CN113505660A - Paper engineering drawing operation reading device and method thereof - Google Patents
Paper engineering drawing operation reading device and method thereof Download PDFInfo
- Publication number
- CN113505660A CN113505660A CN202110690032.9A CN202110690032A CN113505660A CN 113505660 A CN113505660 A CN 113505660A CN 202110690032 A CN202110690032 A CN 202110690032A CN 113505660 A CN113505660 A CN 113505660A
- Authority
- CN
- China
- Prior art keywords
- picture
- engineering drawing
- paper engineering
- job
- rendering
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 52
- 238000009877 rendering Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 35
- 239000003086 colorant Substances 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004040 coloring Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
Abstract
The invention relates to a paper engineering drawing operation reading device and a method thereof, wherein the device comprises a shooting module and a picture processing module which are sequentially connected, and the method comprises the following steps: s1, acquiring an operation photo corresponding to the paper engineering drawing operation through the shooting module, and transmitting the operation photo to the picture processing module; and S2, the picture processing module sequentially carries out preprocessing, positioning, binaryzation, small-area model matching and label rendering operations on the job photo to obtain a job picture with a rendering color, namely, the reviewing of the paper engineering drawing job is completed. Compared with the prior art, the invention realizes the automatic and accurate reading and amending of the paper engineering drawing, saves the time for teachers to amend the operation of the paper engineering drawing, improves the automation level of engineering drawing teaching, and can generate good real-time feedback to learners.
Description
Technical Field
The invention relates to the technical field of automatic marking of paper engineering drawing operation, in particular to a paper engineering drawing operation marking device and a paper engineering drawing operation marking method.
Background
In traditional engineering drawing teaching, students need to learn about problems existing in themselves after practicing and drawing paper engineering drawings, and meanwhile, teachers also need to read and approve the paper engineering drawing homework of the students.
However, as the work load of students is increased, the work load of teacher's reviewing work is increased correspondingly, which causes the efficiency and quality of the work reviewing to be affected adversely, and on the other hand, it is difficult for students to accurately know the accuracy of the work themselves, so it is necessary to develop an intelligent device capable of assisting in the reviewing of the work, and chinese patent CN201510776179 proposes an intelligent reviewing method and system for engineering drawing work based on three-dimensional reconstruction, which is based on the AutoCAD software platform essentially, reconstructs a two-dimensional view, extracts key data from the three-dimensional view, and finally compares information according to a standard answer database, on the one hand, the operation is complicated, and on the other hand, the method also depends on the accuracy of the reconstruction program of the three-dimensional view, once the reconstruction of the three-dimensional view is not accurate, which inevitably causes the accuracy of the subsequent information comparison to be reduced, and in addition, the method is only suitable for the work of electronic version engineering drawing, the method can not adapt to the paper engineering drawing operation, and the user can not intuitively know the problems of the places in the operation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a paper engineering drawing operation reviewing device and a method thereof so as to efficiently and accurately review the paper engineering drawing operation.
The purpose of the invention can be realized by the following technical scheme: the device for reading and amending the paper engineering drawing operation comprises a shooting module and a picture processing module, wherein the shooting module is used for shooting the paper engineering drawing operation to be read and amended to obtain a corresponding operation picture, an answer template picture with a preset value is stored in the picture processing module, and the picture processing module is used for processing and analyzing the operation picture to complete reading and amending the paper engineering drawing operation.
Further, the picture processing module comprises a preprocessing unit, a binarization unit, a positioning matching unit and a label rendering unit, wherein the preprocessing unit is used for performing background removal, area calibration and inclination correction operation on the operation photo;
the binarization unit is used for carrying out binarization processing on the preprocessed operation picture;
the positioning matching unit is used for performing template size matching operation on the binarized operation picture and the answer template picture to obtain an optimal matching data matrix;
the label rendering unit is used for labeling the optimal matching data matrix and rendering different labels into corresponding colors so as to obtain the operation pictures of the rendered colors.
A paper engineering drawing operation reading method comprises the following steps:
s1, acquiring an operation photo corresponding to the paper engineering drawing operation through the shooting module, and transmitting the operation photo to the picture processing module;
and S2, the picture processing module sequentially carries out preprocessing, positioning, binaryzation, small-area model matching and label rendering operations on the job photo to obtain a job picture with a rendering color, namely, the reviewing of the paper engineering drawing job is completed.
Further, the step S2 specifically includes the following steps:
s21, removing the background of the non-working surface in the working photo;
s22, carrying out area calibration on the operation photo without the background;
s23, performing inclination correction on the region calibrated in the operation picture based on the answer template picture to obtain an identification region;
s24, performing clipping operation and binarization processing on the identification area of the job photo;
s25, performing small-region model matching on the job picture after binarization processing and the answer template picture to obtain an optimal matching data matrix;
and S26, labeling the optimal matching data matrix, rendering different labels into preset corresponding colors, and obtaining operation pictures of the rendered colors, namely completing reading and amending the paper engineering drawing operation.
Further, the specific process of step S21 is as follows: and counting the data values of the RGB channels of the operation photos, calculating the mean value K of the data values, and replacing the pixel point value which is greater than K in the RGB channels with 255, namely replacing the pixel point with a white background so as to remove the background of the non-operation surface.
Further, in step S22, specifically, four base points are selected from the background-removed photo, and the trapezoid area covered by the four base points is used as the calibration area.
Further, in step S23, the perspective transformation is specifically performed on the selected four base points and the answer template picture, so that the trapezoid area covered by the four base points is converted into a regular quadrilateral area, thereby implementing the tilt correction of the calibration area to obtain the identification area.
Further, the step S24 specifically includes the following steps:
s241, cutting the regular quadrilateral identification area to obtain an identification area picture;
s242, binarization processing is carried out on the identification area picture: firstly, taking a B channel of an RGB color channel of a picture, then calculating a data mean value of the B channel, and recording a data value of the B channel smaller than the mean value as a logical yes and a data value of the B channel larger than the mean value as a logical not.
Further, the step S25 specifically includes the following steps:
s251, selecting four base points on the job picture and the answer template picture after binarization processing;
and S252, based on the four base points selected in the step S251, using the black pixel point a1 in the job picture after binarization processing to correspond to the pixel point b1 in the answer template picture, then using a1 to search the black pixel point in a rectangular region with a preset size and taking b1 as the center, thus obtaining a plurality of matched data matrixes, and finally screening the plurality of data matrixes to obtain an optimal matching matrix.
Further, the step S26 is specifically to perform labeling and color rendering according to the matrix point values in the optimal matching matrix: if the matrix point value is 0, the background color is white; if the matrix point value is 1, rendering the correct line into black; if the matrix point value is 2, rendering the line with less pictures into red; and if the matrix point value is 3, rendering the multi-drawing line to be yellow.
Compared with the prior art, the invention has the following advantages:
according to the method, the shooting module and the picture processing module are arranged, the answer template picture with the preset value is stored in the picture processing module, the shooting module is used for shooting the paper engineering drawing operation to be read in batches to obtain the corresponding operation picture, and the picture processing module is used for processing and analyzing the operation picture to complete reading in batches of the paper engineering drawing operation, so that the paper engineering drawing operation can be automatically and accurately read in batches, and the reading efficiency is improved.
The method and the device have the advantages that the operation photos with rendering colors are obtained by carrying out preprocessing, binaryzation, positioning matching and label rendering on the shot paper engineering drawing operation photos, so that the accuracy of reading and amending is guaranteed, and meanwhile, a user can visually see the wrong positions in the operation in real time.
Drawings
FIG. 1 is a schematic diagram of the apparatus of the present invention;
FIG. 2 is a schematic flow diagram of the process of the present invention;
FIG. 3 is a schematic diagram of an embodiment of an application process;
FIG. 4 is a schematic view of a tag rendering process;
the notation in the figure is: 1. the device comprises a shooting module 2, a picture processing module 201, a preprocessing unit 202, a binarization unit 203, a positioning matching unit 204 and a label rendering unit.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
The utility model provides a paper engineering drawing operation reading device, is including the shooting module 1 and the picture processing module 2 that connect gradually, and the shooting module 1 is used for shooing the paper engineering drawing operation of waiting to read in order to obtain corresponding operation photo, and the answer template picture that has the default in the picture processing module 2, and picture processing module 2 is used for handling the analysis to the operation photo, in order to accomplish the reading in batches to the paper engineering drawing operation.
