CN110188600B - Drawing evaluation method, system and storage medium - Google Patents
Drawing evaluation method, system and storage medium Download PDFInfo
- Publication number
- CN110188600B CN110188600B CN201910299650.3A CN201910299650A CN110188600B CN 110188600 B CN110188600 B CN 110188600B CN 201910299650 A CN201910299650 A CN 201910299650A CN 110188600 B CN110188600 B CN 110188600B
- Authority
- CN
- China
- Prior art keywords
- painting
- images
- image
- stars
- article
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a painting evaluation method, which comprises the following steps: firstly, a painting scene and a painting template are acquired, a user is prompted to paint, a painting image of the user and a standard image are compared, and scoring is carried out on the painting image of the user according to painting evaluation standards; according to the invention, through learning and analyzing the contents and composition of the objects contained in various scene drawing images of the contents such as the cartoon, the picture book and the like, a set of drawing learning guiding method and evaluating method are established, the creativity and composition integrity of the painting can be objectively evaluated, the pleasure of drawing is increased, and more positive learning of drawing is encouraged.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to a painting evaluation method, a painting evaluation system, and a storage medium.
Background
The children's painting is favorable to strengthening children's creativity, imagination and practical ability, and the main aspects of children's painting is that the sight of painting content is associatively and creative, the richness of content, composition etc. to children's painting's result carry out teaching instruction and evaluation, generally mainly encouraged. With the deep development of artificial intelligence, the method has deeper application in painting teaching, however, how to give objective evaluation after children paint and to encourage them appropriately so as to increase the interest and enthusiasm of their painting learning becomes a problem to be solved.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the purposes of the invention is to provide a painting evaluation method which can guide and evaluate painting learning and objectively evaluate creativity and composition integrity of painting works, thereby increasing pleasure of painting learning.
Another object of the present invention is to provide a painting evaluation system capable of guiding and evaluating painting learning, objectively evaluating creativity and composition integrity of the painting, and increasing pleasure of painting learning.
It is still another object of the present invention to provide a computer-readable medium in which a program is executed to guide and evaluate drawing learning, objectively evaluate creativity and composition completeness of a drawing work, and increase pleasure of drawing learning.
One of the purposes of the invention is realized by adopting the following technical scheme: :
the painting evaluation method specifically comprises the following steps:
s101, selecting a corresponding standard template in a corresponding scene according to a received template selection command, displaying partial line manuscript graphic content of the standard template, and prompting a user to creatively imagine and draw the current line manuscript;
s102, obtaining a painting image finished by a user, processing the painting image to obtain article combination and distribution rule data of the painting image, and comparing the article combination and distribution rule data with article combination and distribution rule data of a standard template;
and S103, scoring the drawing image of the user according to drawing evaluation criteria.
Further, S1 is preceded by constructing a standard library:
s201, formulating a plurality of scenes, wherein each scene collects a plurality of picture images conforming to the scene, and/or extracts key frame images conforming to the scene from a plurality of animation videos;
s202, processing the images, carrying out gray scale processing on the picture images and/or the key frame images in each scene, removing the color filling blocks of the whole piece in the images, and only extracting the outline line images;
s203, receiving frame selection and labeling information of main objects contained in the outline image, performing learning training by using a convolutional neural network, extracting a standard template, and establishing an identification library of various objects;
s204, analyzing a composition method of the picture image and/or the key frame image collected under various scenes, counting the article combination and distribution rules of the corresponding scenes, and establishing drawing evaluation standards according to the counted article combination and distribution rules of the various scenes.
Further, S202 specifically is: after the color clustering, different processing modes are adopted according to the images of different wind drawing: for an image drawn by using color blocks, determining the same-color filling blocks of each piece according to the same continuous color points, wherein the junction between two different color blocks is an external contour; for an image drawn by using the line manuscript color adding block, only the continuous edge-hooking line manuscript area is extracted according to the color value of the line manuscript, and the rest color block part is removed.
Further, S203 is specifically: according to different space density arrangement characteristics such as the composition structure and the outline of various articles, dividing the outline line image of each article into M square areas, calculating the ratio of the number of points in each square to the total number of points of the image to obtain M square N dimension feature vectors, inputting the extracted feature vectors, taking the labeling name of the article as output, repeatedly identifying and training by using a convolutional neural network, extracting a standard template, storing the standard template in a file, and establishing an identification library of various articles.
Further, the composition method of the drawing images collected under the analysis of various scenes in S204 counts the article combination and distribution rules corresponding to various scenes, specifically: firstly analyzing the types of the articles contained in various scene images, firstly carrying out gray processing on the various scene images, extracting contour lines in the images, carrying out feature extraction on the contour lines in the images, comparing the extracted feature vectors with an established article identification library, and judging and marking various articles contained in the images; respectively counting the rule of various article combinations contained in various scenes; and counting the area size combination rule and the position distribution rule of various objects marked in each image.
Further, the processing of the painting image in S102 specifically includes: and carrying out feature extraction on the painting image, comparing the extracted feature vector with the established object identification model, judging various objects contained in the painting image completed by the user, and calculating the size proportion and position distribution proportion data of the various objects in the picture.
Further, the drawing standard in S103 is specifically: the scoring criteria are divided into innovativeness and composition rationality, and the innovativeness is divided into picture scoring by a 3-5-star scale: 5 stars are particularly creative and 1 star is a grade without creative.
Further, the innovative scoring process is: adopting two extreme scoring modes, when the quantity and combination of the object types contained in the picture of the user are closer to the statistical consistency of the quantity and combination of the object types correspondingly contained in the scene, judging that the picture is more creative, and the quantity of the obtained stars is more and is closer to 5 stars; the other extreme is that when the number of the object types and combinations contained in the picture of the user is smaller and is closer to 0 with the number of the object types and combinations contained in the corresponding statistics under the scene, the more innovative is, the more the number of the obtained stars is, and the more the number of the obtained stars is, the more the number of the obtained stars is close to 5 stars; when the relative included item types and combined quantities are in the middle of the statistics, the fewer stars are obtained, the closer to 1 star.
Further, the scoring process of composition rationality is as follows: for the size proportion and position distribution proportion data of the objects contained in the picture, adopting two extreme scoring modes, and obtaining more stars as the composition distribution rule score is higher as the composition distribution rule score is closer to statistics; the higher the score is, the more stars are obtained, which is completely different from the statistical composition distribution rule; the lower the score obtained in the middle region, the fewer stars obtained, the closer to 1 star.
The second purpose of the invention is realized by adopting the following technical scheme:
an electronic device comprising a processor and a memory, the memory storing an executable computer program, the processor being readable and operable to implement the painting evaluation method of any one of claims 1 to 8.
The third purpose of the invention is realized by adopting the following technical scheme:
a computer-readable storage medium, characterized in that the storage medium stores an executable computer program which, when run, implements the painting assessment method according to any one of claims 1 to 8.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, through learning and analyzing the contents and composition of the articles contained in various scene drawing images of the contents such as the cartoon, the picture book and the like, a set of drawing learning guiding method and evaluating method are established, the creativity and composition integrity of the painting can be objectively evaluated, the pleasure of drawing is increased, and more positive learning of the drawing is encouraged.
Drawings
FIG. 1 is a flow chart of a painting evaluation method provided by the invention;
fig. 2 is a key frame image of an animation video of a painting evaluation method according to the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and detailed description, wherein it is to be understood that, on the premise of no conflict, the embodiments described below or technical features may be arbitrarily combined to form new embodiments.
Referring to fig. 1, a painting evaluation method specifically includes the following steps:
s101, selecting a corresponding standard template in a corresponding scene according to a received template selection command, displaying partial line manuscript graphic content of the standard template, and prompting a user to creatively imagine and draw the current line manuscript;
s102, obtaining a painting image finished by a user, processing the painting image to obtain article combination and distribution rule data of the painting image, and comparing the article combination and distribution rule data with article combination and distribution rule data of a standard template;
further, the processing of the painting image specifically includes: and (3) extracting features of the painting image, comparing the extracted feature vectors with the established object identification model, judging various objects contained in the painting image completed by the user, and calculating the size proportion and position distribution proportion data of the various objects in the picture.
And S103, scoring the drawing image of the user according to drawing evaluation criteria.
Preferably, the drawing scoring criteria: the scoring criteria are divided into innovativeness and composition rationality, and the innovativeness is divided into picture scoring by a 3-5-star scale: 5 stars are particularly creative and 1 star is a grade without creative.
Further, the innovative scoring process is: adopting two extreme scoring modes, judging that the picture is more creative and the number of acquired stars is more and more approximate to 5 stars when the number and combination of the object types contained in the picture of the user are more similar to the counted number and combination consistency of the object types correspondingly contained in the scene; the other extreme is that when the number of item types and combinations contained in the user's picture is as small as 0 as possible in correspondence with the number of item types and combinations contained in the statistics of the scene, the more innovative the more stars are obtained, the closer to 5 stars are the more the number of stars is; when the relative included item types and combined numbers are in the middle of the statistics, the fewer stars are obtained, the closer to 1 star.
Further, the scoring process of composition rationality is: for the size proportion and position distribution proportion data of the objects contained in the picture, adopting two extreme scoring modes, and obtaining more stars as the composition distribution rule score is higher as the composition distribution rule score is closer to statistics; the higher the score is, the more stars are obtained, which is completely different from the statistical composition distribution rule; the lower the score obtained in the middle region, the fewer stars obtained, the closer to 1 star.
Further, S1 is preceded by constructing a standard library:
s201, formulating a plurality of scenes, wherein each scene collects a plurality of picture images conforming to the scene, and/or extracts key frame images conforming to the scene from a plurality of animation videos;
preferably, the standard drawing library can be built on a server, or can be built on hand-held PC software or APP.
S202, processing the images, carrying out gray scale processing on the picture images and/or the key frame images in each scene, removing the color filling blocks of the whole piece in the images, and only extracting the outline line images;
preferably, the gray scale processing, that is, the gray scale processing, may be performed on the color image by four methods, i.e., a component method, a maximum value method, an average method, or a weighted average method.
Preferably, after color clustering, different processing modes are adopted according to images of different drawn winds: for an image drawn by using color blocks, determining the same-color filling blocks of each piece according to the same continuous color points, wherein the junction between two different color blocks is an external contour; for an image drawn by using a line manuscript plus color block, the continuous edge-pointing line manuscript area is extracted according to the color value of the line manuscript, and the rest color block part is removed.
S203, receiving frame selection and labeling information of main objects contained in the outline image, performing learning training by using a convolutional neural network, extracting a standard template, and establishing an identification library of various objects;
preferably, the minimum circumscribed rectangle covering the outline is selected according to the external outline image frame of each article, and the name of each article is marked.
Preferably, according to different space density arrangement characteristics such as the composition structure and the outline of each article, dividing the outline image of each article into M square areas, calculating the ratio of the number of points in each square to the total number of points of the image to obtain M square N dimensional feature vectors, inputting the extracted feature vectors, taking the labeling name of the article as output, and performing repeated recognition training by using a convolutional neural network, namely obtaining the combined distribution data of each article by calculating the ratio of the area size of the minimum circumscribed rectangle of each article to the total area of the canvas and the relative position of the minimum circumscribed rectangle of each article in the whole canvas, extracting the standard template, storing the standard template into a file, and establishing a recognition library of each article.
S204, analyzing a composition method of the picture image and/or the key frame image collected under various scenes, counting the article combination and distribution rules of the corresponding scenes, and establishing drawing evaluation standards according to the counted article combination and distribution rules of the various scenes.
Preferably, firstly analyzing the types of the articles contained in various scene images, firstly carrying out gray processing on the various scene images, extracting contour lines in the images, carrying out feature extraction on the contour lines in the images, comparing the extracted feature vectors with an established article identification library, and judging and marking various articles contained in the images; respectively counting the rule of various article combinations contained in various scenes; and counting the area size combination rule and the position distribution rule of various objects marked in each image.
For example, counting the types of the identified objects in each picture in each scene and other various objects appearing in combination with each object, such as a scene of spring tour, extracting key frames from a video of a payphone cartoon named spring tour to obtain an image as shown in fig. 2, identifying and statistically analyzing the objects contained in the image, and obtaining the object combination contained in the scene of spring tour: cloud, sky, mountain, meadow, kite, sun, bird, tree, mushroom, pool, and petiolus; and meanwhile, counting the area size combination rule and the position distribution rule of each article in the picture, namely obtaining the combination distribution data of each article by calculating the size proportion of the area size of the minimum circumscribed rectangle of each article to the total area of the canvas and the relative position of the minimum circumscribed rectangle of each article in the whole canvas.
The invention also provides an electronic device comprising a processor and a memory, wherein the memory stores an executable computer program, and the processor can read the program in the memory and run to realize the painting evaluation method.
The invention also provides a computer readable storage medium, which is characterized in that the storage medium stores an executable computer program, and the computer program can realize the painting evaluation method when running.
The above embodiments are only preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but any insubstantial changes and substitutions made by those skilled in the art on the basis of the present invention are intended to be within the scope of the present invention as claimed.
Claims (9)
1. The painting evaluation method is characterized by comprising the following steps of:
s101, selecting a corresponding standard template in a corresponding scene according to a received template selection command, displaying partial line manuscript graphic content of the standard template, and prompting a user to creatively imagine and draw the current line manuscript;
s102, obtaining a painting image finished by a user, processing the painting image to obtain article combination and distribution rule data of the painting image, and comparing the article combination and distribution rule data with article combination and distribution rule data of a standard template;
s103, scoring the drawing image of the user according to drawing evaluation criteria;
s101 further includes building a standard library:
s201, formulating a plurality of scenes, wherein each scene collects a plurality of picture images conforming to the scene, and/or extracts key frame images conforming to the scene from a plurality of animation videos;
s202, processing the images, carrying out gray scale processing on the picture images and/or the key frame images in each scene, removing the color filling blocks of the whole piece in the images, and only extracting the outline line images;
s203, receiving frame selection and labeling information of main objects contained in the outline image, performing learning training by using a convolutional neural network, extracting a standard template, and establishing an identification library of various objects;
s204, analyzing a composition method of the picture images and/or the key frame images collected under various scenes, counting object combination and distribution rules of the corresponding scenes, and establishing drawing evaluation standards according to the counted object combination and distribution rules of the various scenes.
2. The painting evaluation method according to claim 1, wherein S202 is specifically: after the color clustering, different processing modes are adopted according to the images of different wind drawing: for an image drawn by using color blocks, determining the same-color filling blocks of each piece according to the same continuous color points, wherein the junction between two different color blocks is an external contour; for an image drawn by using the color blocks of the line manuscript, only the continuous edge-pointing line manuscript area is extracted according to the color value of the line manuscript, and the rest color block part is removed.
3. The painting evaluation method according to claim 2, wherein S203 is specifically: dividing the contour line image of each article into M square areas according to different space density arrangement characteristics of each article, calculating the ratio of the number of points in each square to the total number of points of the image to obtain M square N dimension feature vectors, inputting the extracted feature vectors, outputting the labeling name of the article, repeatedly identifying and training by using a convolutional neural network, extracting a standard template, storing the standard template in a file, and establishing an identification library of each article.
4. The painting evaluation method according to claim 2, wherein the composition method of the painting images collected under the analysis of the various scenes in S204 counts the article combination and distribution rules corresponding to the various scenes, specifically: firstly analyzing the types of the articles contained in various scene images, firstly carrying out gray scale treatment on the various scene images, extracting contour lines in the images, carrying out feature extraction on the contour lines in the images, comparing the extracted feature vectors with an established article identification library, and judging and marking various articles contained in the images; respectively counting the rule of various article combinations contained in various scenes; and counting the area size combination rule and the position distribution rule of various objects marked in each image.
5. The painting evaluation method according to claim 1, wherein the processing of the painting image in S102 is specifically: and (3) extracting features of the painting image, comparing the extracted feature vectors with the established object identification model, judging various objects contained in the painting image completed by the user, and calculating the size proportion and position distribution proportion data of the various objects in the picture.
6. The painting evaluation method according to claim 1, wherein the painting criteria in S104 are specifically: the scoring criteria are divided into innovativeness and composition rationality, and the innovativeness is divided into picture scoring by a 3-5-star scale: 5 stars are particularly creative and 1 star is a grade without creative.
7. The painting evaluation method according to claim 6, wherein the innovative scoring process is: adopting two extreme scoring modes, when the quantity and combination of the object types contained in the picture of the user are closer to the statistical consistency of the quantity and combination of the object types correspondingly contained in the scene, judging that the picture is more creative, and the quantity of the obtained stars is more and is closer to 5 stars; the other extreme is that when the number of item types and combinations contained in the user's picture is as small as 0 as possible in correspondence with the number of item types and combinations contained in the statistics of the scene, the more innovative the more stars are obtained, the closer to 5 stars are the more the number of stars is; when the relative included object types and the combined quantity are in the middle position of the statistical data, the fewer the acquired stars are, the closer 1 star is;
the scoring process of the composition rationality comprises the following steps: for the size proportion and position distribution proportion data of the objects contained in the picture, adopting two extreme scoring modes, wherein the closer to the statistical composition distribution rule, the higher the score is, the more stars are obtained; the higher the score is, the more stars are obtained, which is completely different from the statistical composition distribution rule; the lower the score obtained in the middle region, the fewer stars obtained, the closer to 1 star.
8. An electronic device, characterized in that: comprising a processor and a memory, the memory storing an executable computer program, the processor being operable to read the program in the memory and to implement the painting evaluation method of any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that the storage medium stores an executable computer program, which when run implements the painting evaluation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910299650.3A CN110188600B (en) | 2019-04-15 | 2019-04-15 | Drawing evaluation method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910299650.3A CN110188600B (en) | 2019-04-15 | 2019-04-15 | Drawing evaluation method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110188600A CN110188600A (en) | 2019-08-30 |
| CN110188600B true CN110188600B (en) | 2023-06-27 |
Family
ID=67714517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910299650.3A Active CN110188600B (en) | 2019-04-15 | 2019-04-15 | Drawing evaluation method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188600B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681468A (en) * | 2020-06-20 | 2020-09-18 | 廊坊市珍珪谷教育科技有限公司 | Teaching system for children education |
| CN112613730B (en) * | 2020-12-18 | 2023-10-10 | 百色学院 | College painting evaluation method and device based on Internet |
| CN116309538B (en) * | 2023-04-24 | 2023-07-28 | 湖北易康思科技有限公司 | Drawing examination evaluation method, device, computer equipment and storage medium |
| CN117456208B (en) * | 2023-11-07 | 2024-06-25 | 广东新裕信息科技有限公司 | Double-flow sketch quality evaluation method based on significance detection |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355973A (en) * | 2016-10-28 | 2017-01-25 | 厦门优莱柏网络科技有限公司 | Method and device for guiding drawing |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3929172A1 (en) * | 1989-09-02 | 1991-03-07 | Bayer Ag | DEVICE FOR DETERMINING THE SIZE DISTRIBUTION OF PIGMENT BEADS IN A LACQUER SURFACE |
| JP3913712B2 (en) * | 2003-06-09 | 2007-05-09 | 秀明 山根 | Character, symbol and figure recognition method, program thereof, computer-readable recording medium storing the program, character, symbol and figure recognition system |
| WO2015012820A1 (en) * | 2013-07-24 | 2015-01-29 | Intuit Inc. | Method and system for data identification and extraction using pictorial representations in a source document |
| CN106682577A (en) * | 2016-11-23 | 2017-05-17 | 北海高创电子信息孵化器有限公司 | Automatic painting practice method |
| CN107038664A (en) * | 2017-03-14 | 2017-08-11 | 北京美院帮网络科技有限公司 | Curricula method for pushing, device, storage medium and processor |
| CN108596105B (en) * | 2018-04-26 | 2023-02-03 | 李辰 | Augmented reality painting and calligraphy system |
| CN109448079A (en) * | 2018-10-25 | 2019-03-08 | 广东智媒云图科技股份有限公司 | A kind of drawing bootstrap technique and equipment |
-
2019
- 2019-04-15 CN CN201910299650.3A patent/CN110188600B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355973A (en) * | 2016-10-28 | 2017-01-25 | 厦门优莱柏网络科技有限公司 | Method and device for guiding drawing |
Non-Patent Citations (2)
| Title |
|---|
| Data augmentation-assisted deep learning of hand-drawn patially colored sketches for visual search;Jamil Ahmad 等;《PLOS ONE》;1-19 * |
| 绘画特征提取方法与情感分析研究综述;贾春花 等;《中国图象图形学报》;937-952 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110188600A (en) | 2019-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110188600B (en) | Drawing evaluation method, system and storage medium | |
| CN107993191B (en) | Image processing method and device | |
| CN105913485B (en) | A kind of generation method and device of three-dimensional virtual scene | |
| CN107341434A (en) | Processing method, device and the terminal device of video image | |
| CN108960409B (en) | Method and device for generating annotation data and computer-readable storage medium | |
| CN106033435B (en) | Item identification method and device, indoor map generation method and device | |
| CN106096542B (en) | Image video scene recognition method based on distance prediction information | |
| CN103810504B (en) | Image processing method and device | |
| CN103916621A (en) | Method and device for video communication | |
| CN109785400B (en) | Silhouette image manufacturing method and device, electronic equipment and storage medium | |
| CN111009041B (en) | Drawing creation method, device, terminal equipment and readable storage medium | |
| CN110097616B (en) | Combined drawing method and device, terminal equipment and readable storage medium | |
| CN111258433A (en) | Teaching interactive system based on virtual scene | |
| CN110322544A (en) | A kind of visualization of 3 d scanning modeling method, system, equipment and storage medium | |
| CN106056606A (en) | Image processing method and device | |
| CN111143615B (en) | Short video emotion classification recognition device | |
| CN110827312B (en) | Learning method based on cooperative visual attention neural network | |
| CN109446929A (en) | A kind of simple picture identifying system based on augmented reality | |
| CN106383912A (en) | Picture retrieval method and apparatus | |
| CN109045664B (en) | Diving scoring method, server and system based on deep learning | |
| CN111259950B (en) | Method for training YOLO neural network based on 3D model | |
| CN107506738A (en) | Feature extracting method, image-recognizing method, device and electronic equipment | |
| CN108806355A (en) | A kind of calligraphy and painting art interactive education system | |
| CN113838158B (en) | Image and video reconstruction method and device, terminal equipment and storage medium | |
| CN104978583B (en) | The recognition methods of figure action and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |