CN114170616A - Electric power engineering material information acquisition and analysis system and method based on graph paper set - Google Patents
Electric power engineering material information acquisition and analysis system and method based on graph paper set Download PDFInfo
- Publication number
- CN114170616A CN114170616A CN202111348016.8A CN202111348016A CN114170616A CN 114170616 A CN114170616 A CN 114170616A CN 202111348016 A CN202111348016 A CN 202111348016A CN 114170616 A CN114170616 A CN 114170616A
- Authority
- CN
- China
- Prior art keywords
- electric power
- power engineering
- data
- database
- engineering construction
- 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
- 239000000463 material Substances 0.000 title claims abstract description 135
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 59
- 238000007405 data analysis Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000003708 edge detection Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 210000004027 cell Anatomy 0.000 description 31
- 238000013527 convolutional neural network Methods 0.000 description 20
- 238000012549 training Methods 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 238000009795 derivation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000010421 standard material Substances 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a system and a method for collecting and analyzing electric power engineering material information based on a graph paper group. The analysis system comprises a data processing module, a data analysis module and a database, wherein the data processing module is simultaneously connected with the data processing module and the database, and the data analysis module is connected with the database. The analysis method comprises the steps of firstly, extracting and preprocessing the electric power engineering construction drawing in a database, and transmitting the preprocessed electric power engineering construction drawing to a data analysis module; the data analysis module establishes a material prediction model again, and extracts electric power material data in the electric power engineering construction drawing according to the material prediction model, the data analysis module stores the extracted electric power material data into a database, and the database carries out material statistics according to the electric power material data. According to the invention, the material data in the electric power engineering construction drawing is automatically extracted and counted through picture character recognition, so that the efficiency and the accuracy of material counting are greatly improved.
Description
Technical Field
The invention relates to the technical field of electric power material statistics, in particular to a system and a method for collecting and analyzing electric power engineering material information based on a graph paper group.
Background
In the construction process of the electric power engineering, constructors often need to carry out corresponding work arrangement strictly according to construction drawings, wherein the work arrangement includes material preparation work. When material preparation is carried out, the material content contained in the construction drawing is often manually identified and counted, and the efficiency of material preparation is very low. And because the quantity of materials is large and the types are multiple, the problems of missing notes or wrong notes and the like easily occur during manual identification and statistics.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a system and a method for collecting and analyzing electric power engineering material information based on a graph paper group.
The purpose of the invention is realized by the following technical scheme:
a power engineering material information acquisition and analysis method based on a graph paper group comprises the following steps:
the method comprises the following steps that firstly, a data processing module extracts electric power engineering construction drawings in a database, the data processing module preprocesses the electric power engineering construction drawings, and the data processing module transmits the preprocessed electric power engineering construction drawings to a data analysis module;
step two, a material prediction model is established by a data analysis module, and electric power material data in the electric power engineering construction drawing are extracted by the data analysis module according to the material prediction model;
and step three, the data analysis module stores the extracted electric power material data into a database, and the database carries out material statistics according to the electric power material data.
Electric power material data are acquired by carrying out character recognition on the electric power engineering construction drawing, recognition speed is improved, the condition that misclassification and misclassification cannot occur is guaranteed, and efficiency and accuracy of material statistics are greatly improved. And the electric power engineering construction drawing is preprocessed to highlight the image characteristics in the electric power engineering construction drawing, so that the accuracy of subsequent character recognition can be effectively improved, and the accuracy of material statistics is further improved. And the material statistics is directly carried out by utilizing the database without manual material statistics, so that the statistical error rate is reduced.
Further, the specific process of extracting the electric power material data in the electric power engineering construction drawing by the data analysis module according to the material prediction model in the step two is as follows: firstly, extracting the characteristics of an electric power engineering construction drawing to obtain characteristic points of the electric power engineering construction drawing, then positioning the position of an electric power material table in the electric power engineering construction drawing according to the characteristic points of the electric power engineering construction drawing, and carrying out picture segmentation on the electric power engineering construction drawing according to the position of the electric power material table to obtain an electric power material table picture; and carrying out picture character recognition on the electric power material table picture to acquire electric power material data.
The material data is often recorded in a form in the electric power engineering construction drawing, and when picture identification is carried out, the large probability that a plurality of areas with parallel transverse lines and parallel vertical lines are intersected is a form area, so that the areas meeting the form characteristics are found out by identifying the characteristic points, character identification is carried out, and the interference of other characters in the electric power engineering construction drawing on material data extraction is reduced.