The image processing module 2 comprises a preprocessing unit 201, a binarization unit 202, a positioning matching unit 203 and a label rendering unit 204, wherein the preprocessing unit 201 is used for performing background removal, area calibration and inclination correction operation on the operation photo;
the binarization unit 202 is configured to perform binarization processing on the preprocessed job picture;
the positioning matching unit 203 is used for performing template size matching operation on the binarized job picture and the answer template picture to obtain an optimal matching data matrix;
the label rendering unit 204 is configured to perform labeling on the optimal matching data matrix, and render different labels into corresponding colors to obtain a job picture of the rendered color.
The device is applied to practice to realize a paper engineering drawing operation reading method, as shown in fig. 2, and comprises the following steps:
s1, acquiring an operation photo corresponding to the paper engineering drawing operation through the shooting module, and transmitting the operation photo to the picture processing module;
s2, the picture processing module sequentially carries out preprocessing, positioning, binaryzation, small-area model matching and label rendering operations on the operation picture to obtain the operation picture of the rendering color, namely, completing the reading and amending of the operation of the paper engineering drawing, and is specific:
first, the background of the non-working surface in the working photo is removed: counting data values of RGB channels of the operation photos, calculating a mean value K of the data values, and replacing pixel point values larger than K in the RGB channels with 255, namely replacing the pixel points with a white background so as to remove the background of the non-operation surface;
and then, carrying out area calibration on the operation photo with the background removed: selecting four base points from the background-removed working photo, and taking a trapezoid area covered by the four base points as a calibrated area;
and then based on the answer template picture, performing tilt correction on the region calibrated in the operation picture to obtain an identification region: carrying out perspective transformation processing on the selected four base points and an answer template picture to convert an irregular quadrilateral area covered by the four base points into a regular quadrilateral area, thereby realizing the inclination correction of the calibration area and obtaining an identification area;
clipping operation and binarization processing are carried out on the identification area of the operation photo: firstly, cutting an identification area of a regular quadrilateral to obtain an identification area picture;
then, carrying out binarization processing on the identification area picture: taking a B channel of an RGB color channel of the picture, calculating a data mean value of the B channel, and recording a logical yes for the data value of the B channel which is smaller than the mean value and a logical not for the data value of the B channel which is larger than the mean value;
performing small-area model matching on the operation picture after binarization processing and the answer template picture to obtain an optimal matching data matrix: firstly, selecting four base points on a job picture and an answer template picture after binarization processing;
based on the selected four base points, a black pixel point a1 in the job picture after binarization processing corresponds to a pixel point b1 in the answer template picture, then a1 is used for searching a black pixel point in a rectangular area with a preset size and taking b1 as the center, so that a plurality of matched data matrixes are obtained, and finally an optimal matching matrix is obtained by screening in the plurality of data matrixes;
and finally, performing labeling processing on the optimal matching data matrix, rendering different labels into preset corresponding colors, obtaining operation pictures of rendered colors, namely completing reading and amending the paper engineering drawing operation, and when performing label rendering: if the matrix point value in the optimal matching matrix is 0, the background color is white; if the matrix point value is 1, rendering the correct line into black; if the matrix point value is 2, rendering the line with less pictures into red; and if the matrix point value is 3, rendering the multi-drawing line to be yellow.
In summary, in order to realize the automatic and accurate reading of the paper engineering drawing, the technical scheme mainly processes and analyzes the shot operation picture so as to accurately realize the positioning of the engineering drawing from a complex environment, and avoids the adverse effect of different thickness of the lines of the hand-drawn engineering drawing on the discrimination rate in the template matching reading process, thereby improving the accuracy of the reading of the paper engineering drawing.
The technical scheme mainly carries out the following processing and analysis on the operation photos:
(1) picture preprocessing: the method is used for removing a background of an input original picture, selecting an identification area and performing tilt correction to obtain a regular picture, and specifically, according to information of pixel points of an input operation picture, the method comprises the steps of using picture pixel statistical analysis to extract engineering drawing operation from a complex background, then calibrating an area which is interested in reading and amending, realizing tilt correction by applying a perspective transformation model, and cutting and extracting the corrected picture to obtain a regular picture.
(2) Binarization of the picture: the method is used for performing logical yes and non-change on preprocessed picture data points, firstly taking a B channel of a picture RGB color channel, then calculating a data mean value of the B channel, performing pixel statistical analysis on the B channel in the RGB color channel for extracting the picture if the data value of the B channel is smaller than the mean value, and performing logical not if the data value of the B channel is larger than the mean value, calculating the data mean value of the B channel, and comparing the data mean value with a pixel point value to realize 0-1 change of the extracted picture B channel, thereby completing binarization processing;
(3) positioning the picture: the method is used for accurately matching the engineering drawing operation review, firstly determining four positioning base points of the engineering drawing, then uniformly matching the sizes of the engineering drawing and the template drawing by using the four base points of the template drawing, specifically selecting the four positioning base points, and adopting a small-area searching model to improve the matching precision due to the fact that a small area error exists in the matching of the binary image and the template drawing;
(4) coloring the picture: the method is used for judging the mistakes of the engineering drawing operation, rendering different judging results into different colors, and finally finishing the marking of the engineering drawing operation.
The specific process of this embodiment applying this technical solution is shown in fig. 3:
firstly, reading in a photo shot by student engineering drawing operation and a corresponding standard answer template;
and then, performing operation of removing background of the operation picture: counting data values of RGB channels of the shot pictures, calculating a mean value K of the data values, and replacing pixel point values larger than K in the RGB channels with 255, namely replacing the pixel points with white backgrounds;
then selecting four base points in the picture after background removal, wherein the trapezoid areas covered by the four base points are areas to be identified;
processing the selected four base points and the standard template by using a perspective transformation model, changing the trapezoid area covered by the four base points into a regular quadrilateral area, and cutting and storing the regular quadrilateral area;
then, carrying out binarization processing on the cut picture, firstly taking a channel B of an RGB color channel of the picture, then calculating a data mean value of the channel B, and regarding that the data value of the channel B is smaller than the mean value as logic yes, and regarding that the data value of the channel B is larger than the mean value as logic not;
then selecting four base points of the binaryzation and standard template pictures for matching the two pictures, improving matching accuracy through a small-region searching model, when the base points are determined during small-region model matching, enabling black pixel points a1 in the binaryzation pictures to correspond to pixel points b1 in the standard template pictures, then searching black pixel points of a rectangular small region with b1 as the center [5x5] by using a1, obtaining 25 matched data matrixes, and finally searching an optimal matching matrix in the 25 data matrixes, wherein the optimal matching matrix indicates that the matching degree of the operation pictures and the answer template pictures is highest.
And finally, labeling the optimal matching matrix, rendering different labels with different colors (as shown in fig. 4), and feeding the rendered pictures back to the user.
The technical scheme not only realizes the automatic reading of the paper engineering drawing operation, but also solves the problem of influence of the thickness of the line of the engineering drawing operation on the matching precision, and simultaneously improves the office efficiency of engineering drawing teaching workers; in addition, for learners of engineering drawing, the learners can independently know the wrong degree of the drawing content after the engineering drawing is finished, so that the learning efficiency and the interest of the learners are improved.
Claims (10)
1. The paper engineering drawing operation reading device is characterized by comprising a shooting module (1) and a picture processing module (2), wherein the shooting module (1) is used for shooting paper engineering drawing operation to be read in a reading mode to obtain a corresponding operation picture, answer template pictures with preset values are stored in the picture processing module (2), and the picture processing module (2) is used for processing and analyzing the operation picture to complete reading of the paper engineering drawing operation.
2. The paper engineering drawing work reading device as claimed in claim 1, wherein the picture processing module (2) comprises a preprocessing unit (201), a binarization unit (202), a positioning matching unit (203) and a label rendering unit (204), wherein the preprocessing unit (201) is used for performing background removal, area calibration and inclination correction operations on the work photo;
the binarization unit (202) is used for carrying out binarization processing on the preprocessed job picture;
the positioning matching unit (203) is used for performing template size matching operation on the binarized operation picture and the answer template picture to obtain an optimal matching data matrix;
the label rendering unit (204) is used for labeling the optimal matching data matrix and rendering different labels into corresponding colors to obtain job pictures of rendered colors.
3. A paper engineering work reading method using the paper engineering work reading device of claim 1, comprising the steps of:
s1, acquiring an operation photo corresponding to the paper engineering drawing operation through the shooting module, and transmitting the operation photo to the picture processing module;
and S2, the picture processing module sequentially carries out preprocessing, positioning, binaryzation, small-area model matching and label rendering operations on the job photo to obtain a job picture with a rendering color, namely, the reviewing of the paper engineering drawing job is completed.
4. The method for reviewing paper engineering drawing works as claimed in claim 3, wherein said step S2 specifically comprises the steps of:
s21, removing the background of the non-working surface in the working photo;
s22, carrying out area calibration on the operation photo without the background;
s23, performing inclination correction on the region calibrated in the operation picture based on the answer template picture to obtain an identification region;
s24, performing clipping operation and binarization processing on the identification area of the job photo;
s25, performing small-region model matching on the job picture after binarization processing and the answer template picture to obtain an optimal matching data matrix;
and S26, labeling the optimal matching data matrix, rendering different labels into preset corresponding colors, and obtaining operation pictures of the rendered colors, namely completing reading and amending the paper engineering drawing operation.
5. The method for reviewing paper engineering drawing works as claimed in claim 4, wherein the specific process of step S21 is as follows: and counting the data values of the RGB channels of the operation photos, calculating the mean value K of the data values, and replacing the pixel point value which is greater than K in the RGB channels with 255, namely replacing the pixel point with a white background so as to remove the background of the non-operation surface.
6. The method as claimed in claim 4, wherein the step S22 is to select four base points from the background-removed working photograph, and the trapezoid area covered by the four base points is used as the calibration area.
7. The method as claimed in claim 6, wherein the step S23 is specifically implemented by performing perspective transformation on the selected four base points and the answer template picture, so as to convert the trapezoid area covered by the four base points into a regular quadrilateral area, thereby implementing the tilt correction of the calibration area and obtaining the identification area.
8. The method for reviewing paper engineering drawing works as claimed in claim 7, wherein said step S24 specifically comprises the steps of:
s241, cutting the regular quadrilateral identification area to obtain an identification area picture;
s242, binarization processing is carried out on the identification area picture: firstly, taking a B channel of an RGB color channel of a picture, then calculating a data mean value of the B channel, and recording a data value of the B channel smaller than the mean value as a logical yes and a data value of the B channel larger than the mean value as a logical not.
9. The method for reviewing paper engineering drawing works as claimed in claim 4, wherein said step S25 specifically comprises the steps of:
s251, selecting four base points on the job picture and the answer template picture after binarization processing;
and S252, based on the four base points selected in the step S251, using the black pixel point a1 in the job picture after binarization processing to correspond to the pixel point b1 in the answer template picture, then using a1 to search the black pixel point in a rectangular region with a preset size and taking b1 as the center, thus obtaining a plurality of matched data matrixes, and finally screening the plurality of data matrixes to obtain an optimal matching matrix.
10. The method for reviewing paper engineering drawing works as claimed in claim 4, wherein said step S26 is specifically to perform labeling and color rendering according to matrix point values in the optimal matching matrix: if the matrix point value is 0, the background color is white; if the matrix point value is 1, rendering the correct line into black; if the matrix point value is 2, rendering the line with less pictures into red; and if the matrix point value is 3, rendering the multi-drawing line to be yellow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110690032.9A CN113505660A (en) | 2021-06-22 | 2021-06-22 | Paper engineering drawing operation reading device and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110690032.9A CN113505660A (en) | 2021-06-22 | 2021-06-22 | Paper engineering drawing operation reading device and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113505660A true CN113505660A (en) | 2021-10-15 |
Family
ID=78010214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110690032.9A Pending CN113505660A (en) | 2021-06-22 | 2021-06-22 | Paper engineering drawing operation reading device and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113505660A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447907A (en) * | 2015-11-13 | 2016-03-30 | 江苏科技大学 | Engineering drawing assignment intelligent correcting method and engineering drawing assignment intelligent correcting system based on three-dimensional reconstruction |
| CN107103312A (en) * | 2017-06-07 | 2017-08-29 | 深圳天珑无线科技有限公司 | A kind of image processing method and device |
| CN109472266A (en) * | 2018-01-29 | 2019-03-15 | 国网浙江省电力公司湖州供电公司 | Image document checks system and method in a kind of electrical engineering course of receiving |
| CN110660091A (en) * | 2019-09-30 | 2020-01-07 | 北京一起教育信息咨询有限责任公司 | Image registration processing method and device and photographing correction operation system |
| CN111242045A (en) * | 2020-01-15 | 2020-06-05 | 西安汇永软件科技有限公司 | Automatic operation exercise right and wrong indication method and system |
| CN111507251A (en) * | 2020-04-16 | 2020-08-07 | 北京世纪好未来教育科技有限公司 | Method and device for positioning answer area in test question image and electronic equipment |
| CN111563429A (en) * | 2020-04-23 | 2020-08-21 | 广东博智林机器人有限公司 | Drawing verification method and device, electronic equipment and storage medium |
-
2021
- 2021-06-22 CN CN202110690032.9A patent/CN113505660A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447907A (en) * | 2015-11-13 | 2016-03-30 | 江苏科技大学 | Engineering drawing assignment intelligent correcting method and engineering drawing assignment intelligent correcting system based on three-dimensional reconstruction |
| CN107103312A (en) * | 2017-06-07 | 2017-08-29 | 深圳天珑无线科技有限公司 | A kind of image processing method and device |
| CN109472266A (en) * | 2018-01-29 | 2019-03-15 | 国网浙江省电力公司湖州供电公司 | Image document checks system and method in a kind of electrical engineering course of receiving |
| CN110660091A (en) * | 2019-09-30 | 2020-01-07 | 北京一起教育信息咨询有限责任公司 | Image registration processing method and device and photographing correction operation system |
| CN111242045A (en) * | 2020-01-15 | 2020-06-05 | 西安汇永软件科技有限公司 | Automatic operation exercise right and wrong indication method and system |
| CN111507251A (en) * | 2020-04-16 | 2020-08-07 | 北京世纪好未来教育科技有限公司 | Method and device for positioning answer area in test question image and electronic equipment |
| CN111563429A (en) * | 2020-04-23 | 2020-08-21 | 广东博智林机器人有限公司 | Drawing verification method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 宁津生 等: "《测绘学概论》", 30 September 2016, 武汉大学出版社 * |
| 许琳娟 等: "《非均匀沙床面颗粒运动试验研究》", 31 October 2018, 黄河水利出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949564B (en) | Pointer type instrument automatic reading method based on deep learning | |
| CN108171297A (en) | A kind of answer card identification method and device | |
| CN111160352B (en) | Workpiece metal surface character recognition method and system based on image segmentation | |
| CN103439348B (en) | Remote controller key defect detection method based on difference image method | |
| CN113083804A (en) | Laser intelligent derusting method and system and readable medium | |
| CN109886928A (en) | A kind of target cell labeling method, device, storage medium and terminal device | |
| CN108537218A (en) | A kind of identifying processing method and device of answering card | |
| CN115619787B (en) | UV glue defect detection method, system, equipment and medium | |
| CN111190595A (en) | Method, device, medium and electronic equipment for automatically generating interface code based on interface design drawing | |
| CN112419291A (en) | Training method of bottle blank defect detection model, storage medium and terminal equipment | |
| CN117437647B (en) | Oracle character detection method based on deep learning and computer vision | |
| CN107067399A (en) | A kind of paper image segmentation processing method | |
| CN111144160B (en) | Full-automatic material cutting method and device and computer readable storage medium | |
| CN113505660A (en) | Paper engineering drawing operation reading device and method thereof | |
| CN116309398A (en) | Printed circuit board small target defect detection method based on multi-channel feature fusion learning | |
| CN115482535A (en) | Test paper automatic correction method, storage medium and equipment | |
| CN114639110A (en) | Intelligent reading method and system | |
| CN115393855A (en) | License plate product quality detection method, system and equipment | |
| CN107045635A (en) | A kind of paper image paging sub title processing method of online paper-marking system | |
| CN113435168A (en) | Method, system, terminal and medium for automatically editing rubber picture | |
| CN111674033A (en) | Engine nameplate intelligent printing and sorting method and system based on OCR | |
| CN110956174A (en) | Device number identification method | |
| CN110096257B (en) | Design graph automatic evaluation system and method based on intelligent recognition | |
| CN117372510B (en) | Map annotation identification method, terminal and medium based on computer vision model | |
| CN113705157B (en) | Photographing and modifying method for paper work |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211015 |