CN109035357A - A kind of automatic drawing method of artificial intelligence - Google Patents
A kind of automatic drawing method of artificial intelligence Download PDFInfo
- Publication number
- CN109035357A CN109035357A CN201810753008.3A CN201810753008A CN109035357A CN 109035357 A CN109035357 A CN 109035357A CN 201810753008 A CN201810753008 A CN 201810753008A CN 109035357 A CN109035357 A CN 109035357A
- Authority
- CN
- China
- Prior art keywords
- hand drawing
- drawing pattern
- path
- pattern
- hand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 30
- 238000010422 painting Methods 0.000 claims abstract description 19
- 239000003973 paint Substances 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000007689 inspection Methods 0.000 claims abstract description 5
- 241001269238 Data Species 0.000 claims description 6
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 208000001491 myopia Diseases 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007591 painting process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present invention provides a kind of automatic drawing method of artificial intelligence, which is characterized in that the automatic drawing method of artificial intelligence includes: S1: obtaining hand drawing pattern data and handles hand drawing pattern path data;S2: hand drawing pattern route characteristic is extracted;S3: understanding and uses the route characteristic extracted;S4: moving towards according to the path that the hand drawing pattern route characteristic of extraction and hand drawing pattern routing algorithm model calculate, and generates automatic drawing path and can paint;S5: hand drawing pattern is painted route availability inspection automatically;S6: automatic drawing path is returned to, automatic painting function is completed.The automatic drawing method of artificial intelligence of the invention only needs to draw seldom a part of pattern, and the pattern that model can be drawn according to user moves towards according to the path calculated in existing lines style and model, continues to complete the complete drafting of hand drawing pattern.
Description
Technical field
The present invention relates to hand drawing pattern identification and image regeneration fields, and in particular to a kind of artificial intelligence side of drawing automatically
Method.
Background technique
In the short-sighted frequency production process of Freehandhand-drawing, Freehandhand-drawing material and text are the principal visual component parts in video.And hand
It draws the Freehandhand-drawing SVG and bitmap material that material is provided by Freehandhand-drawing platform and the hand drawing pattern that user draws forms.Compared to platform
The material of offer, the hand drawing pattern that user draws can more show the idea of user, embody the style of user.
However it is limited to drawing level, although many people want the idea that makes a display of one's by the short-sighted frequency of Freehandhand-drawing, but do not have
There is method to draw out beautiful hand drawing pattern, or is unable to complete drafting in a short time.
Especially on computer equipment, user can only by mouse or touch screen controlling equipment come hand drawing pattern, Freehandhand-drawing
Difficulty and time cost can further increase, and cause user that can only complete to create by selecting or adding existing Freehandhand-drawing material
Process.
The technology of automatic drawing aspect at present, the Freehandhand-drawing path of mainly preset several fixations of use, is supplied to user
Selection uses, or the stretch diameter drawn according to user carries out picture similarity mode and selects again, and this implementation is used
Family can not embody the drawing style of oneself, can not also select the path type outside preset, be difficult meet demand.
Summary of the invention
In view of this, the present invention provides a kind of automatic drawing method of artificial intelligence, it is only necessary to seldom a part of pattern is drawn,
The pattern that model can be drawn according to user, moves towards according to the path calculated in existing lines style and model, has continued
At the complete drafting of hand drawing pattern.
The present invention provides a kind of automatic drawing method of artificial intelligence, which is characterized in that the artificial intelligence side of drawing automatically
Method includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it is moved towards, is generated according to the path that the hand drawing pattern route characteristic of extraction and hand drawing pattern routing algorithm model calculate
Automatic drawing path can paint;
S5: hand drawing pattern is painted route availability inspection automatically;
S6: automatic drawing path is returned to, automatic painting function is completed.
Further, the automatic drawing method of the artificial intelligence further includes algorithm model generating process, comprising:
Data training is carried out to multiple hand drawing pattern path datas and multiple hand drawing pattern style datas and generates hand drawing pattern
Algorithm model.
Further, the automatic drawing method of the artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar automatic drawing path of diameter feature;
S5: the validity in path of painting automatically to hand drawing pattern checks;
S6: it returns to hand drawing pattern and paints automatically path, complete automatic painting function.
Further, the automatic drawing method of the artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar a variety of automatic drawing paths of diameter feature;
S5: the paint automatically validity in path of a variety of hand drawing patterns is checked;
S6: returning to a variety of hand drawing patterns and paint automatically path, completes to draw automatically according to different hand drawing patterns path of painting automatically
Function is drawn, a variety of drawing is generated, user is allowed to select in a variety of drawing of generation.
The advantages and positive effects of the present invention are: user only needs to draw seldom a part of pattern, model
According to the pattern that user draws, is moved towards according to the path calculated in existing lines style and model, continue to complete hand drawing pattern
Complete drafting.In automatic drawing process, user can modify and adjust, and algorithm can be in real time according to the newest tune of user
The adjustment of the whole path trend as a result, progress is painted automatically.Personal drawing style and fastly can be retained by thus meeting user
The demand that hand drawing pattern required for speed is completed is drawn.
Detailed description of the invention
Fig. 1 is a kind of schematic diagram of the automatic drawing method first embodiment of artificial intelligence of the invention;
Fig. 2 is a kind of schematic diagram of the automatic drawing method second embodiment of artificial intelligence of the invention;
Fig. 3 is a kind of schematic diagram of the automatic drawing method 3rd embodiment of artificial intelligence of the invention;
Fig. 4 is the structural schematic diagram of the application learning database;
Fig. 5 is the schematic diagram for automatically generating a variety of drawing paths of third embodiment of the invention.
Specific embodiment
In order to better understand the present invention, the present invention is further retouched with attached drawing combined with specific embodiments below
It states.
The present invention provides a kind of automatic drawing method of artificial intelligence, and the automatic drawing method of artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it is moved towards, is generated according to the path that the hand drawing pattern route characteristic of extraction and hand drawing pattern routing algorithm model calculate
Automatic drawing path can paint;
S5: hand drawing pattern is painted route availability inspection automatically;
S6: automatic drawing path is returned to, automatic painting function is completed.
Further, the automatic drawing method of the artificial intelligence further includes algorithm model generating process, comprising:
Data training is carried out to multiple hand drawing pattern path datas and multiple hand drawing pattern style datas and generates hand drawing pattern
Algorithm model.
Further, the automatic drawing method of the artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar automatic drawing path of diameter feature;
S5: the validity in path of painting automatically to hand drawing pattern checks;
S6: it returns to hand drawing pattern and paints automatically path, complete automatic painting function.
Further, the automatic drawing method of the artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar a variety of automatic drawing paths of diameter feature;
S5: the paint automatically validity in path of a variety of hand drawing patterns is checked;
S6: returning to a variety of hand drawing patterns and paint automatically path, completes to draw automatically according to different hand drawing patterns path of painting automatically
Function is drawn, a variety of drawing is generated, user is allowed to select in a variety of drawing of generation.
Seen from the above description, the automatic drawing method of artificial intelligence in the present invention has used the circulation mind of artificial intelligence
Through network technology, in the way of deep learning, based on the hand drawing pattern of more than one hundred million orders of magnitude, carry out path profile, trend, style,
The feature extractions such as layout cooperate the existing ownership type label of pattern, carry out model training;By to a variety of hand drawing pattern data
Data training is carried out, generates hand drawing pattern algorithm model AutoDrawModel, and be stored in learning database.In painting process,
User only needs to draw seldom a part of pattern, and hand drawing pattern algorithm model AutoDrawModel can be drawn according to user
Pattern, moved towards according to the path that is calculated in existing lines style and model, continue to complete the complete drafting of hand drawing pattern.?
In automatic drawing process, user can modify and adjust, and algorithm can be in real time according to the newest adjustment of user as a result, carry out certainly
The adjustment of dynamic drawing path trend.
It further include the hand drawing pattern routing database for being stored with hand drawing pattern path data in the learning database
HandDrawingPathData and the hand drawing pattern style data library for being stored with hand drawing pattern style data
HandDrawingPathFeature。
Further, tool storage room is additionally provided in the learning database, the tool storage room includes hand drawing pattern path data
Characteristic-acquisition method getHandDrawingPathFeature (), the method that automatic drawing manuscript path is generated according to model
GenerateAutoDrawSketch () checks the method checkAutoDrawSketch () of manuscript route availability, adjusts
The method adjustAutoDrawSketch () of whole manuscript path style and features and the method for updating user's drawing style record
updateUserHandDrawingStyleInfo()。
In one embodiment of the invention, first obtain hand drawing pattern data and to hand drawing pattern path data at
Reason;Extract hand drawing pattern route characteristic;Understand and uses the route characteristic extracted;According to the hand drawing pattern route characteristic of extraction with
And the path trend that hand drawing pattern routing algorithm model calculates, it generates automatic drawing path and can paint;Hand drawing pattern is automatic
Drawing route availability inspection;Automatic drawing path is returned to, automatic painting function is completed.In embodiment in the present invention, only need
Very at least part of pattern is drawn, by the extraction in drawing path and drawing style and features to the partial pattern, and
Based on existing drawing path and drawing style and features, Freehandhand-drawing is calculated by hand drawing pattern algorithm model AutoDrawModel
The path of pattern is moved towards, and then seems the path trend of hand drawing pattern certainly according to hand drawing pattern algorithm model AutoDrawModel
It is dynamic to complete to draw.
In yet another embodiment of the present invention, the present invention is also based on existing drawing path and drawing style is special
Sign, and store a large amount of hand drawing pattern path data hand drawing pattern routing database HandDrawingPathData and
The hand drawing pattern style data library HandDrawingPathFeature of a large amount of hand drawing pattern style data is stored, is imitated
Generate automatic drawing path similar with the hand drawing pattern route characteristic;And to the validity in path of painting automatically to hand drawing pattern
It is checked;The path if it is valid, return hand drawing pattern is painted automatically, completes automatic painting function.If paint path without
Effect then imitates again and generates automatic drawing path similar with the hand drawing pattern route characteristic.
In yet another embodiment of the present invention, existing drawing path and drawing style and features are also based on, with
And store hand drawing pattern routing database HandDrawingPathData and the storage of a large amount of hand drawing pattern path data
The hand drawing pattern style data library HandDrawingPathFeature of a large amount of hand drawing pattern style data is imitated and is generated
A variety of automatic drawing paths similar with the hand drawing pattern route characteristic;And the validity in path of painting automatically to hand drawing pattern into
Row checks;The path if it is valid, return hand drawing pattern is painted automatically, completes automatic painting function, completes drawing, last client
Optimal drawing is selected, Fig. 4 is specifically shown in.If path of painting is invalid, imitates and generate and hand drawing pattern path spy again
Similar a variety of automatic drawing paths are levied,
It should be noted that herein, relational terms such as first and second and the like be used merely to an entity or
Person's operation is distinguished with another entity or operation, is appointed without necessarily requiring or implying existing between these entities or operation
What this actual relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
Finally, it should be noted that obviously, the above embodiment is merely an example for clearly illustrating the present invention, and simultaneously
The non-restriction to embodiment.For those of ordinary skill in the art, it can also do on the basis of the above description
Other various forms of variations or variation out.There is no necessity and possibility to exhaust all the enbodiments.And thus drawn
The obvious changes or variations that Shen goes out are still in the protection scope of this invention.
Claims (4)
1. a kind of automatic drawing method of artificial intelligence, which is characterized in that the automatic drawing method of artificial intelligence includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it is moved towards, is generated according to the path that the hand drawing pattern route characteristic of extraction and hand drawing pattern routing algorithm model calculate
Automatic drawing path can paint;
S5: hand drawing pattern is painted route availability inspection automatically;
S6: automatic drawing path is returned to, automatic painting function is completed.
2. the automatic drawing method of artificial intelligence according to claim 1, it is characterised in that: the artificial intelligence is painted automatically
Method further includes algorithm model generating process, comprising:
Data training is carried out to multiple hand drawing pattern path datas and multiple hand drawing pattern style datas and generates hand drawing pattern
Algorithm model.
3. the automatic drawing method of artificial intelligence according to claim 1, it is characterised in that: the artificial intelligence is painted automatically
Method includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar automatic drawing path of diameter feature;
S5: the validity in path of painting automatically to hand drawing pattern checks;
S6: it returns to hand drawing pattern and paints automatically path, complete automatic painting function.
4. the automatic drawing method of artificial intelligence according to claim 1 or 2, it is characterised in that: the artificial intelligence is automatic
Drawing method includes:
S1: hand drawing pattern data are obtained and hand drawing pattern path data is handled;
S2: hand drawing pattern route characteristic is extracted;
S3: understanding and uses the route characteristic extracted;
S4: it according to the hand drawing pattern route characteristic and hand drawing pattern routing algorithm of extraction, imitates and generates and the hand drawing pattern road
The similar a variety of automatic drawing paths of diameter feature;
S5: the paint automatically validity in path of a variety of hand drawing patterns is checked;
S6: returning to a variety of hand drawing patterns and paint automatically path, completes to draw automatically according to different hand drawing patterns path of painting automatically
Function is drawn, a variety of drawing is generated, user is allowed to select in a variety of drawing of generation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810753008.3A CN109035357B (en) | 2018-07-10 | 2018-07-10 | Artificial intelligence automatic drawing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810753008.3A CN109035357B (en) | 2018-07-10 | 2018-07-10 | Artificial intelligence automatic drawing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109035357A true CN109035357A (en) | 2018-12-18 |
CN109035357B CN109035357B (en) | 2023-01-03 |
Family
ID=64642157
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810753008.3A Active CN109035357B (en) | 2018-07-10 | 2018-07-10 | Artificial intelligence automatic drawing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109035357B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110322529A (en) * | 2019-07-12 | 2019-10-11 | 电子科技大学 | A method of it is painted based on deep learning aided art |
CN111047671A (en) * | 2019-12-24 | 2020-04-21 | 成都来画科技有限公司 | Optimization method of drawing path of hand-drawn picture and storage medium |
CN112148944A (en) * | 2020-09-22 | 2020-12-29 | 西京学院 | Manufacturing method, manufacturing system, terminal and storage medium of manual fiber picture |
CN116630481A (en) * | 2023-07-25 | 2023-08-22 | 天津象小素科技有限公司 | Drawing path optimization method and system based on AI drawing |
CN117824663A (en) * | 2024-03-05 | 2024-04-05 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2483943A1 (en) * | 1995-12-26 | 1997-07-10 | Imax Corporation | Computer-assisted animation construction system and method and user interface |
CN107180443A (en) * | 2017-04-28 | 2017-09-19 | 深圳市前海手绘科技文化有限公司 | A kind of Freehandhand-drawing animation producing method and its device |
US20180150947A1 (en) * | 2016-11-28 | 2018-05-31 | Adobe Systems Incorporated | Facilitating sketch to painting transformations |
-
2018
- 2018-07-10 CN CN201810753008.3A patent/CN109035357B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2483943A1 (en) * | 1995-12-26 | 1997-07-10 | Imax Corporation | Computer-assisted animation construction system and method and user interface |
US20180150947A1 (en) * | 2016-11-28 | 2018-05-31 | Adobe Systems Incorporated | Facilitating sketch to painting transformations |
CN107180443A (en) * | 2017-04-28 | 2017-09-19 | 深圳市前海手绘科技文化有限公司 | A kind of Freehandhand-drawing animation producing method and its device |
Non-Patent Citations (1)
Title |
---|
YIFAN LIU等: ""Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks"", 《NEUROCOMPUTING》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110322529A (en) * | 2019-07-12 | 2019-10-11 | 电子科技大学 | A method of it is painted based on deep learning aided art |
CN111047671A (en) * | 2019-12-24 | 2020-04-21 | 成都来画科技有限公司 | Optimization method of drawing path of hand-drawn picture and storage medium |
CN111047671B (en) * | 2019-12-24 | 2023-05-16 | 成都来画科技有限公司 | Method for optimizing drawing path of hand-drawn picture and storage medium |
CN112148944A (en) * | 2020-09-22 | 2020-12-29 | 西京学院 | Manufacturing method, manufacturing system, terminal and storage medium of manual fiber picture |
CN116630481A (en) * | 2023-07-25 | 2023-08-22 | 天津象小素科技有限公司 | Drawing path optimization method and system based on AI drawing |
CN116630481B (en) * | 2023-07-25 | 2023-10-13 | 天津象小素科技有限公司 | Drawing path optimization method and system based on AI drawing |
CN117824663A (en) * | 2024-03-05 | 2024-04-05 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
CN117824663B (en) * | 2024-03-05 | 2024-05-10 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
Also Published As
Publication number | Publication date |
---|---|
CN109035357B (en) | 2023-01-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109035357A (en) | A kind of automatic drawing method of artificial intelligence | |
Knight et al. | Making grammars: From computing with shapes to computing with things | |
Bell et al. | Relational encounters and vital materiality in the practice of craft work | |
Durupinar et al. | Perform: Perceptual approach for adding ocean personality to human motion using laban movement analysis | |
Kim et al. | Agile 3D sketching with air scaffolding | |
Chen et al. | Magic decorator: automatic material suggestion for indoor digital scenes | |
US10984317B2 (en) | Dataset for learning a function taking images as inputs | |
CN106648057A (en) | Information showing method and system based on virtual reality technology | |
US20120038628A1 (en) | Real-time automatic concatenation of 3d animation sequences | |
Hahn et al. | Sketch abstractions for character posing | |
CN110598017B (en) | Self-learning-based commodity detail page generation method | |
CN112784531B (en) | Chinese character form and character library generation method based on deep learning and component splicing | |
Baseski et al. | Dissimilarity between two skeletal trees in a context | |
Tang et al. | Animated construction of Chinese brush paintings | |
Horsley et al. | Building an automatic sprite generator with deep convolutional generative adversarial networks | |
Zhang et al. | Chinese calligraphy specific style rendering system | |
Karimi et al. | A computational model for visual conceptual blends | |
Guzdial et al. | Visual procedural content generation with an artificial abstract artist | |
Liu et al. | Dynamic sketching: Simulating the process of observational drawing | |
Li et al. | Anchor‐based crowd formation transformation | |
Trombin | Working with fractals: a resource for practitioners of biophilic design | |
Delame et al. | Gesture-based design of 2D contours: an alternative to sketching? | |
Saikawa et al. | Logotype design support system based on sketches | |
Yu et al. | Style-consistency calligraphy synthesis system in digital library | |
Arora | Creative Visual Expression in Immersive 3D Environments |
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 |