape of the carpet pattern of each identification information saved in feature database
Characteristic value judges that the difference of the color feature value and the color feature value of the carpet pattern of the identification information in the feature database is
In the no first threshold range for being located at setting, and the carpet pattern of the identification information in the texture eigenvalue and the feature database
Whether the difference of texture eigenvalue is located within the scope of the second threshold of setting, and the mark in shape feature value and the feature database
Whether the difference of the shape feature value of the carpet pattern of information is located in the third threshold range of setting；If it is judged that being all
It is, it is determined that the carpet pattern of the identification information and the color feature value, texture eigenvalue and shape feature value in feature database
Match.
S104：According to the scoring of the user, the corresponding raising amount of the scoring is determined, by the color characteristic of the carpet pattern
The raising amount is respectively increased in value, texture eigenvalue and shape feature value, and searches and the color spy after raising in feature database
The identification information of value indicative, texture eigenvalue and the matched carpet pattern of shape feature value；According to the matched carpet found
The identification information of pattern determines each grain pattern gene of the carpet pattern of the identification information, generates ground according to each grain pattern gene
Blanket pattern.
When user's scoring is less than given threshold, illustrate that user does not feel quite pleased the carpet pattern, in order to generate user
In embodiments of the present invention the corresponding raising of the scoring can be arranged to the scoring for being less than given threshold in satisfied carpet pattern
Amount, the raising amount is for adjusting color feature value, texture eigenvalue and shape feature value.The raising amount is according to a large number of users
What aesthetical standard determined, which can be positive value and is also possible to negative value, thus, it can be known that in order to reach the satisfaction of user, when
The absolute value of its corresponding raising amount is larger when scoring smaller, and the absolute value of its corresponding raising amount is smaller when scoring larger.
It, will be by the color feature value, texture eigenvalue and shape of the carpet pattern after determining the corresponding raising amount of the scoring
The raising amount is respectively increased in characteristic value, and searches and the color feature value, texture eigenvalue and the shape after raising in feature database
The identification information of the matched carpet pattern of shape characteristic value, specifically includes：
For the color feature value, texture eigenvalue and shape of the carpet pattern of each identification information saved in feature database
Characteristic value, color feature value and the color feature value of the carpet pattern of the identification information in the feature database after judging the raising
Difference whether be located in the first threshold range of setting, and mark in the texture eigenvalue after the raising and the feature database
Whether the difference of the texture eigenvalue of the carpet pattern of information is located within the scope of the second threshold of setting, and the shape after the raising
Whether the difference of the shape feature value of the carpet pattern of the identification information is located at the third of setting in characteristic value and the feature database
In threshold range；If it is judged that being all yes, it is determined that the carpet pattern of the identification information and the color characteristic in feature database
Value, texture eigenvalue and the matching of shape feature value.
Due to determining color feature value, texture eigenvalue and the shape of each carpet pattern generated in embodiments of the present invention
Shape characteristic value generates the higher carpet pattern of user's scoring, thus the carpet pattern of the generation enable according to the scoring of user
It meets the needs of users as early as possible, improves the formation efficiency of carpet pattern, and improve the experience of user.
Specifically, determining that the color feature value of the carpet pattern includes in embodiments of the present invention：
According to the number of the pixel of pixel value each in the carpet pattern, the color histogram of the carpet pattern is determined
Figure, using the color histogram as the color feature value of the carpet pattern.
The texture eigenvalue for determining the carpet pattern includes：
According to co-occurrence matrix, the texture eigenvalue of carpet pattern is determined.
Wherein, using co-occurrence matrix, determine that the texture eigenvalue of pattern belongs to the prior art, it is right in embodiments of the present invention
The process is without repeating.
The shape feature value for determining the carpet pattern includes：
Using small wave converting method, the shape feature value of carpet pattern is determined.
Wherein, using small wave converting method, determine that the shape feature value of pattern belongs to the prior art, in the embodiment of the present invention
In to the process without repeating.
Fig. 3 is a kind of structural schematic diagram of pattern generating apparatus provided in an embodiment of the present invention, is applied to generate carpet figure
The electronic equipment of case, described device include：
Generation module 31 is extracted, for according to corner grain pattern gene, the main body grain pattern gene selected from grain pattern gene pool
Carpet pattern is generated with frame grain pattern gene；
First matching generation module 32, for obtaining user to the carpet pattern for the carpet pattern generated every time
Scoring, when judging that user is greater than given threshold to the scoring of the carpet pattern, according to the color feature value of the carpet pattern, texture
Characteristic value and shape feature value are searched matched with the color feature value, texture eigenvalue and shape feature value in feature database
The identification information of carpet pattern；According to the identification information of the matched carpet pattern found, the ground of the identification information is determined
Each grain pattern gene of blanket pattern generates carpet pattern according to each grain pattern gene；
Second matching generation module 33, for obtaining user to the carpet pattern for the carpet pattern generated every time
Scoring, when judging user to the scoring of the carpet pattern no more than given threshold, by the color feature value of the carpet pattern, texture
The raising amount is respectively increased in characteristic value and shape feature value, and searches and the color feature value after raising, line in feature database
Manage the identification information of characteristic value and the matched carpet pattern of shape feature value；According to the mark of the matched carpet pattern found
Know information, determine each grain pattern gene of the carpet pattern of the identification information, carpet pattern is generated according to each grain pattern gene.