Furthermore, before picture character recognition is carried out on the electric power material table pictures, the data analysis module also transmits the electric power material table pictures to the data processing module for preprocessing and edge detection processing, the data processing module transmits the processed electric power material table pictures back to the data analysis module, and the data analysis module carries out cell picture segmentation according to the processed electric power material table pictures.
Horizontal lines and vertical lines in the material table picture can be effectively detected through preprocessing and edge detection, and effective division basis can be provided when the cell picture is divided.
Furthermore, after the data analysis module divides the cell pictures, the data analysis module classifies the cell pictures, the data analysis module identifies the picture characters of the cell pictures according to the classification results, and stores the identification results of the picture characters of the cell pictures into the database in a classified manner.
Because the material table contains various materials, the material table picture is divided again, picture character recognition is carried out by taking the cell as a unit, and the accuracy of character recognition is improved.
Further, the picture character recognition is specifically OCR picture character recognition.
Further, the preprocessing comprises graying processing, binarization processing and denoising processing.
Further, after the electric power engineering construction drawing is preprocessed in the step one, edge detection is carried out on the electric power engineering construction drawing.
The electric power engineering construction drawing after the preprocessing and the edge detection processing can easily obtain the characteristic value of the table region range, namely, the large probability that the regions with a plurality of parallel transverse lines and a plurality of parallel and crossed vertical lines are the table regions is high, and the subsequent picture segmentation and identification efficiency is improved.
Furthermore, after the database performs material statistics on the electric power material data in the third step, the database transmits the material statistics result to the display module for displaying.
The utility model provides an electric power engineering goods and materials information acquisition and analytic system based on picture paper group, includes data processing module, data analysis module and database, data processing module is connected with data processing module and database simultaneously, data processing module is used for carrying out the preliminary treatment to electric power engineering construction drawing, data analysis module is connected with the database, data analysis module is used for drawing electric power goods and materials data, the database is used for storing electric power engineering construction drawing and electric power goods and materials data, the database still is used for carrying out goods and materials statistics to electric power goods and materials data.
Furthermore, the electric power engineering material information acquisition and analysis system based on the drawing group further comprises a display module, wherein the display module is connected with the database and is used for displaying material statistical results.
The invention has the beneficial effects that:
can come automatic extraction and statistics goods and materials data in the electric power engineering construction drawing through picture word discernment, compare in artifical discernment, the efficiency and the rate of accuracy of goods and materials statistics obtain great promotion. Still get rid of the influence of interference factor among the identification process through carrying out the preliminary treatment to electric power engineering construction drawing, and further promote the rate of accuracy of picture word recognition through carrying out the picture cutting to electric power engineering construction drawing.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a comparison graph before and after pretreatment of an electric power process construction drawing in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a material table according to an embodiment of the invention;
FIG. 4 is a diagram illustrating a result of recognizing cell pictures according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a CNN convolutional neural network according to an embodiment of the present invention;
FIG. 6 is a basic unit type neuron of the CNN convolutional neural network according to the embodiment of the present invention;
FIG. 7 is a schematic illustration of a material statistic according to an embodiment of the invention;
FIG. 8 is a schematic structural diagram of an embodiment of the present invention;
wherein: 1. the system comprises a data processing module 2, a data analysis module 3, a database 4 and a display module.
Detailed Description
The invention is further described below with reference to the figures and examples.
Example (b):
a method for collecting and analyzing electric power engineering material information based on graph paper sets is shown in figure 1 and comprises the following steps:
firstly, a data processing module 1 extracts an electric power engineering construction drawing in a database 3, the data processing module 1 preprocesses the electric power engineering construction drawing, and the data processing module 1 transmits the preprocessed electric power engineering construction drawing to a data analysis module 2 as a comparison drawing before and after drawing preprocessing is shown in fig. 2;
step two, the data analysis module 2 establishes a material prediction model, and the data analysis module 2 extracts electric power material data in the electric power engineering construction drawing according to the material prediction model;
and step three, the data analysis module 2 stores the extracted electric power material data into a database 3, the database 3 performs material statistics according to the electric power material data, and the database 3 is specifically a DBS (database system).
The specific process of extracting the electric power material data in the electric power engineering construction drawing by the data analysis module 2 according to the material prediction model in the second step is as follows: firstly, extracting the characteristics of an electric power engineering construction drawing to obtain characteristic points of the electric power engineering construction drawing, then positioning the position of an electric power material form in the electric power engineering construction drawing according to the characteristic points of the electric power engineering construction drawing, and carrying out picture segmentation on the electric power engineering construction drawing according to the position of the electric power material form to obtain an electric power material form picture, wherein the material form picture is shown in figure 3; and carrying out picture character recognition on the electric power material table picture to acquire electric power material data.
Before picture character recognition is carried out on the electric power material table pictures, the data analysis module 2 also transmits the electric power material table pictures to the data processing module 1 for preprocessing and edge detection processing, the data processing module 1 transmits the processed electric power material table pictures back to the data analysis module 2, and the data analysis module 2 carries out cell picture segmentation according to the processed electric power material table pictures.
After the data analysis module 2 divides the cell pictures, the data analysis module 2 classifies the cell pictures, the data analysis module 2 performs picture character recognition on the cell pictures according to the classification results, and stores the recognition results of the picture characters of the cell pictures into the database 3 in a classification manner, wherein the picture character recognition results of the cell pictures are shown in fig. 4.
Since some cells can be classified according to the general form of the table, such as cells describing titles, label cells and cells of specific contents, and the types of the contents stored in the cells in the same column are similar, the cells of the same kind are uniformly identified, and the image and character identification results are uniformly stored.
In order to improve the accuracy of picture character recognition, after the picture character recognition result of the cell picture is obtained, the data analysis module 2 compares the picture character recognition result of the cell picture in the database 3 with the standard material data in the database 3, searches the statistical characteristic of the forecast deviation of the material prediction model, and establishes a training data set according to the statistical characteristic of the forecast deviation. And training the material prediction model by adopting a pyrrch frame according to the training data set, adjusting model parameters of the material prediction model, wherein the training model specifically adopts a CNN convolutional neural network model.
A schematic diagram of a CNN convolutional neural network structure is shown in fig. 5, and a basic structure of a CNN convolutional neural network model includes two layers, namely a feature extraction layer and a feature mapping layer. The basic unit type neurons in the CNN convolutional neural network are shown in FIG. 6, in which x1,x2,…,xnThe method is characterized in that the method is an input of a neuron, a straight line connected with each input represents a connection weight W of the neuron, b is a bias term of the neuron, F () is an activation function, and Y is an output of the neuron. The output formula corresponding to the neuron is as follows:
the convolutional neural network is composed of such neurons, a typical CNN convolutional neural network model starts with several layers of convolutional layers and downsampling layers which are alternated, and a one-dimensional network close to an output layer is a fully-connected layer. The convolutional neural network is also one of the artificial neural networks, so the derivation work can be developed by using the derivation mode of the artificial neural network, wherein the convolution operation of the feature extraction layer in the CNN convolutional neural network model is equivalent to the connection weight W in the artificial neural network, and the downsampling operation in the feature mapping layer can also be realized by using the convolution mode. In the artificial neural network, the weight value of the network is updated layer by returning the error layer by layer through a back propagation algorithm and is updated layer by utilizing a gradient descent method according to the error returned by the lower layer, and the weight value is updated in the CNN convolutional neural network in such a way.
The gradient descent formula is as follows:
if the accuracy of character recognition is not high, the result of subsequent material statistics can be deviated, so that the material prediction model is continuously trained through recognized electric power material data and standard material data in the database 3, and model parameters are continuously adjusted to improve the accuracy of picture character recognition.
In order to further improve the accuracy of character recognition, different training sets are adopted to train different types of cell pictures to obtain a special training model. For example, for a cell whose number, quality, and other cell contents are numbers, a training set of numbers 0 to 9 may be used to train the model, so as to obtain a cell content specific to the number type. In addition, for the cells of the type of material names and specifications, because the possibility of using special nouns and special symbols in the cells is high, the model trained by a common library has poor effect, and a training data set is established according to the special nouns and specifications of materials to train the model so as to obtain the model for identifying the special material information.
Because different types of cells are trained by different types of models, when the cells are identified, the titles need to be additionally identified, the specific type of the corresponding column of the cell is judged, and then the corresponding model is used for training, so that the accuracy is improved.
The preprocessing comprises graying processing, binarization processing and denoising processing.
After preprocessing the electric power engineering construction drawing, performing edge detection on the electric power engineering construction drawing, and specifically performing edge detection on an image through a Laplace operator.
After the database 3 performs material statistics on the electric power material data in the third step, the database 3 transmits the material statistical result to the display module 4 for display, and the material statistical result is shown in fig. 7.
The utility model provides an electric power engineering goods and materials information acquisition and analytic system based on picture paper group, as shown in fig. 8, including data processing module 1, data analysis module 2, database 3 and display module 4, data processing module 1 is connected with data processing module 1 and database 3 simultaneously, data processing module 1 is used for carrying out the preliminary treatment to electric power engineering construction drawing, data analysis module 2 is connected with database 3, data analysis module 2 is used for extracting electric power goods and materials data, database 3 is used for storing electric power engineering construction drawing and electric power goods and materials data, database 3 still is used for carrying out goods and materials statistics to electric power goods and materials data.
The display module 4 is connected with the database 3, and the display module 4 is used for displaying material statistical results.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (10)
1. A power engineering material information acquisition and analysis method based on a graph paper group is characterized by comprising the following steps:
the method comprises the following steps that firstly, a data processing module extracts electric power engineering construction drawings in a database, the data processing module preprocesses the electric power engineering construction drawings, and the data processing module transmits the preprocessed electric power engineering construction drawings to a data analysis module;
step two, a material prediction model is established by a data analysis module, and electric power material data in the electric power engineering construction drawing are extracted by the data analysis module according to the material prediction model;
and step three, the data analysis module stores the extracted electric power material data into a database, and the database carries out material statistics according to the electric power material data.
2. The method for collecting and analyzing electric power engineering material information based on the drawing set according to claim 1, wherein the specific process of the data analysis module extracting the electric power material data in the electric power engineering construction drawing according to the material prediction model in the second step is as follows: firstly, extracting the characteristics of an electric power engineering construction drawing to obtain characteristic points of the electric power engineering construction drawing, then positioning the position of an electric power material table in the electric power engineering construction drawing according to the characteristic points of the electric power engineering construction drawing, and carrying out picture segmentation on the electric power engineering construction drawing according to the position of the electric power material table to obtain an electric power material table picture; and carrying out picture character recognition on the electric power material table picture to acquire electric power material data.
3. The method for collecting and analyzing power engineering material information based on the drawing set as claimed in claim 2, wherein before performing the picture character recognition on the power material table picture, the data analysis module further transmits the power material table picture to the data processing module for preprocessing and edge detection processing, the data processing module transmits the processed power material table picture back to the data analysis module, and the data analysis module performs cell picture segmentation according to the processed power material table picture.
4. The electric power engineering material information collection and analysis method based on the drawing group as claimed in claim 3, wherein after the data analysis module divides the unit cell picture, the data analysis module classifies the unit cell picture, the data analysis module performs picture character recognition on the unit cell picture according to the classification result, and stores the recognition result in the database in a classification manner.
5. The method for collecting and analyzing the information of the electric power engineering materials based on the drawing set as claimed in claim 2, wherein the drawing character recognition is specifically an OCR drawing character recognition.
6. The method for collecting and analyzing the material information of the power engineering based on the drawing set as claimed in claim 1, wherein the preprocessing comprises graying processing, binarization processing and de-noising processing.
7. The method for collecting and analyzing the electric power engineering material information based on the drawing group as claimed in claim 1, wherein in the step one, after the electric power engineering construction drawing is preprocessed, the electric power engineering construction drawing is subjected to edge detection.
8. The method for collecting and analyzing power engineering material information based on the drawing set as claimed in claim 1, wherein in the third step, after the database performs material statistics on the power material data, the database transmits the material statistics result to the display module for display.
9. The utility model provides an electric power engineering goods and materials information acquisition and analytic system based on picture paper group, its characterized in that, includes data processing module, data analysis module and database, data processing module is connected with data processing module and database simultaneously, data processing module is used for carrying out the preliminary treatment to electric power engineering construction drawing, data analysis module is connected with the database, data analysis module is used for extracting electric power goods and materials data, the database is used for storing electric power engineering construction drawing and electric power goods and materials data, the database still is used for carrying out goods and materials statistics to electric power goods and materials data.
10. The method for collecting and analyzing the material information of the power engineering based on the drawing paper group as claimed in claim 9, further comprising a display module, wherein the display module is connected with the database, and the display module is used for displaying the material statistical result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111348016.8A CN114170616A (en) | 2021-11-15 | 2021-11-15 | Electric power engineering material information acquisition and analysis system and method based on graph paper set |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111348016.8A CN114170616A (en) | 2021-11-15 | 2021-11-15 | Electric power engineering material information acquisition and analysis system and method based on graph paper set |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114170616A true CN114170616A (en) | 2022-03-11 |
Family
ID=80479016
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111348016.8A Pending CN114170616A (en) | 2021-11-15 | 2021-11-15 | Electric power engineering material information acquisition and analysis system and method based on graph paper set |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114170616A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105426856A (en) * | 2015-11-25 | 2016-03-23 | 成都数联铭品科技有限公司 | Image table character identification method |
CN108596066A (en) * | 2018-04-13 | 2018-09-28 | 武汉大学 | A kind of character identifying method based on convolutional neural networks |
CN109993112A (en) * | 2019-03-29 | 2019-07-09 | 杭州睿琪软件有限公司 | The recognition methods of table and device in a kind of picture |
CN111401312A (en) * | 2020-04-10 | 2020-07-10 | 深圳新致软件有限公司 | PDF drawing character recognition method, system and equipment |
WO2020164281A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技(深圳)有限公司 | Form parsing method based on character location and recognition, and medium and computer device |
CN111860348A (en) * | 2020-07-21 | 2020-10-30 | 国网山东省电力公司青岛供电公司 | Deep learning-based weak supervision power drawing OCR recognition method |
CN112818812A (en) * | 2018-12-13 | 2021-05-18 | 北京金山数字娱乐科技有限公司 | Method and device for identifying table information in image, electronic equipment and storage medium |
-
2021
- 2021-11-15 CN CN202111348016.8A patent/CN114170616A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105426856A (en) * | 2015-11-25 | 2016-03-23 | 成都数联铭品科技有限公司 | Image table character identification method |
CN108596066A (en) * | 2018-04-13 | 2018-09-28 | 武汉大学 | A kind of character identifying method based on convolutional neural networks |
CN112818812A (en) * | 2018-12-13 | 2021-05-18 | 北京金山数字娱乐科技有限公司 | Method and device for identifying table information in image, electronic equipment and storage medium |
WO2020164281A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技(深圳)有限公司 | Form parsing method based on character location and recognition, and medium and computer device |
CN109993112A (en) * | 2019-03-29 | 2019-07-09 | 杭州睿琪软件有限公司 | The recognition methods of table and device in a kind of picture |
CN111401312A (en) * | 2020-04-10 | 2020-07-10 | 深圳新致软件有限公司 | PDF drawing character recognition method, system and equipment |
CN111860348A (en) * | 2020-07-21 | 2020-10-30 | 国网山东省电力公司青岛供电公司 | Deep learning-based weak supervision power drawing OCR recognition method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112418117B (en) | Small target detection method based on unmanned aerial vehicle image | |
CN108805076B (en) | Method and system for extracting table characters of environmental impact evaluation report | |
Shahab et al. | ICDAR 2011 robust reading competition challenge 2: Reading text in scene images | |
CN111460927B (en) | Method for extracting structured information of house property evidence image | |
CN102346847B (en) | License plate character recognizing method of support vector machine | |
CN108596038B (en) | Method for identifying red blood cells in excrement by combining morphological segmentation and neural network | |
CN105389593A (en) | Image object recognition method based on SURF | |
CN111353491B (en) | Text direction determining method, device, equipment and storage medium | |
CN108897778A (en) | A kind of image labeling method based on multi-source big data analysis | |
CN108319672B (en) | Mobile terminal bad information filtering method and system based on cloud computing | |
CN111401353A (en) | Method, device and equipment for identifying mathematical formula | |
CN107169106A (en) | Video retrieval method, device, storage medium and processor | |
CN101604384A (en) | Individualized fingerprint identification method | |
CN111026870A (en) | ICT system fault analysis method integrating text classification and image recognition | |
CN105930792A (en) | Human action classification method based on video local feature dictionary | |
CN114140665A (en) | Dense small target detection method based on improved YOLOv5 | |
CN106023159A (en) | Disease spot image segmentation method and system for greenhouse vegetable leaf | |
CN113254634A (en) | File classification method and system based on phase space | |
CN115311689A (en) | Cattle face identification feature extraction model construction method and cattle face identification method | |
CN111340032A (en) | Character recognition method based on application scene in financial field | |
CN114971294A (en) | Data acquisition method, device, equipment and storage medium | |
CN118115782A (en) | Jet printing color two-dimensional code defect detection method based on deep learning | |
CN116524725B (en) | Intelligent driving traffic sign image data identification system | |
CN117372956A (en) | Method and device for detecting state of substation screen cabinet equipment | |
CN114170616A (en) | Electric power engineering material information acquisition and analysis system and method based on graph paper set |
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 |