CN114627486B - Electric drawing composition analysis method and system - Google Patents
Electric drawing composition analysis method and system Download PDFInfo
- Publication number
- CN114627486B CN114627486B CN202210279992.0A CN202210279992A CN114627486B CN 114627486 B CN114627486 B CN 114627486B CN 202210279992 A CN202210279992 A CN 202210279992A CN 114627486 B CN114627486 B CN 114627486B
- Authority
- CN
- China
- Prior art keywords
- information
- equipment
- drawing image
- text
- electric drawing
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of power grids, and provides a method and a system for analyzing the composition of an electric drawing, wherein the method comprises the following steps: obtaining an electric drawing image; analyzing each primitive information in the electric drawing image, and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information; correlating the equipment information with the text information to obtain equipment and text correlation information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information; generating a drawing description file according to the equipment and text association information and the equipment and connecting line association information; and marking in the electric drawing image according to the drawing description file. Through the technical scheme, the problem that the identification speed of the electric drawing composition analysis method in the prior art is low is solved.
Description
Technical Field
The invention relates to the technical field of power grids, in particular to a method and a system for analyzing the composition of an electric drawing.
Background
In the power system of China, a large number of power drawings exist, and in the long-term processing process, due to the problems of technology and management, the identification of people on the drawings is mostly repeated, and the problem can occur in a large probability. With the development of computer technology, some engineering departments have widely adopted rcnn, fat_ rcnn and other technologies to analyze images. However, the result is often not ideal, taking the master_ rcnn algorithm as an example, the drawing needs to be firstly subjected to object detection to determine the position, and then the master_ rcnn is adopted to classify the objects, so that the recognition speed is slower.
Disclosure of Invention
The invention provides a method and a system for analyzing the composition of an electric drawing, which solve the problem of low recognition speed of the method for analyzing the composition of the electric drawing in the related technology.
The technical scheme of the invention is as follows:
in a first aspect, a method for analyzing a composition of an electrical drawing includes:
Obtaining an electric drawing image;
Analyzing each primitive information in the electric drawing image, and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
correlating the equipment information with the text information to obtain equipment and text correlation information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
generating a drawing description file according to the equipment and text association information and the equipment and connecting line association information;
And marking in the electric drawing image according to the drawing description file.
In a second aspect, a power drawing composition analysis system includes:
the first obtaining unit is used for obtaining an electric drawing image;
the first analysis unit is used for analyzing each primitive information in the electric drawing image and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
The first association unit is used for associating the equipment information with the text information to obtain equipment and text association information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
the first generation unit is used for generating drawing description files according to the equipment and text association information and the equipment and connecting line association information;
The first labeling unit is used for labeling the electric drawing image according to the drawing description file.
In a third aspect, a computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of the electrical drawing composition analysis method.
The working principle and the beneficial effects of the invention are as follows:
according to the method, firstly, the primitive information is extracted from the electric drawing image, the associated information of each primitive is generated, then the drawing description file is generated according to the associated information of each primitive, the positions and types of the primitives are directly returned, the primitives are re-marked in the electric drawing image, and compared with a mode of combining the master_ rcnn with target detection, the calculation time is greatly shortened.
Drawings
The invention will be described in further detail with reference to the drawings and the detailed description.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of one embodiment of the method of the present invention;
FIG. 3 is a schematic diagram of the system of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by one of ordinary skill 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.
Example 1
As shown in fig. 1, a flow chart of the method of the present invention includes:
S100: obtaining an electric drawing image;
specifically, the power drawing image may be obtained by using an existing image acquisition device, which is not described herein.
S200: analyzing each primitive information in the electric drawing image, and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
s300: correlating the equipment information with the text information to obtain equipment and text correlation information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
S400: generating a drawing description file according to the equipment and text association information and the equipment and connecting line association information;
s500: and marking in the electric drawing image according to the drawing description file.
According to the method, firstly, the primitive information is extracted from the electric drawing image, the associated information of each primitive is generated, then the drawing description file is generated according to the associated information of each primitive, the positions and types of the primitives are directly returned, the primitives are re-marked in the electric drawing image, and compared with a mode of combining the master_ rcnn with target detection, the calculation time is greatly shortened.
It should be noted that, in the conventional method, the drawing is converted into the binary matrix, when the bus is identified, the bus is slid at a step pitch with the same height pixel as 1 to identify the outline, and when the different drawing sizes are dealt with, the thickness of the bus cannot be intuitively determined, so that the bus is easy to be confused with the connecting line, and the identification effect is poor. In this embodiment, the bus and the connecting line are identified together in this embodiment, and the information such as the connecting line and the bus is matched by adopting a mode of putting a shrinking line template, which is favorable for accurate identification of the bus.
As shown in fig. 2, a flow chart of one embodiment of the present invention is shown. The specific process of step S200 includes:
s210: and extracting text information (text label data) in the electric drawing image by using the trained ocr model, so that the drawing only keeps equipment and circuit information.
S220: the improved YOLOV s model is adopted to identify the equipment information in the electric drawing image, the YOLOV identification model has the characteristics of high identification speed and good effect, but in order to realize the proprietary detection of the small-sized target equipment in the electric drawing, the accuracy of equipment identification is improved, and further structural optimization and parameter adjustment are required to be carried out on the network structure of the YOLOV model. The problem of the identification of the power drawing equipment is that a plurality of small targets exist in practical application, and the downsampling of the YOLO algorithm is generally 32 times, so that the width and the height must be divided by 32. Since it is generally selected as a multiple of 32 in multi-scale training, a minimum of 320×320 and a maximum of 640×640, the input size of data is adjusted to 640×640, which can improve the accuracy of recognition of small objects by the apparatus to some extent. Because the electric drawings are inconsistent in size, and some drawings are particularly large, some equipment cannot be identified due to the fact that the drawings are reduced in a trade way, the embodiment adopts a sliding window to divide one drawing into a plurality of pictures for identification, the identification results are combined, and the position information of the equipment is recorded. And clearing equipment information in the power drawing image, and only retaining circuit information.
S230: identifying a bus and a connecting wire in the electric drawing image in a template matching mode, and deleting the bus and the connecting wire from the electric drawing image; and storing the bus position and the connecting wire end point position.
After the drawing is scaled, the corresponding thickness of the bus is scaled, and the implementation adopts a scaling line template mode to match information such as connecting lines, buses and the like, so that the method is suitable for drawings with different sizes.
Further, the specific process of step S300 includes:
Selecting any piece of equipment information as current equipment information, executing the operation of equipment and text association, and executing the operation of equipment and connection line association; the operation of associating the equipment with the text comprises the following steps: according to the equipment position in the current equipment information, calculating the Euclidean distance between the equipment position and each text position, obtaining a plurality of first Euclidean distances, selecting the smallest first Euclidean distance, and storing the association relationship between the text information corresponding to the smallest first Euclidean distance and the equipment information as equipment and text association information;
The operations of the device associated with the connection line include: according to the equipment position in the current equipment information, calculating the Euclidean distance between the equipment position and each connecting terminal point to obtain a plurality of second Euclidean distances, selecting the smallest second Euclidean distance, and storing the association relationship between the connecting line information corresponding to the smallest second Euclidean distance and the equipment information as the equipment and connecting line association information;
and switching the other device information to serve as the current device information, and repeatedly executing the operation of associating the device with the text and the operation of associating the device with the connecting line until all the device information is traversed.
Further, the specific process of step S400 includes:
selecting any piece of equipment information as target equipment information, and executing the operation of generating a target equipment description file; the operation of generating the description file specifically includes: generating a drawing description file according to the text information associated with the target equipment information and the connecting line information associated with the target equipment information;
and switching the other device information to serve as target device information, and repeatedly executing the operation of generating the target device description file until the device information is traversed.
Further, step S200 is preceded by a step of preprocessing, where the step of preprocessing includes:
Judging the complexity of the electric drawing image by adopting a mode of calculating information entropy;
And determining a corresponding threshold according to the complexity degree of the electric drawing image, and performing the operation of enlarging or reducing the electric drawing image.
Specifically, firstly, carrying out gray processing on an electric drawing image; carrying out histogram statistics on the gray level of the electric drawing image, and calculating the probability Pi (x) of each gray level number; and then carrying out information entropy formula calculation to obtain the information entropy, wherein the information entropy is as follows:
The information entropy indicates the information amount we obtain when an event occurs, and the larger the information amount is, the more complex the image is. Corresponding thresholds are designated for images with different complexity degrees, so that the drawing is enlarged or reduced. The drawing size is adjusted in a self-adaptive mode, the complex drawing is amplified, and the primitive information in the drawing can be accurately identified.
Example two
As shown in fig. 3, the present embodiment provides a system for analyzing the composition of an electrical drawing, including:
the first obtaining unit is used for obtaining an electric drawing image;
the first analysis unit is used for analyzing each primitive information in the electric drawing image and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
The first association unit is used for associating the equipment information with the text information to obtain equipment and text association information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
the first generation unit is used for generating drawing description files according to the equipment and text association information and the equipment and connecting line association information;
The first labeling unit is used for labeling the electric drawing image according to the drawing description file.
Further, the method further comprises the following steps:
the first calculation unit is used for judging the complexity degree of the electric drawing image in a mode of calculating information entropy;
The first processing unit is used for determining a corresponding threshold according to the complexity degree of the electric drawing image and performing the operation of enlarging or reducing the electric drawing image.
Further, the method further comprises the following steps:
the second processing unit is used for carrying out graying processing on the electric drawing image;
The second calculation unit is used for carrying out histogram statistics on the gray level of the electric drawing image and calculating the probability of each gray level number;
the third calculation unit is used for calculating information entropy according to the probability of each gray level number;
and the first judging unit is used for judging the complexity degree of the electric drawing image according to the information entropy.
Further, the method further comprises the following steps:
The first recognition unit is used for recognizing character information in the electric drawing image by adopting the OCR model and deleting the character information from the electric drawing image; the text information comprises text positions;
the second identification unit is used for identifying equipment information in the electric drawing image by adopting an image identification model and deleting the equipment information from the electric drawing image; the device information includes a device location;
the third recognition unit recognizes a bus and a connecting wire in the electric drawing image in a template matching mode, and deletes the bus and the connecting wire from the electric drawing image; and storing the bus position and the connecting wire end point position.
The various modifications and specific examples of the electric drawing composition analysis method in the first embodiment are equally applicable to the electric drawing composition analysis system of the present embodiment, and those skilled in the art can clearly know the implementation method of the electric drawing composition analysis system of the present embodiment through the detailed description of the electric drawing composition analysis method, so that the details are not described herein for the sake of brevity.
Example III
The present embodiment proposes a computer-readable storage medium, in which a computer program is stored, which when executed by a processor, implements the steps of the above-described electrical drawing composition analysis method.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (8)
1. The method for analyzing the composition of the electric drawing is characterized by comprising the following steps:
Obtaining an electric drawing image;
Analyzing each primitive information in the electric drawing image, and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
correlating the equipment information with the text information to obtain equipment and text correlation information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
generating a drawing description file according to the equipment and text association information and the equipment and connecting line association information;
marking in the electric drawing image according to the drawing description file;
the step of analyzing the primitive information in the power drawing image further comprises the following steps:
Judging the complexity of the electric drawing image by adopting a mode of calculating information entropy;
Determining a corresponding threshold according to the complexity of the electric drawing image, and performing the operation of enlarging or reducing the electric drawing image;
After the drawing is scaled, the mode of scaling the line template is adopted to match the information of the connecting line and the bus, so that the method is suitable for drawings with different sizes.
2. The method for analyzing the composition of the electric drawing according to claim 1, wherein the method for judging the complexity of the electric drawing image by calculating the information entropy comprises the following steps:
Carrying out graying treatment on the electric drawing image;
carrying out histogram statistics on the gray level of the electric drawing image, and calculating the probability of each gray level number;
Calculating information entropy according to the probability of each gray level number;
and judging the complexity degree of the electric drawing image according to the information entropy.
3. The method for analyzing the composition of the electric drawing according to claim 1, wherein analyzing each primitive information in the electric drawing image and deleting the primitive information from the electric drawing image specifically comprises:
Adopting an OCR model to identify text information in the electric drawing image, and deleting the text information from the electric drawing image; the text information comprises text positions;
Identifying equipment information in the electric drawing image by adopting an image identification model, and deleting the equipment information from the electric drawing image; the device information includes a device location;
Identifying a bus and a connecting wire in the electric drawing image in a template matching mode, and deleting the bus and the connecting wire from the electric drawing image; and storing the bus position and the connecting wire end point position.
4. The method for analyzing the composition of the electrical drawing according to claim 3, wherein the step of identifying the equipment information in the electrical drawing image by using the image identification model specifically comprises the steps of:
and cutting one electric drawing image into a plurality of pictures by adopting a sliding window, respectively identifying the pictures by adopting an improved YOLOV s model, and combining identification results of the pictures to obtain equipment information in the whole electric drawing image.
5. The method for analyzing the composition of the electric drawing according to claim 3, wherein the equipment information is associated with text information to obtain equipment and text associated information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information, wherein the method specifically comprises the following steps of:
Selecting any piece of equipment information as current equipment information, executing the operation of equipment and text association, and executing the operation of equipment and connection line association; the operation of associating the equipment with the text comprises the following steps: according to the equipment position in the current equipment information, calculating the Euclidean distance between the equipment position and each text position, obtaining a plurality of first Euclidean distances, selecting the smallest first Euclidean distance, and storing the association relationship between the text information corresponding to the smallest first Euclidean distance and the equipment information as equipment and text association information;
The operations of the device associated with the connection line include: according to the equipment position in the current equipment information, calculating the Euclidean distance between the equipment position and each connecting terminal point to obtain a plurality of second Euclidean distances, selecting the smallest second Euclidean distance, and storing the association relationship between the connecting line information corresponding to the smallest second Euclidean distance and the equipment information as the equipment and connecting line association information;
and switching the other device information to serve as the current device information, and repeatedly executing the operation of associating the device with the text and the operation of associating the device with the connecting line until all the device information is traversed.
6. The method for analyzing the composition of the electric drawing according to claim 1, wherein the generating the drawing description file according to the equipment and text association information and the equipment and connection line association information specifically includes:
Selecting any piece of equipment information as target equipment information, and executing the operation of generating a target equipment description file; the operation of generating the target equipment description file specifically comprises the following steps: generating a drawing description file according to the text information associated with the target equipment information and the connecting line information associated with the target equipment information;
And switching the other device information to serve as target device information, and repeatedly executing the operation of generating the target device description file until all the device information is traversed.
7. The utility model provides an electric power drawing composition analysis system which characterized in that includes:
the first obtaining unit is used for obtaining an electric drawing image;
the first analysis unit is used for analyzing each primitive information in the electric drawing image and deleting the primitive information from the electric drawing image; the primitive information includes: text information, equipment information, bus information and connecting line information;
The first association unit is used for associating the equipment information with the text information to obtain equipment and text association information; correlating the equipment information with the connecting wire information to obtain equipment and connecting wire correlation information; wherein the bus information is used as equipment information;
the first generation unit is used for generating drawing description files according to the equipment and text association information and the equipment and connecting line association information;
The first labeling unit is used for labeling the electric drawing image according to the drawing description file;
the first calculation unit is used for judging the complexity degree of the electric drawing image in a mode of calculating information entropy;
The first processing unit is used for determining a corresponding threshold according to the complexity degree of the electric drawing image and performing the operation of enlarging or reducing the electric drawing image;
After the drawing is scaled, the mode of scaling the line template is adopted to match the information of the connecting line and the bus, so that the method is suitable for drawings with different sizes.
8. A computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, which when executed by a processor, implements the steps of the electrical drawing composition analysis method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279992.0A CN114627486B (en) | 2022-03-22 | 2022-03-22 | Electric drawing composition analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279992.0A CN114627486B (en) | 2022-03-22 | 2022-03-22 | Electric drawing composition analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114627486A CN114627486A (en) | 2022-06-14 |
| CN114627486B true CN114627486B (en) | 2024-06-07 |
Family
ID=81904866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210279992.0A Active CN114627486B (en) | 2022-03-22 | 2022-03-22 | Electric drawing composition analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114627486B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156795A (en) * | 2010-02-12 | 2011-08-17 | 华东电网有限公司 | Simulation information system of digital transformer station based on transformer station configuration description file |
| CN105718636A (en) * | 2016-01-14 | 2016-06-29 | 中国南方电网有限责任公司 | Automatic conversion method for station primary wiring diagram model |
| CN112149548A (en) * | 2020-09-17 | 2020-12-29 | 宁夏宁电电力设计有限公司 | CAD drawing intelligent input and identification method and device suitable for terminal row |
| CN112464314A (en) * | 2020-12-16 | 2021-03-09 | 南京金水尚阳信息技术有限公司 | File conversion method and device for hybrid power |
| CN113743057A (en) * | 2021-09-16 | 2021-12-03 | 南京金水尚阳信息技术有限公司 | Object recognition redrawing-based power grid OCS drawing conversion method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11250262B2 (en) * | 2020-03-12 | 2022-02-15 | RapidDeploy, Inc. | Wildfire surveillance UAV and fire surveillance system |
-
2022
- 2022-03-22 CN CN202210279992.0A patent/CN114627486B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156795A (en) * | 2010-02-12 | 2011-08-17 | 华东电网有限公司 | Simulation information system of digital transformer station based on transformer station configuration description file |
| CN105718636A (en) * | 2016-01-14 | 2016-06-29 | 中国南方电网有限责任公司 | Automatic conversion method for station primary wiring diagram model |
| CN112149548A (en) * | 2020-09-17 | 2020-12-29 | 宁夏宁电电力设计有限公司 | CAD drawing intelligent input and identification method and device suitable for terminal row |
| CN112464314A (en) * | 2020-12-16 | 2021-03-09 | 南京金水尚阳信息技术有限公司 | File conversion method and device for hybrid power |
| CN113743057A (en) * | 2021-09-16 | 2021-12-03 | 南京金水尚阳信息技术有限公司 | Object recognition redrawing-based power grid OCS drawing conversion method |
Non-Patent Citations (1)
| Title |
|---|
| 工程图纸识别与理解的研究现状分析;董玉德, 赵韩, 王平, 张国平;合肥工业大学学报(自然科学版);20050128(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114627486A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114463586A (en) | Training and image recognition method, device, equipment and medium of image recognition model | |
| CN109800698A (en) | Icon detection method based on depth network | |
| CN112149548B (en) | CAD drawing intelligent input and identification method and device suitable for terminal row | |
| CN111860525A (en) | Bottom-up optical character recognition method suitable for terminal block | |
| CN116452667A (en) | Target identification and positioning method based on image processing | |
| CN111445386A (en) | Image correction method based on four-point detection of text content | |
| CN111738319A (en) | Clustering result evaluation method and device based on large-scale samples | |
| CN111161300A (en) | Nilback image segmentation method based on improved Otsu method | |
| CN113657370A (en) | Character recognition method and related equipment thereof | |
| CN107729863B (en) | Human finger vein recognition method | |
| CN116309963B (en) | Batch labeling method and device for images, electronic equipment and storage medium | |
| CN113963197A (en) | Image recognition method and device, electronic equipment and readable storage medium | |
| CN114627486B (en) | Electric drawing composition analysis method and system | |
| CN114973300B (en) | Component type identification method and device, electronic equipment and storage medium | |
| CN111488811A (en) | Face recognition method and device, terminal equipment and computer readable medium | |
| CN112487853A (en) | Handwriting comparison method and system, electronic equipment and storage medium | |
| CN115424254A (en) | License plate recognition method, system, equipment and storage medium | |
| CN114283409A (en) | Method for recognizing and structurally deriving terminal strip wiring | |
| CN111178409B (en) | Image matching and recognition system based on big data matrix stability analysis | |
| CN110569831B (en) | Feature matching method and system for power equipment nameplate | |
| CN114998906B (en) | Text detection method, training method and device of model, electronic equipment and medium | |
| Shekar | Skeleton matching based approach for text localization in scene images | |
| CN117314728B (en) | GPU operation regulation and control method and system | |
| Kaur et al. | A novel technique for robust image segmentation | |
| CN118038480A (en) | Engineering drawing data analysis processing method and system |
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 |