The first matching determining module 32 and the second matching determining module 33, are specifically used for according in the carpet pattern
The number of the pixel of each pixel value determines the color histogram of the carpet pattern, using the color histogram as the carpet
The color feature value of pattern.
The first matching determining module 32 and the second matching determining module 33, are specifically used for being determined according to co-occurrence matrix
The texture eigenvalue of carpet pattern.
The first matching determining module 32 and the second matching determining module 33, are specifically used for using small wave converting method,
Determine the shape feature value of carpet pattern.
The first matching determining module 32 and the second matching determining module 33, specifically for for saving in feature database
Color feature value, texture eigenvalue and the shape feature value of the carpet pattern of each identification information, judge the color feature value with
Whether the difference of the color feature value of the carpet pattern of the identification information is located at the first threshold range of setting in the feature database
It is interior, and whether the difference of the texture eigenvalue and the texture eigenvalue of the carpet pattern of the identification information in the feature database is located at
Within the scope of the second threshold of setting, and the shape feature of shape feature value and the carpet pattern of the identification information in the feature database
Whether the difference of value is located in the third threshold range of setting；If it is judged that being all yes, it is determined that the mark of this in feature database
The carpet pattern for knowing information is matched with the color feature value, texture eigenvalue and shape feature value.
The embodiment of the invention provides a kind of method for generating pattern and device, this method is selected according to from grain pattern gene pool
Corner grain pattern gene, main body grain pattern gene and frame grain pattern gene generate carpet pattern；According to each user to the ground of generation
The scoring of blanket pattern is searched and the color feature value of the carpet pattern, line when the scoring is greater than given threshold in feature database
The identification information for managing characteristic value and the matched carpet pattern of shape feature value, according to the identification information of the carpet pattern found,
The each grain pattern gene for determining the carpet pattern of identification information generates carpet pattern according to each grain pattern gene；When the scoring not
When greater than given threshold, the corresponding raising amount of the scoring is determined, each characteristic value is improved into the amount of being correspondingly improved, in feature database
The identification information with the matched carpet pattern of characteristic value after the raising is searched, is believed according to the mark of the carpet pattern found
Breath, determines each grain pattern gene of the carpet pattern of identification information, generates carpet pattern according to each grain pattern gene.Due at this
In inventive embodiments determine generate each carpet pattern color feature value, texture eigenvalue and shape feature value, according to
The scoring at family generates the higher carpet pattern of user's scoring, so that the carpet pattern of the generation enable meets user's as early as possible
Demand, improves the formation efficiency of carpet pattern, and improves the experience of user.
For systems/devices embodiment, since it is substantially similar to the method embodiment, so the comparison of description is simple
Single, the relevent part can refer to the partial explaination of embodiments of method.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Those of ordinary skill in the art will appreciate that all or part of the steps in realization above method embodiment is can
It is completed with instructing relevant hardware by program, the program can store in computer-readable storage medium,
The storage medium designated herein obtained, such as：ROM/RAM, magnetic disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (8)
1. a kind of method for generating pattern, which is characterized in that applied to the electronic equipment for generating carpet pattern, this method includes：
Carpet figure is generated according to the corner grain pattern gene, main body grain pattern gene and frame grain pattern gene selected from grain pattern gene pool
Case；
For the carpet pattern generated every time, scoring of the user to the carpet pattern is obtained, judges user to the carpet pattern
When scoring is greater than given threshold, according to the color feature value of the carpet pattern, texture eigenvalue and shape feature value, in feature database
The identification information of middle lookup and the color feature value, texture eigenvalue and the matched carpet pattern of shape feature value；According to lookup
The identification information of the matched carpet pattern arrived determines each grain pattern gene of the carpet pattern of the identification information, according to every
A grain pattern gene generates carpet pattern；
When judging user to the scoring of the carpet pattern no more than given threshold, according to the scoring of the user, the scoring is determined
The raising amount is respectively increased in the color feature value of the carpet pattern, texture eigenvalue and shape feature value by corresponding raising amount,
And search in feature database with improve after the color feature value, texture eigenvalue and the matched carpet pattern of shape feature value
Identification information；According to the identification information of the matched carpet pattern found, the every of the carpet pattern of the identification information is determined
A grain pattern gene generates carpet pattern according to each grain pattern gene；
The mark searched in feature database with the color feature value, texture eigenvalue and the matched carpet pattern of shape feature value
Know information, including：
For the color feature value, texture eigenvalue and shape feature of the carpet pattern of each identification information saved in feature database
Value, judge the color feature value of the carpet pattern of the identification information in the color feature value and the feature database difference whether position
In in the first threshold range of setting, and in the texture eigenvalue and the feature database carpet pattern of the identification information texture
Whether the difference of characteristic value is located within the scope of the second threshold of setting, and the identification information in shape feature value and the feature database
The difference of shape feature value of carpet pattern whether be located in the third threshold range of setting；If it is judged that be all it is yes,
Then determine that the carpet pattern of the identification information in feature database is matched with the color feature value, texture eigenvalue and shape feature value.
2. the method as described in claim 1, which is characterized in that the color feature value for determining the carpet pattern includes：
According to the number of the pixel of pixel value each in the carpet pattern, the color histogram of the carpet pattern is determined, it will
Color feature value of the color histogram as the carpet pattern.
3. the method as described in claim 1, which is characterized in that the texture eigenvalue for determining the carpet pattern includes：
According to co-occurrence matrix, the texture eigenvalue of carpet pattern is determined.
4. the method as described in claim 1, which is characterized in that the shape feature value for determining the carpet pattern includes：
Using small wave converting method, the shape feature value of carpet pattern is determined.
5. a kind of pattern generating apparatus, which is characterized in that applied to the electronic equipment for generating carpet pattern, described device includes：
Generation module is extracted, for according to corner grain pattern gene, main body grain pattern gene and the frame selected from grain pattern gene pool
Grain pattern gene generates carpet pattern；
First matching generation module, for obtaining scoring of the user to the carpet pattern, sentencing for the carpet pattern generated every time
When disconnected user is greater than given threshold to the scoring of the carpet pattern, according to the color feature value of the carpet pattern, texture eigenvalue
With shape feature value, searched and the color feature value, texture eigenvalue and the matched carpet figure of shape feature value in feature database
The identification information of case；According to the identification information of the matched carpet pattern found, the carpet pattern of the identification information is determined
Each grain pattern gene, according to each grain pattern gene generate carpet pattern；
Second matching generation module, for obtaining scoring of the user to the carpet pattern, sentencing for the carpet pattern generated every time
When disconnected user is not more than given threshold to the scoring of the carpet pattern, according to the scoring of the user, determine that the scoring is corresponding
The raising amount is respectively increased in the color feature value of the carpet pattern, texture eigenvalue and shape feature value by raising amount, and in spy
The mark for levying the color feature value searched in library with after raising, texture eigenvalue and the matched carpet pattern of shape feature value is believed
Breath；According to the identification information of the matched carpet pattern found, each grain pattern of the carpet pattern of the identification information is determined
Gene generates carpet pattern according to each grain pattern gene；
The first matching determining module and the second matching determining module, specifically for for each mark saved in feature database
Color feature value, texture eigenvalue and the shape feature value of the carpet pattern of information, judge the color feature value and the feature
Whether the difference of the color feature value of the carpet pattern of the identification information is located in the first threshold range of setting in library, and the line
Whether the difference of the texture eigenvalue of the carpet pattern of the identification information is located at the of setting in reason characteristic value and the feature database
In two threshold ranges, and the difference of shape feature value and the shape feature value of the carpet pattern of the identification information in the feature database
Whether it is located in the third threshold range of setting；If it is judged that being all yes, it is determined that the identification information of this in feature database
Carpet pattern is matched with the color feature value, texture eigenvalue and shape feature value.
6. device as claimed in claim 5, which is characterized in that the first matching determining module and second matches determining mould
Block determines that the color of the carpet pattern is straight specifically for the number according to the pixel of pixel value each in the carpet pattern
Fang Tu, using the color histogram as the color feature value of the carpet pattern.
7. device as claimed in claim 5, which is characterized in that the first matching determining module and second matches determining mould
Block is specifically used for determining the texture eigenvalue of carpet pattern according to co-occurrence matrix.
8. device as claimed in claim 5, which is characterized in that the first matching determining module and second matches determining mould
Block is specifically used for using small wave converting method, determines the shape feature value of carpet pattern.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510447137.6A CN105138732B (en) | 2015-07-27 | 2015-07-27 | A kind of method for generating pattern and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510447137.6A CN105138732B (en) | 2015-07-27 | 2015-07-27 | A kind of method for generating pattern and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105138732A CN105138732A (en) | 2015-12-09 |
| CN105138732B true CN105138732B (en) | 2018-11-23 |
Family
ID=54724079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510447137.6A Active CN105138732B (en) | 2015-07-27 | 2015-07-27 | A kind of method for generating pattern and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105138732B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680145A (en) * | 2017-08-11 | 2018-02-09 | 清远川奥高新材料有限公司 | A kind of ground cushion image rapid generation and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584465B1 (en) * | 2000-02-25 | 2003-06-24 | Eastman Kodak Company | Method and system for search and retrieval of similar patterns |
| CN101824712A (en) * | 2009-12-31 | 2010-09-08 | 上海市色织科学技术研究所 | Method and device for controlling carpet loom apparatus to automatically generate pattern on base fabric |
| CN102637236A (en) * | 2012-05-03 | 2012-08-15 | 杭州慕锐网络技术有限公司 | Intelligent color matching method for textile patterns |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8582802B2 (en) * | 2009-10-09 | 2013-11-12 | Edgenet, Inc. | Automatic method to generate product attributes based solely on product images |
-
2015
- 2015-07-27 CN CN201510447137.6A patent/CN105138732B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584465B1 (en) * | 2000-02-25 | 2003-06-24 | Eastman Kodak Company | Method and system for search and retrieval of similar patterns |
| CN101824712A (en) * | 2009-12-31 | 2010-09-08 | 上海市色织科学技术研究所 | Method and device for controlling carpet loom apparatus to automatically generate pattern on base fabric |
| CN102637236A (en) * | 2012-05-03 | 2012-08-15 | 杭州慕锐网络技术有限公司 | Intelligent color matching method for textile patterns |
Non-Patent Citations (4)
| Title |
|---|
| 基于拓扑构型的地毯图案生成方法;赵海英等;《计算机辅助设计与图形学学报》;20130415;第25卷(第4期);第502-509页 * |
| 基于进化计算的地毯图案生成方法;赵海英等;《图学学报》;20150215;第36卷(第1期);第41-46页正文第1节倒数第1段，第2节-第3节，图1-图2 * |
| 新疆民间艺术图案数字化技术;赵海英等;《计算机系统应用》;20111215;第20卷(第12期);第167-172页 * |
| 维吾尔族地毯图案数字化技术;赵海英等;《纺织学报》;20120415;第33卷(第4期);第142-145页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105138732A (en) | 2015-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108010041A (en) | Human heart coronary artery extracting method based on deep learning neutral net cascade model | |
| CN102360490B (en) | Color conversion and editing propagation-based method for enhancing seasonal feature of image | |
| CN108898145A (en) | A kind of image well-marked target detection method of combination deep learning | |
| CN101599179A (en) | Method for automatically generating field motion wonderful scene highlights | |
| CN103544685B (en) | A kind of image composition beautification method adjusted based on main body and system | |
| CN108537239A (en) | A kind of method of saliency target detection | |
| CN108647663A (en) | Estimation method of human posture based on deep learning and multi-level graph structure model | |
| CN101739434A (en) | Multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method | |
| CN105205846B (en) | Ink animation production method | |
| CN103761736B (en) | A kind of image partition method based on Bayes's harmony degree | |
| CN108829711A (en) | A kind of image search method based on multi-feature fusion | |
| CN105139342A (en) | Method and device for zooming pictures | |
| CN104915952B (en) | Local protrusion object extraction method based on multiway tree in a kind of depth image | |
| CN105138732B (en) | A kind of method for generating pattern and device | |
| Du et al. | Double-channel guided generative adversarial network for image colorization | |
| CN116308530A (en) | Advertisement implantation method, advertisement implantation device, advertisement implantation equipment and readable storage medium | |
| Sormann et al. | Graph cut based multiple view segmentation for 3d reconstruction | |
| CN104331883A (en) | Image boundary extraction method based on non-symmetry and anti-packing model | |
| CN104766367B (en) | Three-dimensional gridding topology structure chart construction method in computing three-dimensional model processing | |
| CN115272057A (en) | Training of cartoon sketch image reconstruction network and reconstruction method and equipment thereof | |
| Ding et al. | Real-time interactive image segmentation using improved superpixels | |
| CN114998472B (en) | Method and device for determining shoe color matching, electronic equipment and storage medium | |
| CN104091318B (en) | A kind of synthetic method of Chinese Sign Language video transition frame | |
| Guo et al. | Image saliency detection based on geodesic‐like and boundary contrast maps | |
| CN105263025B (en) | A kind of video Zero watermarking method based on time-space domain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |