CN110489794B - Construction method of happy and tall building block plane drawing facing simple strokes - Google Patents
Construction method of happy and tall building block plane drawing facing simple strokes Download PDFInfo
- Publication number
- CN110489794B CN110489794B CN201910636575.5A CN201910636575A CN110489794B CN 110489794 B CN110489794 B CN 110489794B CN 201910636575 A CN201910636575 A CN 201910636575A CN 110489794 B CN110489794 B CN 110489794B
- Authority
- CN
- China
- Prior art keywords
- building block
- model
- matrix
- building blocks
- pixel matrix
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
Abstract
The invention relates to a computer aided design technology, in particular to a construction method of a happy and tall building block plane drawing facing to simplified strokes, which comprises the following steps: step 1, converting the basic building block into a corresponding building block matrix model according to the number of convex grains of the basic building block of the Gao type, the arrangement rule of the convex grains and other characteristics; step 2, extracting a skeleton of the simple stroke image, and converting the image into a pixel matrix model; step 3, taking the building block matrix model as a discrete variable and the pixel matrix model as a target, and obtaining a set of feasible solutions through a genetic algorithm; and 4, analyzing the set of feasible solutions to obtain a Legao plane model and a drawing which are most similar to the original simple strokes. The method provides a solution for converting the simple stroke image into the corresponding building block model drawing, any input simple stroke can be converted into the drawing of the successfully-built Happy high type building block model, personalized customization service of the Happy high type drawing is realized, and the abilities in various aspects such as artistic aesthetic feeling, practical practice and the like of children are improved.
Description
Technical Field
The invention belongs to the technical field of computer aided design, and particularly relates to a construction method of a happy building block plane drawing facing to simplified strokes.
Background
The Legao type building block is a plastic building block splicing toy with convex grains on the upper surface and corresponding quantity of convex grains embedded in the bottom surface. The user can use different kinds of building blocks to plan and build any model according to the imagination of the user. Because the building blocks are wide in building range, building results are not limited, and various building cases are developed. The happy building blocks are also popular among users of all countries in the world.
For users with small ages, it is difficult to build a complex model of music height by autonomous design. In order to simplify the difficulty of building models for children, the Legao company provides matched building drawings for each set of the sold Legao building block toys, and provides corresponding electronic files on an official website for auxiliary explanation.
However, the matching drawings provided by the le Gao company cannot be converted from self-defined drawings to drawings, and cannot realize personalized drawing customization service. For a given picture, it is difficult for the user to convert to a happy paper. If the infant user wants to find the happy drawing corresponding to the simplified stroke of the heart instrument, the infant user can only turn to a happy-related discussion community under the existing method, but the process is complex and ineffective.
Currently, the mainstream software related to building le gao type building blocks is Lego Digit Designer (LDD for short). The method realizes a software system, so that a user can simulate building operation by using the virtual building blocks in a computer to further obtain a virtual happy model. Known software related to the construction of a building block of the le Gao type converts the building block into a virtual model, thereby performing a virtual operation. The software is not yet able to build drawings as required by the user.
The construction of a model drawing is a complex problem for any user; it is a very difficult problem for the infant user with insufficient design ability. If the problem can be solved, the requirements of the infant can be better met, the interest of the infant in the educational toy is promoted, the number of times of hands-on practice of the infant is increased, and the aesthetic feeling, the hands-on ability and other related abilities of the infant are exercised.
Disclosure of Invention
The invention aims to provide a drawing which can convert any input simple strokes into a happy building block model which can be successfully built. Therefore, personalized customization service of the Happy building block drawing is realized.
In order to achieve the purpose, the invention adopts the technical scheme that: a construction method of a happy and tall building block plane drawing facing to simplified strokes comprises the following steps:
step 2, extracting a skeleton of the simple stroke image, and converting the image into a pixel matrix model;
step 3, taking the building block matrix model as a discrete variable and the pixel matrix model as a target, and obtaining a set of feasible solutions through a genetic algorithm;
and 4, analyzing the set of feasible solutions to obtain a Legao plane model and a drawing which are most similar to the original simple strokes.
In the above construction method of the le Gao type building block plane drawing oriented to the simple strokes, the rules for converting the characteristics into the corresponding building block matrix model in the step 1 are as follows: the characteristics of the basic building blocks of the Gaoyao type comprise the color of the building blocks, the number of convex grains of the building blocks and the arrangement rule of the convex grains; the number of the convex grains is the number of elements of the building block matrix model, and the arrangement rule of the convex grains is the array arrangement rule of the building block matrix model; the basic building blocks of the Happy Gao type are rectangular building blocks, building blocks with different shapes are endowed with different numbers, and building blocks with the same shape are endowed with different numbers according to different colors; the building blocks with the same shape and the same color are endowed with different numbers according to different placing forms; the numbering of the blocks starts with 1.
In the above construction method of the le Gao type building block plane drawing oriented to the simple strokes, the rule of converting the image into the pixel matrix model in step 2 is as follows: the simple stroke image is an image in a picture form represented by simple lines; and (3) representing the image in a 0-1 matrix, setting 1 to the matrix part element covered by the line and 0 to the matrix part element uncovered by the line, and further obtaining a pixel matrix model of the image.
In the above method for constructing a simplified stroke-oriented Happy high-class building block plane drawing, the step 3 of obtaining a set of feasible solutions by a genetic algorithm includes the following steps:
step 3.1, inputting the simple stroke image, and generating a pixel matrix with moderate size according to the pixel size of the simple stroke image; setting the value of a pixel matrix element corresponding to the position covered by the line in the original simple stroke image as 1, and setting the other pixel matrix elements as 0 to obtain a pixel matrix corresponding to the simple stroke image;
step 3.2, converting pixel matrix elements corresponding to the obtained simple stroke image into vectors with the length same as the number of the pixel matrix elements from left to right and from top to bottom; each element of the original pixel matrix corresponds to each dimensionality of the vector in sequence one by one; the vector is used as a final target result of the genetic algorithm;
3.3, initializing a population, wherein if a building block does not exist at a certain position, the vector dimension corresponding to the position is set to be 0; setting the initial positions of the dimensionalities corresponding to all the positions of the pixel matrixes covered by the building blocks as the serial numbers of the building blocks in the vectors corresponding to the pixel matrixes, and setting the residual positions as-1; generating a certain number of vectors meeting requirements in a random form to serve as an initialization population;
and 3.4, continuously screening and iterating the initialized population according to a proper fitness function in the crossing and variation process until a satisfactory set of feasible solutions is obtained.
In the construction method of the above-mentioned yugao type building block plane drawing oriented to the simple sketches, when a certain dimension of a vector is-1 in the process of crossing and variation, the dimension of the vector does not cross a certain dimension of other vectors or the dimension of the vector does not have variation operation;
in the above construction method of the le Gao-like building block plane drawing oriented to the simplified strokes, the step 4 of analyzing the set of feasible solutions to obtain the le Gao plane model and the drawing most similar to the original simplified strokes comprises the following steps,
4.1, sorting the set of feasible solutions according to the similarity degree of the original sketch images, wherein the higher the similarity degree is, the higher the ranking is; comparing the similarity degree between the pixel matrix corresponding to different solutions and the pixel matrix corresponding to the original simple stroke image by taking a similarity measurement method as a basis value;
4.2, converting the vector of the feasible solution with the top rank into a matrix form, and converting each element in the matrix into a corresponding building block matrix model to obtain a drawing corresponding to the original simple drawing; and simultaneously recording the number of the corresponding building block matrix model, and outputting the number in the form of a plane model and a drawing.
The invention has the beneficial effects that: most of the prior art related to the le gao type building blocks mainly aims at realizing the building process of the le gao type building blocks in a virtual space. The invention provides a solution for converting simplified stroke images into corresponding building block model drawings, any input simplified stroke can be converted into the drawings of the successively constructed le Gao type building block models, the personalized customization service of the le Gao type building block drawings is realized, the friendliness degree and the attraction of the intelligence-developing toys to the children of low age are improved, and the aesthetic and practical abilities of the children are enhanced.
Drawings
FIG. 1 is a flow chart of a construction method of a simplified stroke-oriented Happy high-class building block plane drawing in one embodiment of the invention;
FIG. 2 is a schematic representation of a model of a Lego block according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a pixel matrix of simple strokes in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart of the use of a genetic algorithm in an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The embodiment provides a solution from the simple strokes to the generation of the Happy building block model drawing paper so as to improve the attraction of the Happy to children.
The embodiment is realized by the following technical scheme, as shown in fig. 1, a method for constructing a simplified stroke-oriented le Gao type building block plane drawing comprises the following steps:
s1: and modeling the basic building blocks of the Gao type, and converting the building blocks of different shapes into corresponding building block matrix models according to the number of the convex grains, the arrangement rule of the convex grains and other characteristics.
S2: scanning and recognizing the input simple stroke images, extracting the skeletons of the images by using a graphic image processing technology, and converting the images into pixel matrix models with proper sizes.
S3: and taking the Legao type building block matrix model as a discrete variable, taking the pixel matrix model as a target, and obtaining a set of feasible solutions by using a genetic algorithm.
S4: and further analyzing the obtained feasible solution set to obtain a Legao plane model and a drawing which are most similar to the original simple strokes, and recommending the plane model and the drawing to the user.
In step S1, the characteristics of the basic building blocks include the color of the building blocks, the number of the convex particles of the building blocks, and the arrangement rule of the convex particles, where the number of the convex particles is the number of elements of the building block matrix, and the arrangement rule of the convex particles is the array arrangement rule of the building block matrix; the basic building blocks referred to herein are rectangular blocks; the numbers of the building blocks with different shapes are different; the numbers of the building block models in the same shape are different according to different colors; the building block models with the same shape and the same color have different numbers according to different placing forms (two placing forms of horizontal placing and vertical placing); the numbering of the blocks starts with 1.
In step S2, the input simple stroke is an image represented by a simple line in a picture format, and the image is represented in a 0-1 matrix, with 1 being set in the matrix part element covered by the line and 0 being set in the matrix part element uncovered by the line, thereby obtaining a pixel matrix model of the image.
In step S3, the initial population includes a plurality of vectors having the same length as the number of elements of the pixel matrix, and each element of the pixel matrix sequentially corresponds to each dimension of the vector from left to right and from top to bottom; in the process of initializing a population, if a building block does not exist at a certain position, setting the vector dimension corresponding to the position as 0; setting the initial positions of the dimensionalities corresponding to the positions as the serial numbers of the building blocks in the vectors corresponding to the pixel matrixes for all the positions of the pixel matrixes covered by the building blocks, and setting the residual positions as-1; the building blocks can not be stacked; generating a certain number of vectors meeting requirements in a random form to serve as an initialization population; and continuously screening and iterating the initialized population according to a proper fitness function in the crossing and variation processes until a satisfactory set of feasible solutions is obtained.
The condition of building block stacking can not occur in the process of crossing and mutation, namely when one dimension of the vector is-1, the dimension of the vector can not cross with one dimension of other vectors or the dimension of the vector can not have mutation operation.
And, in step S4, the set of feasible solutions is sequenced; and recommending the feasible solution with the top ranking to the user in the form of a plane model and a drawing.
And sorting the set of feasible solutions according to the similarity degree of the set of feasible solutions and the original sketch image, wherein the higher the similarity degree is, the higher the ranking is. A similarity measure method may be used as a basis value to compare the similarity between the pixel matrix corresponding to the different solutions and the pixel matrix corresponding to the original simple stroke image.
The happy Gao model constructed through the generated drawing is planar, the model is laid on a building block base of the happy Gao, and the height of the model is a layer of happy Gao type building blocks.
When the building block is specifically implemented, firstly, the existing building blocks of the Gaoqi type are modeled. Convert the basic building blocks of happy high class building blocks into the matrix model according to certain characteristic, the characteristic of building block includes: the color of the building blocks, the number of the convex grains of the building blocks and the arrangement rule of the convex grains. The basic building blocks referred to herein are rectangular blocks. The number of the convex grains of the building block is the number of elements of the building block matrix, and the arrangement rule of the convex grains is the arrangement rule of the building block matrix. Meanwhile, numbering different types of building block models, wherein the building block models in different shapes are numbered differently, and the building block models in the same shape are numbered differently according to different colors; the number of the building block models with the same shape and the same color is different according to different placing forms (the building block models have two placing forms of horizontal placing and vertical placing). The form of the building block model matrix is shown in fig. 2.
The processing of the input strokes can be started after the modeling of the basic building blocks is completed. For the input simple stroke, firstly, a moderate pixel matrix is generated according to the pixel size of the simple stroke. The pixel positions of the simple strokes all correspond to elements in the pixel matrix one to one. In the original simple stroke image, the value of the pixel matrix element corresponding to the position covered by the line is set to 1, and the values of the other elements are set to 0, so as to obtain the pixel matrix corresponding to the simple stroke image. FIG. 3 shows a pixel matrix model obtained after image recognition and processing of "H".
The feasible solution to the problem is a vector. The length of the vector is consistent with the length of a target vector converted from the simple stroke pixel matrix, and each dimension of the vector also corresponds to each element of the pixel matrix in sequence. In this vector, the values of the dimensions contain different meanings: when the value of the dimension is-1, the element corresponding to the dimension cannot be placed in the building block model; when the value of the dimension is 0, the element corresponding to the dimension is not provided with the building block model; when the value of the dimension is n (n >0), the element corresponding to the dimension is indicated to place the building block model with the number of n. The feasible solution vector can be converted into a pixel matrix according to a specific format, and the pixel matrix is a possible drawing of an original simple drawing with building block model information.
And after a pixel matrix model corresponding to the simple stroke is obtained, converting the pixel matrix model into vectors with the length same as the number of the elements of the pixel matrix from left to right and from top to bottom. And each element of the original pixel matrix corresponds to each dimension of the vector one by one in sequence. The vector serves as the final target result of the genetic algorithm. In the process of genetic algorithm, a plurality of vectors with the same length as the target result vector are randomly generated to serve as an initial population. In the vectors, if a certain position is not covered by a building block, the vector dimension corresponding to the position is set to be 0; setting initial positions of dimensionalities corresponding to the positions as the serial numbers of the building block models in vectors corresponding to the pixel matrixes for all the positions in the pixel matrixes covered by a certain building block, and setting dimensionalities corresponding to the rest positions as-1; there cannot be stacking between blocks, i.e. only one value can be contained in one dimension of the vector. After the population initialization is completed, free crossover and mutation are performed. It should be noted that, because stacking cannot occur between building blocks, when a value of a certain dimension is-1, it indicates that a region corresponding to the dimension belongs to a sub-region of the certain building block, and if the local region performs intersection and mutation operations, it is a case that the building blocks are stacked in the region as a result, and thus such dimension does not participate in the intersection and mutation. After many variations, intersections and screening operations, a set of solutions satisfying the conditions can be obtained. The specific process is shown in fig. 4.
And after the solution set is obtained, comparing the elements in the set with the target vector, and finding the elements which are similar to the target vector by adopting a cosine similarity measurement method. The cosine similarity measurement method refers to that a cosine value between included angles of two vectors in a vector space is used as a numerical value for measuring difference between two individuals, and the closer the cosine value is to 1, the closer the included angle is to 0, the more similar the two vectors are. And arranging the feasible solutions and the cosine values of the target vectors in a descending order to obtain feasible solutions with top ranks. And converting the vector with the top rank into a matrix form, and converting each element in the matrix into a corresponding building block model, so as to obtain the drawing corresponding to the original simple drawing. And meanwhile, recording the number of the used building block model, and transmitting the number to a user as output together with a drawing.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
Although specific embodiments of the present invention have been described above with reference to the accompanying drawings, it will be appreciated by those skilled in the art that these are merely illustrative and that various changes or modifications may be made to these embodiments without departing from the principles and spirit of the invention. The scope of the invention is only limited by the appended claims.
Claims (2)
1. A construction method of a happy and tall building block plane drawing facing to simplified strokes is characterized by comprising the following steps:
step 1, converting into a corresponding building block matrix model according to the quantity of convex grains of basic building blocks of the Gao type and the arrangement rule characteristics of the convex grains;
step 2, extracting a skeleton of the simple stroke image, and converting the image into a pixel matrix model;
step 3, taking the building block matrix model as a discrete variable and the pixel matrix model as a target, and obtaining a set of feasible solutions through a genetic algorithm;
step 4, analyzing the set of feasible solutions to obtain a Legao plane model and a drawing which are most similar to the original simple strokes;
step 1, converting the number of the convex grains of the basic building block of the Gao type and the arrangement rule characteristics of the convex grains into corresponding building block matrix models according to the following rules: the characteristics of the basic building blocks of the Gaoyao type comprise the color of the building blocks, the number of convex grains of the building blocks and the arrangement rule of the convex grains; the number of the convex grains is the number of elements of the building block matrix model, and the arrangement rule of the convex grains is the array arrangement rule of the building block matrix model; the basic building blocks of the Happy and tall building blocks are rectangular building blocks, building blocks with different shapes are endowed with different numbers, and building blocks with the same shape are endowed with different numbers according to different colors; the building blocks with the same shape and the same color are endowed with different numbers according to different placing forms; the numbering of the blocks starts with 1;
step 2, the rule of converting the image into the pixel matrix model is as follows: the simple stroke image is an image in a picture form represented by simple lines; the image is represented in a 0-1 matrix, the matrix part elements covered by the lines are set to be 1, the matrix part elements uncovered by the lines are set to be 0, and then a pixel matrix model of the image is obtained;
step 3, the step of obtaining the feasible solution set through the genetic algorithm comprises the following steps:
step 3.1, inputting the simple stroke image, and generating a pixel matrix with moderate size according to the pixel size of the simple stroke image; setting the value of a pixel matrix element corresponding to the position covered by the line in the original simple stroke image as 1, and setting the other pixel matrix elements as 0 to obtain a pixel matrix corresponding to the simple stroke image;
step 3.2, converting pixel matrix elements corresponding to the obtained simple stroke image into vectors with the length same as the number of the pixel matrix elements from left to right and from top to bottom; each element of the original pixel matrix corresponds to each dimensionality of the vector in sequence one by one; the vector is used as a final target result of the genetic algorithm;
3.3, initializing a population, wherein if a building block does not exist at a certain position, the vector dimension corresponding to the position is set to be 0; setting the initial positions of the dimensionalities corresponding to all the positions of the pixel matrixes covered by the building blocks as the serial numbers of the building blocks in the vectors corresponding to the pixel matrixes, and setting the residual positions as-1; generating a certain number of vectors meeting requirements in a random form to serve as an initialization population;
step 3.4, continuously screening and iterating the initialized population according to a proper fitness function in the crossing and variation process until a satisfactory set of feasible solutions is obtained;
step 4, analyzing the set of feasible solutions to obtain a Legao plane model and a drawing which are most similar to the original simple strokes comprises the following steps,
4.1, sorting the set of feasible solutions according to the similarity degree of the original sketch images, wherein the higher the similarity degree is, the higher the ranking is; comparing the similarity degree between the pixel matrix corresponding to different solutions and the pixel matrix corresponding to the original simple stroke image by taking a similarity measurement method as a basis value;
4.2, converting the vector of the feasible solution with the top rank into a matrix form, and converting each element in the matrix into a corresponding building block matrix model to obtain a drawing corresponding to the original simple drawing; and simultaneously recording the number of the corresponding building block matrix model, and outputting the number in the form of a plane model and a drawing.
2. The method as claimed in claim 1, wherein when a dimension of the vector is-1 during the crossing and mutation process, the dimension of the vector is not crossed with a dimension of other vectors or there is no mutation operation in the dimension of the vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910636575.5A CN110489794B (en) | 2019-07-15 | 2019-07-15 | Construction method of happy and tall building block plane drawing facing simple strokes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910636575.5A CN110489794B (en) | 2019-07-15 | 2019-07-15 | Construction method of happy and tall building block plane drawing facing simple strokes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110489794A CN110489794A (en) | 2019-11-22 |
| CN110489794B true CN110489794B (en) | 2022-08-05 |
Family
ID=68547136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910636575.5A Active CN110489794B (en) | 2019-07-15 | 2019-07-15 | Construction method of happy and tall building block plane drawing facing simple strokes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489794B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992472A (en) * | 2019-12-06 | 2020-04-10 | 广东邦宝益智玩具股份有限公司 | Building block 3D model intelligent building system construction method |
| CN115364494B (en) * | 2022-07-26 | 2024-02-23 | 福州市鹭羽智能科技有限公司 | Automatic stacking device and method for building blocks based on patterns |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294864A (en) * | 2013-05-29 | 2013-09-11 | 南京大学 | Computer-aided disordered needlework manufacture method using genetic algorithms |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7467154B2 (en) * | 2005-06-29 | 2008-12-16 | Microsoft Corporation | Producing a locally optimal path through a lattice by overlapping search |
| JP2013066146A (en) * | 2011-08-31 | 2013-04-11 | Sony Corp | Image processing device, image processing method, and program |
-
2019
- 2019-07-15 CN CN201910636575.5A patent/CN110489794B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294864A (en) * | 2013-05-29 | 2013-09-11 | 南京大学 | Computer-aided disordered needlework manufacture method using genetic algorithms |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110489794A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111632374B (en) | Method and device for processing face of virtual character in game and readable storage medium | |
| Jürgens et al. | The language of fractals | |
| CN107392984A (en) | A kind of method and computing device based on Face image synthesis animation | |
| US20140114630A1 (en) | Generating Artifacts based on Genetic and Breeding Simulation | |
| CN110489794B (en) | Construction method of happy and tall building block plane drawing facing simple strokes | |
| CN108062796A (en) | Hand work and virtual reality experience system and method based on mobile terminal | |
| CN108121975A (en) | A kind of face identification method combined initial data and generate data | |
| CN111967533B (en) | Sketch image translation method based on scene recognition | |
| CN107729311A (en) | A kind of Chinese text feature extracting method of the fusing text tone | |
| CN112102480B (en) | Image data processing method, apparatus, device and medium | |
| CN112085835B (en) | Three-dimensional cartoon face generation method and device, electronic equipment and storage medium | |
| CN107993490A (en) | Mathematical operation equipment, teaching aid, platform and the method that it is provided | |
| CN104281865B (en) | A kind of method and apparatus for generating Quick Response Code | |
| CN113096001A (en) | Image processing method, electronic device and readable storage medium | |
| CN107077746A (en) | System, method and computer program product for network transmission and the Automatic Optimal of the 3D texture models of real-time rendering | |
| CN110889718A (en) | Method and apparatus for screening program, medium, and electronic device | |
| Harjoseputro et al. | The Javanese letters classifier with mobile client-server architecture and convolution neural network method | |
| CN110097615B (en) | Stylized and de-stylized artistic word editing method and system | |
| Ono et al. | LEGO builder: automatic generation of LEGO assembly manual from 3D polygon model | |
| Wang et al. | Generative model with coordinate metric learning for object recognition based on 3D models | |
| Sideris et al. | Making a new world out of an old one: in search of a common language for archaeological immersive VR representation | |
| Zhao et al. | Learning from the tangram to solve mini visual tasks | |
| Ryu et al. | A serious game design for english education on Smart TV platform | |
| US11657569B1 (en) | Method for creating a tangible objection and digitizing the tangible object using an artificial intelligence process | |
| CN112613495B (en) | Real person video generation method and device, readable storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |