CN113673309B - Method, system and medium for identifying hand-drawn form - Google Patents
Method, system and medium for identifying hand-drawn form Download PDFInfo
- Publication number
- CN113673309B CN113673309B CN202110757815.4A CN202110757815A CN113673309B CN 113673309 B CN113673309 B CN 113673309B CN 202110757815 A CN202110757815 A CN 202110757815A CN 113673309 B CN113673309 B CN 113673309B
- Authority
- CN
- China
- Prior art keywords
- binary tree
- rectangle
- module
- updated
- standard rectangle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Processing Or Creating Images (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method, a system and a medium for identifying a hand-drawn form, wherein the method comprises the following steps: drawing a rectangle to obtain a graph outline; performing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle; drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a table; modeling operation is carried out through the standard rectangle and the table to obtain a binary tree; drawing a straight line or oblique line, executing a second segmentation operation on the table, and executing a traversal updating operation on the binary tree to obtain an updated binary tree; performing a moving operation or a zooming operation on the table to obtain an updated table; performing updating operation on the updating binary tree according to the updating table by a dynamic programming method to obtain a table binary tree; by means of the method, the hand-drawn graph can be accurately identified, the hand-drawn irregular rectangle is converted into the standard rectangle, the moving or scaled form is displayed completely after the form is moved or scaled, and user experience is improved.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to a system, a method, and a medium for hand-drawn form recognition.
Background
With the development of science and technology and the rise of paperless office work, intelligent equipment is widely applied to scenes such as conferences, offices, teaching and the like. Among them, the whiteboard software application in the intelligent device is especially frequent, and in many times, irregular forms need to be drawn by bare hands in the whiteboard software, and the irregular forms need to be converted into corresponding standard forms by an identification method.
In the prior art, the hand-drawn form cannot be accurately identified, when the drawn form moves or zooms, the complete form information cannot be displayed, and the user experience is very unfriendly.
Disclosure of Invention
The invention mainly solves the problem that the hand-drawn form and the drawn form cannot be accurately identified and cannot be completely displayed after being moved or zoomed.
In order to solve the problems, the invention adopts a technical scheme that: a method for identifying a hand-drawn form is provided, comprising the following steps:
drawing a rectangle: drawing a rectangle to obtain a graph outline;
building a standard rectangle: performing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle;
drawing a table: drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a table;
modeling a binary tree: modeling operation is carried out through the standard rectangle and the table to obtain a binary tree;
constructing an updated binary tree: drawing a straight line or oblique line, and executing a second dividing operation on the table to obtain an updated table; according to the update table, performing traversal update operation on the binary tree to obtain an updated binary tree;
form movement scaling: performing a moving operation or a scaling operation on the updated table to obtain a usable table;
constructing a table binary tree: and executing secondary updating operation on the updating binary tree through a dynamic programming method according to the usable table to obtain a table binary tree.
Further, the step of obtaining the graphical profile further comprises: and acquiring a sampling point sequence of the rectangle in the screen input area according to the drawing order, and obtaining the figure outline.
Further, the step of constructing a standard rectangle further includes: and acquiring coordinates of four vertexes of the figure outline, respectively fitting the four vertexes according to the polygon fitting algorithm, adjusting the coordinates, and constructing the standard rectangle.
Further, the step of performing a first partitioning operation on the standard rectangle to obtain a table further includes: acquiring the straight line intersecting the standard rectangle in the screen input area, and dividing the standard rectangle into a plurality of rectangle father unit cells through the straight line; and forming the table by a plurality of rectangular father cells and the standard rectangles.
Further, the step of modeling the binary tree further comprises: and setting four vertex coordinates of the standard rectangle as root nodes, setting four vertex coordinates of the parent unit cell of the rectangle as parent nodes, and modeling through the root nodes and the parent nodes to obtain the binary tree.
Further, the step of drawing a straight line or a diagonal line and performing a second splitting operation on the table further includes:
drawing information in the screen input area is acquired, and judgment operation is carried out on the drawing information:
if the drawing information is the straight line, dividing the father cell into a plurality of rectangular sub cells;
if the drawing information is the oblique line, the father cell is divided into a plurality of triangle sub-cells.
Further, the step of performing a traversal update operation on the binary tree to obtain an updated binary tree further includes:
if the parent cell is divided into a plurality of rectangular sub-cells, four vertex coordinates of each rectangular sub-cell are obtained, and the four vertex coordinates are set as child nodes of the parent node corresponding to the parent cell;
if the parent cell is divided into a plurality of triangle sub-cells, three vertex coordinates of each triangle sub-cell are obtained, and the three vertex coordinates are set as child nodes of the parent node corresponding to the parent cell.
Further, the step of constructing a tabular binary tree further comprises: and acquiring four vertex coordinates of the updated table through the dynamic programming method, and updating the four vertex coordinates to corresponding nodes in the binary tree to obtain the table binary tree.
A system for hand-drawn form recognition, comprising: the system comprises a rectangle drawing module, a standard rectangle building module, a drawing table module, a modeling binary tree module, a updating binary tree building module, a table moving scaling module and a table binary tree building module;
the rectangle drawing module is used for drawing a rectangle to obtain a graph outline;
the standard rectangle constructing module is used for executing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle;
the drawing form module is used for drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a form;
the modeling binary tree module is used for executing modeling operation through the standard rectangle and the table to obtain a binary tree;
the construction and update binary tree module is used for drawing straight lines or oblique lines, and executing second segmentation operation on the table to obtain an updated table; according to the update table, performing traversal update operation on the binary tree to obtain an updated binary tree;
the table movement scaling module is used for executing movement operation or scaling operation on the updated table to obtain a usable table;
the form binary tree constructing module is used for executing secondary updating operation on the updating binary tree through a dynamic programming method according to the usable form to obtain a form binary tree.
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the method of hand-drawn form recognition.
The beneficial effects of the invention are as follows:
1. the method for identifying the hand-painted form can accurately identify the shape of the hand-painted figure through a polygon fitting algorithm, can quickly convert the hand-painted irregular figure into a regular rectangle, and improves user experience;
2. the system for identifying the hand-drawn form can record the vertex coordinate information of the form through the binary tree, update the vertex coordinate information in the binary tree in real time according to the movement and the scaling of the form, and completely display the moved or scaled form;
3. the medium for identifying the hand-drawn form can accurately identify the straight line or the oblique line of the hand-drawn form, improve the speed and the precision of the hand-drawn form and improve the experience of a user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying a hand-drawn form according to embodiment 1 of the present invention;
FIG. 2 is an application example of the method for identifying a hand-drawn form according to embodiment 1 of the present invention;
FIG. 3 is a block diagram of a binary tree of the method of hand-drawn form identification of embodiment 1 of the present invention;
FIG. 4 is a block diagram of an updated binary tree of the method of hand-drawn form identification of embodiment 1 of the present invention;
fig. 5 is a schematic diagram of a system for identifying a hand-drawn form according to embodiment 2 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that terms such as "graphic outline", "transformation", "segmentation", "modeling", "traversal", "update", "scaling", "binary tree", "sampling point", "sequence", "coordinates", "cell", "root node", "parent node", "child node", and the like should be construed broadly unless explicitly specified and defined otherwise. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature.
Example 1
It should be noted first that the method of the present invention is mainly applied to drawing software of smart devices such as smart televisions, tablets, smart phones, etc., and in order to more clearly explain the present invention, the application scenario is set as the whiteboard drawing software of the smart phone in the present embodiment, but this does not represent that the scope of protection of the present invention is limited to the whiteboard drawing software applied to the smart phone.
An embodiment of the present invention provides a method for identifying a hand-drawn form, please refer to fig. 1 to 4, comprising the following steps:
s100, drawing a rectangle:
drawing a rectangular outline in whiteboard drawing software of the smart phone, wherein the rectangular outline needs to be drawn at one time, and a screen sampling point sequence arranged according to a drawing sequence is obtained to obtain a drawn rectangular graphic outline.
S200, constructing a standard rectangle:
from the graphic profile, coordinates of four vertices of the graphic profile are obtained, and here, in order of the upper left vertex, the lower right vertex, and the upper right vertex, the coordinates of the four vertices are respectively [ (1, 5), (2, 1), (6, 0.5), (7, 6) ], it should be noted that the values of the coordinates of the four vertices are set here only for more clearly explaining the method of the present invention, and the scope of the present invention is not limited thereto.
According to a polygon fitting algorithm, four vertex coordinates are fitted, namely, the coordinates of the remaining three vertices are respectively modified according to the upper left vertex as a reference, the coordinates of the upper left vertex are (1, 5), the x-axis coordinates of the lower left vertex are fitted to be 1, the y-axis coordinates of the upper right vertex are fitted to be 5, the coordinates of the lower left vertex are changed to be (1, 1), the coordinates of the upper right vertex are changed to be (7, 5), and then the coordinates of the lower right vertex are fitted to be (7, 1) according to the coordinates of the three vertices of the upper left vertex, the lower left vertex and the upper right vertex, and then the four vertex coordinates of the figure outline are fitted to be [ (1, 5), (2, 1), (6, 0.5), (7, 6) ] to be [ (1, 5), (1, 1), (7, 5) ], so that a standard rectangle is constructed.
S300, drawing a table:
drawing a straight line intersecting a standard rectangle, and performing a first division operation on the standard rectangle, wherein the standard rectangle is divided into two rectangular cells, wherein the two cells are set as parent cells for distinguishing from subsequent cells, and the two parent cells and the standard rectangle form a table.
In order to more clearly explain the present invention, the drawn straight line is set to vertically divide the standard rectangle, and then the coordinates of two vertexes where the straight line intersects with the standard rectangle are (4, 5) and (4, 1) from top to bottom, which should be noted that the description is only for explaining the implementation process of the method of the present invention, and the scope of the present invention is not limited thereby.
S400, modeling a binary tree:
setting four vertex coordinates of a standard rectangle as root nodes, setting four vertex coordinates of a father cell as father nodes, and modeling through the root nodes and the two father nodes to obtain a binary tree, as shown in fig. 3.
S500, constructing an updated binary tree:
drawing a straight line or oblique line intersecting the parent cell, and executing a second segmentation operation on the parent cell to obtain a rectangular sub-cell or a triangular sub-cell:
if the drawn straight line is drawn, the parent cell is divided into two rectangular child cells;
if a diagonal line is drawn, the parent cell is divided into two triangle child cells.
As shown in fig. 2, the left parent cell is diagonally divided into two triangular sub-cells, and three vertex coordinates of the two triangular sub-cells are [ (1, 5), (1, 1), (4, 1) ] and [ (1, 5), (4, 1), (4, 5) ];
as shown in fig. 2, the parent cell on the right side is first divided into two rectangular child cells by a transverse straight line, four vertex coordinates of the two rectangular child cells are [ (4, 5), (4, 3), (7, 5) ] and [ (4, 3), (4, 1), (7, 3) ], the rectangular child cell below the two rectangular child cells is divided into two rectangular grandchild cells by a vertical straight line, and four vertex coordinates of the two rectangular grandchild cells are [ (4, 3), (4, 1), (5.5,1), (5.5,3) ] and [ (5.5,3), (5.5,1), (7, 1), (7, 3) ], so as to obtain the updated table.
By updating the coordinates of the table, a traversal update operation is performed on the binary tree, building an updated binary tree as shown in FIG. 4.
S600, form movement scaling:
moving or zooming the updated table according to the requirements, and when the updated table is moved, dragging the upper left vertex of the standard rectangle to a proper position and releasing the position;
when the scaling operation is carried out on the updated table, the right lower vertex of the standard rectangle is selected and pulled to a proper size for release;
after moving and scaling the updated table, a usable table is obtained.
S700, constructing a table binary tree:
and acquiring coordinates of each vertex of the usable table, and executing secondary updating operation on the updating binary tree by a dynamic programming method, namely updating the coordinates of each vertex of the usable table to the coordinates of the corresponding vertex in the updating binary tree to obtain the final table binary tree.
Example 2
It should be noted first that the system of the present invention is mainly applied to drawing software of smart devices such as smart televisions, tablets, smart phones, etc., and in order to more clearly explain the present invention, the application scenario is set as the whiteboard drawing software of the smart phone in the present embodiment, but this does not represent that the scope of protection of the present invention is limited to the whiteboard drawing software applied to the smart phone.
The embodiment of the invention also provides a system for identifying the hand-drawn form, referring to fig. 5, comprising: the system comprises a rectangle drawing module, a standard rectangle building module, a drawing table module, a modeling binary tree module, a updating binary tree building module, a table moving scaling module and a table binary tree building module;
and a rectangular drawing module:
the rectangle drawing module is used for drawing a rectangle to obtain a figure outline;
specifically, the rectangular drawing module draws the outline of a rectangle in whiteboard drawing software of the smart phone, the outline of the rectangle needs to be drawn at one time, a screen sampling point sequence arranged according to the drawing order is obtained, and the drawing figure outline of the rectangle is obtained.
Building a standard rectangular module:
the standard rectangle module is constructed and used for executing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle;
specifically, the standard rectangular module is constructed to obtain coordinates of four vertices of the graphic outline according to the graphic outline, where the coordinates of the four vertices are [ (1, 5), (2, 1), (6, 0.5), (7, 6) ] in order of the upper left vertex, the lower right vertex and the upper right vertex, and it should be noted that the values of the coordinates of the four vertices are set only for more clearly explaining the system of the present invention, and the scope of the present invention is not limited thereto.
According to a polygon fitting algorithm, four vertex coordinates are fitted, namely, the coordinates of the remaining three vertices are respectively modified according to the upper left vertex as a reference, the coordinates of the upper left vertex are (1, 5), the x-axis coordinates of the lower left vertex are fitted to be 1, the y-axis coordinates of the upper right vertex are fitted to be 5, the coordinates of the lower left vertex are changed to be (1, 1), the coordinates of the upper right vertex are changed to be (7, 5), and then the coordinates of the lower right vertex are fitted to be (7, 1) according to the coordinates of the three vertices of the upper left vertex, the lower left vertex and the upper right vertex, and then the four vertex coordinates of the figure outline are fitted to be [ (1, 5), (2, 1), (6, 0.5), (7, 6) ] to be [ (1, 5), (1, 1), (7, 5) ], so that a standard rectangle is constructed.
And a drawing table module:
the drawing form module is used for drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a form;
specifically, the drawing table module draws a straight line intersecting a standard rectangle, performs a first division operation on the standard rectangle, and divides the standard rectangle into two rectangular cells, wherein in order to distinguish from a subsequent cell, the two cells are set as parent cells, and the two parent cells and the standard rectangle form a table.
Here, in order to more clearly explain the present invention, the drawn straight line is set to vertically equally divide the standard rectangle, and then the coordinates of two vertices where the straight line intersects with the standard rectangle are (4, 5) and (4, 1) from top to bottom, respectively, it should be noted that this is only for explaining the implementation process of the system of the present invention, and the scope of the present invention is not limited thereby.
Modeling a binary tree module:
the modeling binary tree module is used for executing modeling operation through the standard rectangle and the table to obtain a binary tree;
specifically, the modeling binary tree module sets four vertex coordinates of a standard rectangle as root nodes, sets four vertex coordinates of a parent cell as parent nodes, and models the parent cell through the root nodes and the two parent nodes to obtain a binary tree.
Constructing an updating binary tree module:
the updating binary tree module is used for drawing straight lines or oblique lines, and performing second segmentation operation on the table to obtain an updated table; according to the update table, performing traversal update operation on the binary tree to obtain an updated binary tree;
specifically, the construction and updating binary tree module draws a straight line or oblique line intersecting with the parent cell, and performs a second segmentation operation on the parent cell to obtain a rectangular sub-cell or a triangular sub-cell:
if the drawn straight line is drawn, the parent cell is divided into two rectangular child cells;
if a diagonal line is drawn, the parent cell is divided into two triangle child cells.
The left parent cell is diagonally divided into two triangular sub-cells, and three vertex coordinates of the two triangular sub-cells are [ (1, 5), (1, 1), (4, 1) ] and [ (1, 5), (4, 1), (4, 5) ];
the right parent cell is firstly divided into two rectangular child cells by a transverse straight line, four vertex coordinates of the two rectangular child cells are [ (4, 5), (4, 3), (7, 5) ] and [ (4, 3), (4, 1), (7, 3) ] respectively, the rectangular child cell below the two rectangular child cells is divided into two rectangular grandchild cells by a vertical straight line, and four vertex coordinates of the two rectangular grandchild cells are [ (4, 3), (4, 1), (5.5,1), (5.5,3) ] and [ (5.5,3), (5.5,1), (7, 1), (7, 3) ] respectively, so that an updated table is obtained.
And performing traversal updating operation on the binary tree through updating the coordinates of the table to construct an updated binary tree.
A table movement scaling module:
the table moving and scaling module is used for executing moving operation or scaling operation on the updated table to obtain a usable table;
specifically, the table movement scaling module moves or scales the updated table according to the requirement, and when the updated table is moved, the upper left vertex of the standard rectangle is selected and then dragged to a proper position for release;
when the scaling operation is carried out on the updated table, the right lower vertex of the standard rectangle is selected and pulled to a proper size for release;
after moving and scaling the updated table, a usable table is obtained.
A table binary tree module is constructed:
the form binary tree constructing module is used for executing secondary updating operation on the updating binary tree through a dynamic programming method according to the usable form to obtain a form binary tree;
specifically, the module for constructing the table binary tree acquires the coordinates of each vertex of the usable table, and performs a secondary updating operation on the updated binary tree through a dynamic programming method, namely updating the coordinates of each vertex of the usable table to the coordinates of the corresponding vertex in the updated binary tree, so as to obtain a final table binary tree.
Example 3
This embodiment 3 has a computer-readable storage medium for storing computer software instructions for implementing the method for hand-drawing form recognition described in embodiment 1, which contains a program set by the method for hand-drawing form recognition; specifically, the executable program may be built in the system for identifying a hand-drawn form described in embodiment 2, so that the system for identifying a hand-drawn form may implement the method for identifying a hand-drawn form described in embodiment 1 by executing the built-in executable program.
The foregoing embodiment of the present invention has been disclosed with reference to the number of embodiments for the purpose of description only, and does not represent the advantages or disadvantages of the embodiments.
It will be appreciated by those of ordinary skill in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or a program implemented by a program to instruct related hardware may be stored in a computer readable storage medium, where the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (3)
1. A method of hand-drawn form recognition, comprising the steps of:
drawing a rectangle: drawing a rectangle to obtain a graph outline;
building a standard rectangle: performing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle;
drawing a table: drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a table;
modeling a binary tree: modeling operation is carried out through the standard rectangle and the table to obtain a binary tree;
constructing an updated binary tree: drawing a straight line or oblique line, and executing a second dividing operation on the table to obtain an updated table; according to the update table, performing traversal update operation on the binary tree to obtain an updated binary tree;
form movement scaling: performing a moving operation or a scaling operation on the updated table to obtain a usable table;
constructing a table binary tree: according to the usable form, performing a secondary updating operation on the updating binary tree through a dynamic programming method to obtain a form binary tree;
the step of obtaining a graphical profile further comprises: acquiring a sampling point sequence of the rectangle in the screen input area according to the drawing sequence, and obtaining the figure outline;
the step of constructing a standard rectangle further comprises: acquiring coordinates of four vertexes of the figure outline, fitting the four vertexes according to the polygon fitting algorithm, adjusting the coordinates, and constructing the standard rectangle;
the step of performing a first partitioning operation on the standard rectangle to obtain a table further includes: acquiring the straight line intersecting the standard rectangle in the screen input area, and dividing the standard rectangle into a plurality of rectangle father unit cells through the straight line; a plurality of rectangular father cells and the standard rectangle form the table;
the step of modeling a binary tree further comprises: setting four vertex coordinates of the standard rectangle as root nodes, setting four vertex coordinates of the parent unit cell of the rectangle as parent nodes, and modeling through the root nodes and the parent nodes to obtain the binary tree;
the step of drawing a straight line or a diagonal line and performing a second splitting operation on the table further includes: drawing information in the screen input area is acquired, and judgment operation is carried out on the drawing information: if the drawing information is the straight line, dividing the father cell into a plurality of rectangular sub cells; if the drawing information is the oblique line, dividing the father cell into a plurality of triangle sub-cells;
the step of performing a traversal updating operation on the binary tree to obtain an updated binary tree further comprises: if the parent cell is divided into a plurality of rectangular sub-cells, four vertex coordinates of each rectangular sub-cell are obtained, and the four vertex coordinates are set as child nodes of the parent node corresponding to the parent cell; if the parent cell is divided into a plurality of triangular sub-cells, three vertex coordinates of each triangular sub-cell are obtained, and the three vertex coordinates are set as the child nodes of the parent node corresponding to the parent cell;
the step of constructing a tabular binary tree further comprises: and acquiring four vertex coordinates of the updated table through the dynamic programming method, and updating the four vertex coordinates to corresponding nodes in the binary tree to obtain the table binary tree.
2. A system for hand-drawn form recognition employing the method of hand-drawn form recognition of claim 1, the system comprising: the system comprises a rectangle drawing module, a standard rectangle building module, a drawing table module, a modeling binary tree module, a updating binary tree building module, a table moving scaling module and a table binary tree building module;
the rectangle drawing module is used for drawing a rectangle to obtain a graph outline;
the standard rectangle constructing module is used for executing conversion operation on the graph outline through a polygon fitting algorithm to obtain a standard rectangle;
the drawing form module is used for drawing a straight line, and executing a first segmentation operation on the standard rectangle to obtain a form;
the modeling binary tree module is used for executing modeling operation through the standard rectangle and the table to obtain a binary tree;
the construction and update binary tree module is used for drawing straight lines or oblique lines, and executing second segmentation operation on the table to obtain an updated table; according to the update table, performing traversal update operation on the binary tree to obtain an updated binary tree;
the table movement scaling module is used for executing movement operation or scaling operation on the updated table to obtain a usable table;
the form binary tree constructing module is used for executing secondary updating operation on the updating binary tree through a dynamic programming method according to the usable form to obtain a form binary tree.
3. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method steps of a hand-drawn form recognition as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757815.4A CN113673309B (en) | 2021-07-05 | 2021-07-05 | Method, system and medium for identifying hand-drawn form |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757815.4A CN113673309B (en) | 2021-07-05 | 2021-07-05 | Method, system and medium for identifying hand-drawn form |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113673309A CN113673309A (en) | 2021-11-19 |
| CN113673309B true CN113673309B (en) | 2023-10-10 |
Family
ID=78538559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110757815.4A Active CN113673309B (en) | 2021-07-05 | 2021-07-05 | Method, system and medium for identifying hand-drawn form |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673309B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101981583A (en) * | 2008-03-28 | 2011-02-23 | 智能技术Ulc公司 | Method and tool for recognizing a hand-drawn table |
| CN102236789A (en) * | 2010-04-26 | 2011-11-09 | 富士通株式会社 | Method and device for correcting table image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7054871B2 (en) * | 2000-12-11 | 2006-05-30 | Lucent Technologies Inc. | Method for identifying and using table structures |
-
2021
- 2021-07-05 CN CN202110757815.4A patent/CN113673309B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101981583A (en) * | 2008-03-28 | 2011-02-23 | 智能技术Ulc公司 | Method and tool for recognizing a hand-drawn table |
| CN102236789A (en) * | 2010-04-26 | 2011-11-09 | 富士通株式会社 | Method and device for correcting table image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113673309A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112163251B (en) | Building model unitization method and device, storage medium and electronic equipment | |
| CN111275820B (en) | Method, device, terminal and storage medium for drawing three-dimensional wall based on two-dimensional plane | |
| CN114648615B (en) | Method, device and equipment for controlling interactive reproduction of target object and storage medium | |
| JP7264989B2 (en) | Visualization method, device and recording medium for multi-source earth observation image processing | |
| CN114266093A (en) | Standardized BIM model lightweight realization method | |
| CN112711863A (en) | Method, system, equipment and medium for rapidly extracting coordinates based on BIM technology | |
| JPH05346957A (en) | Device and method for presenting shape feature quantity | |
| CN108038916A (en) | A kind of display methods of augmented reality | |
| CN113673309B (en) | Method, system and medium for identifying hand-drawn form | |
| CN111259474A (en) | Large-scale BIM model data processing and loading method and equipment | |
| CN115552364A (en) | Multi-terminal collaborative display updating method and device | |
| JP2837584B2 (en) | How to create terrain data | |
| CN114781014B (en) | Object processing method, device, equipment and computer readable storage medium | |
| CN116310040A (en) | Drawing processing method and device of three-dimensional model, electronic equipment and storage medium | |
| JPH076076A (en) | Hypermedia system | |
| CN116647657A (en) | Responsive Video Canvas Generation | |
| CN116152451A (en) | Multidimensional parameterized city information model construction method, system and computer equipment | |
| CN109887058A (en) | Cross-platform drafting system | |
| JP2003122567A (en) | Device and method for multidimensional programming | |
| CN113126866A (en) | Object determination method and device, electronic equipment and storage medium | |
| CN111753346A (en) | Method for generating cross-sectional view of linear member, Revit platform, and storage medium | |
| JPH0887608A (en) | Method and device for deforming three-dimensional shape model | |
| CN112596659A (en) | Drawing method and device based on intelligent voice and image processing | |
| CN118115993A (en) | Remote sensing image semantic segmentation sample manufacturing method and device based on vector data | |
| JPH01126774A (en) | Graphic input 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 |