CN113591698A - High-voltage cable accessory drawing comparison method and system based on image recognition - Google Patents
High-voltage cable accessory drawing comparison method and system based on image recognition Download PDFInfo
- Publication number
- CN113591698A CN113591698A CN202110869656.7A CN202110869656A CN113591698A CN 113591698 A CN113591698 A CN 113591698A CN 202110869656 A CN202110869656 A CN 202110869656A CN 113591698 A CN113591698 A CN 113591698A
- Authority
- CN
- China
- Prior art keywords
- cable accessory
- pixel
- voltage cable
- recognition
- character
- 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 64
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000010586 diagram Methods 0.000 claims abstract description 17
- 230000002708 enhancing effect Effects 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000012015 optical character recognition Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 238000012795 verification Methods 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
- G06F18/21—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)
- Character Discrimination (AREA)
Abstract
The invention relates to a high-voltage cable accessory drawing comparison method and system based on image recognition, wherein the method comprises the following steps: obtaining a high-voltage cable accessory drawing; performing characteristic identification on the high-voltage cable accessory drawing to obtain a cable accessory characteristic diagram; performing character recognition on the cable accessory characteristic diagram, enhancing character patterns, and acquiring a cable accessory character enhancement diagram; and comparing the cable accessory character enhanced drawing with a corresponding manufacturer template drawing in a preset standard process library, carrying out consistency judgment, and outputting a consistency judgment result of the high-voltage cable accessory drawing. Compared with the prior art, the invention has the advantages of convenient use, safety, reliability, maintenance and management cost reduction and the like.
Description
Technical Field
The invention relates to the technical field of high-voltage cable accessory drawing comparison, in particular to a high-voltage cable accessory drawing comparison method and system based on image recognition.
Background
In view of the fact that at present, a plurality of manufacturers of high-voltage cable accessories have various types of cable accessories, characteristics and limitations of different types, and part of the manufacturers have no history background, the generated high-voltage cable accessories are not subjected to long-term operation experience data as precipitates in some design links, and the drawing process design is often changed.
In order to realize the purpose of managing and controlling a standard process of a high-voltage cable accessory and ensure the safe and stable application of a running cable, management and control and customs control are required to be carried out from the source of signing a technical protocol, identification and solidification of the process are realized by establishing a database of the standard process and utilizing the simulation installation of a first set of cable accessory process, and the comparison of the compliance and the goodness of a drawing is completed in the later-stage technical protocol signing process.
The existing comparison scheme carries out evaluation through manual work, a large number of uncertain factors exist, accuracy of evaluation results cannot be guaranteed, and workload of personnel is increased.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a high-voltage cable accessory drawing comparison method based on image identification, which reduces the workload of personnel investment and the uncertainty of personnel review.
The purpose of the invention can be realized by the following technical scheme:
a high-voltage cable accessory drawing comparison method based on image recognition comprises the following steps:
obtaining a high-voltage cable accessory drawing;
performing characteristic identification on the high-voltage cable accessory drawing to obtain a cable accessory characteristic diagram;
performing character recognition on the cable accessory characteristic diagram, enhancing character patterns, and acquiring a cable accessory character enhancement diagram;
and comparing the cable accessory character enhanced drawing with a corresponding manufacturer template drawing in a preset standard process library, carrying out consistency judgment, and outputting a consistency judgment result of the high-voltage cable accessory drawing.
Further, the LBP algorithm is adopted to perform feature recognition on the high-voltage cable accessory drawing.
Further, the determination process of the window size of the LBP algorithm comprises the following steps:
the parameter k is set and initialized, and,
setting an active window of each pixel according to the parameter k, and setting a calculation formula of the pixel average intensity value of the active window of each pixel;
for each pixel, calculating the pixel average intensity difference between two non-overlapping windows of the pixel in the horizontal direction and the vertical direction respectively,
acquiring a k value which can enable the value of the pixel average intensity difference between two non-overlapping windows in the horizontal direction or the pixel average intensity difference between two non-overlapping windows in the vertical direction to reach the maximum for each pixel;
the size of the active window is determined as the window size of the LBP algorithm, based on the determined k value for each pixel.
Further, the calculation expression of the pixel average intensity value is:
wherein x is the abscissa of the pixel, y is the ordinate of the pixel, Ak(x, y) is the pixel average intensity value of pixel (x, y) in an active window, g (i, j) is the pixel value with coordinate (i, j) in the image;
further, the pixel average intensity difference E between two non-overlapping windows in the horizontal directionk，hThe computational expression of (x, y) is:
Ek，h(x，y)＝|Ak(x+2k-1，y)-Ak(x-2k-1，y)|
the pixel average intensity difference E between two non-overlapping windows in the vertical directionk，vThe computational expression of (x, y) is:
Ek，v(x，y)＝|Ak(x，y+2k-1)-Ak(x，y-2k-1)|。
and further, performing character recognition on the cable accessory characteristic diagram by an optical character recognition method to enhance character patterns, wherein the optical character recognition method comprises the steps of preprocessing the cable accessory characteristic diagram, loading the preprocessed cable accessory characteristic diagram into a pre-trained character recognition engine to perform character recognition, and finally performing image enhancement on a character recognition result.
Further, the character recognition engine employs an open source OCR engine Tesseract.
Further, the consistency judgment process specifically includes: dividing the cable accessory character enhancement diagram and the corresponding factory template drawing into a plurality of areas, respectively calculating fractal dimension values of the two corresponding areas, obtaining an absolute value of a fractal dimension difference value, outputting a judgment result that the drawings are consistent if the absolute value of the fractal dimension difference value is smaller than a preset reference threshold, and otherwise, outputting a judgment result that the drawings are inconsistent.
Further, if the drawings are judged to be inconsistent, corresponding region labels are output.
The invention also provides a high-voltage cable accessory drawing comparison system based on image recognition, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program to execute the steps of the method.
Compared with the prior art, the invention has the following advantages:
(1) compared with the traditional manual examination and management, the process library management is more convenient, safe and reliable, and the cost in the aspects of operation maintenance, manual management and the like is greatly reduced through long-term use, so that better economic benefit is created.
(2) The comprehensive auditing method has the advantages that the working efficiency is greatly improved through the comprehensive auditing of all high-voltage cable accessories, the auditing dimension is comprehensive and scientific, the technical support and the logic design are realized, and the auditing process is simple, efficient and reliable.
(3) When the LBP algorithm is adopted to carry out feature recognition on the high-voltage cable accessory drawing, the limitation of the existing LBP algorithm on the complex high-voltage cable accessory drawing is found, so that an active window selection scheme of a self-adaptive threshold value is provided, the window size which enables the pixel average intensity difference between the windows which are not overlapped in the horizontal direction and the vertical direction to be maximum is obtained, and the error of the LBP on primitive feature extraction can be reduced by combining the window size with the LBP algorithm.
Drawings
Fig. 1 is a schematic flowchart of a high-voltage cable accessory drawing comparison method based on image recognition according to an embodiment of the present invention;
fig. 2 is a comparison graph of recognition effects before and after gray enhancement provided in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the embodiment provides a high-voltage cable accessory drawing comparison method based on image recognition, which includes the following steps:
obtaining a high-voltage cable accessory drawing;
performing feature recognition on a high-voltage cable accessory drawing to obtain a cable accessory feature map;
carrying out character recognition on the cable accessory characteristic diagram, enhancing character patterns and obtaining a cable accessory character enhanced diagram;
and comparing the cable accessory character enhancement diagram with a corresponding manufacturer template drawing in a preset standard process library, carrying out consistency judgment, and outputting a consistency judgment result of the high-voltage cable accessory drawing.
Specifically, in the embodiment, an image recognition technology, an OCR character recognition technology and a consistency detection algorithm are used, a high-definition scanning device scans a high-voltage cable drawing, a technical protocol and other process drawings by adopting a photoelectric technology and a digital processing technology, the process drawings enter a process library, an electronic version process drawing or a process document is subjected to feature extraction and character recognition and is compared with a factory template drawing solidified in a standard process library, and finally a comparison result is judged by a system according to the algorithm so as to form a comparison report for subsequent examination. And the modification situation on the high-voltage cable accessory process drawings or documents of different manufacturers is analyzed, the deletion, addition and modification parts of the drawings are systematically prompted, the process of comparing and verifying the drawings by design and verification personnel is simplified, the error and leakage phenomena are reduced, and the working efficiency is improved.
The following detailed description of the various steps of the method
1. Feature recognition according to image recognition techniques
In the image recognition technology in the high-voltage cable accessory digital process library, feature extraction and edge detection algorithms such as an LBP operator, an HOG operator and the like are mainly involved. The flow of the whole image recognition part in this embodiment includes image preprocessing (image noise reduction, image enhancement), image restoration (reconstructed image, restored image), image coding and compression, image segmentation (dividing regions of different features), and final recognition.
The LBP operator is proposed by ojala et al in 96 years, is a classical operator with characteristic description, is widely applied to the field of image analysis, and can capture abundant detail information and compress redundant information. But when the radius of such LBP operator is too large, the sensitivity to noise is enhanced. The gradient histogram HOG was proposed by the french researcher Dalal. The HOG algorithm mainly aims to perform gradient calculation on the gray and normalized images, count the gradient information of the images, divide the images into small cell units to form unique HOG characteristics of each drawing, and accordingly achieve comparison of subsequent drawings.
Based on the complex characteristics of the high-voltage cable process drawing, such as contrast, color and density distribution, the method has limitations, and the conventional LBP algorithm is deeply researched in order to obtain better feature extraction and classification results. Aiming at the defects of the original algorithm, the size of an adaptive threshold is determined by utilizing the average difference of the global and local pixel gray levels, so that the adaptive threshold has strong adaptivity to drawing identification, and the LBP algorithm of the adaptive threshold is provided.
The LBP algorithm of the adaptive model used in this embodiment combines the window size with the basic LBP algorithm, and has the performance of adaptive analysis features. The window size is determined by the average intensity difference in the horizontal and vertical directions.
Suppose the image is g (x, y)) The calculated size is (2 x 2)k)×(2*2k) Average intensity value of pixels in the active window of (1):
wherein x is the abscissa of the pixel, y is the ordinate of the pixel, Ak(x, y) is the pixel average intensity value of pixel (x, y) in an active window, g (i, j) is the pixel value with coordinate (i, j) in the image;
for each pixel, the pixel average intensity difference between the windows which do not overlap each other in the horizontal and vertical directions is calculated respectively:
in the formula, Ek，h(x, y) is the average intensity difference of pixels between two non-overlapping windows in the horizontal direction, Ek，v(x, y) is the pixel average intensity difference between two non-overlapping windows in the vertical direction;
for each pixel, enable Ek，h(x, y) or Ek，vThe value of k at which the (x, y) value reaches a maximum (regardless of direction) is used to set the optimum size: sbest(x，y)＝(2*2k)×(2*2k)；
As can be seen from the above, SbestAnd (x, y) is the approximate size of the characteristic primitive of the pixel point with (x, y) as the coordinate. The combination of this size and the LBP algorithm reduces the error of LBP in primitive feature extraction.
2. OCR character recognition
The character recognition process of the picture is a whole set of flow, and comprises picture analysis, preprocessing, character recognition, recognition correction and the like, wherein each step is related to the accuracy of a final recognition result. For example, the clearer the picture to be subjected to character recognition (i.e., the better the preprocessing is done), the better the recognition effect is. At present, the most common and mature Character Recognition technology is Optical Character Recognition (OCR). OCR is a technique for converting characters in a paper document into an image file of black and white dot matrix optically for print characters, and converting the characters in the image into a text format by recognition software for further editing and processing by word processing software.
In the OCR recognition process, the method is mainly divided into four parts:
1) and (5) preprocessing the picture. The module has the functions of preprocessing sample pictures such as size unification, segmentation, graying, binarization and the like, and is prepared for subsequent character recognition.
2) And training a word stock. And carrying out targeted training on characters in the sample picture by using Tesseract so as to improve the identification accuracy.
3) And (5) character recognition. And performing character recognition on the picture by utilizing an open source OCR engine Tesseract. The character recognition of a picture in the system is realized only by calling an image _ to _ string method in a pytesseract library. The details are shown in the following formula,
text＝pytesseract.image_to_string(img，lang＝LANG，config＝′--psm 7--oem3′)
wherein, text is the character content returned after recognition; LANG is a self-trained word stock or Tesseract's own language package; img is the picture after preprocessing.
4) A correction is identified. And correcting the picture characters which are rejected or mistakenly recognized. For grayscale images, a grayscale adjustment, i.e. contrast enhancement, can be performed. Taking 1 gray scale image as an example, experiments show that recognition is rejected before enhancement, and recognition is correct after enhancement, and the enhancement effect is shown in fig. 2.
3. Consistency detection algorithm
Fractal geometry gives mathematical description of some irregular geometric bodies appearing in nature, the essence of the mathematical description is self-similarity, and the principle of image analysis by using fractal theory is to analyze by using fractal dimension characteristics of images. The fractal dimension is intuitively matched with the roughness of the surface of an object, and the roughness of different objects in the drawings is greatly different, so that the fractal dimension can be used as a parameter for judging whether the graphs at corresponding positions in the two drawings are consistent or not.
Because the size of the process drawing of the high-voltage cable accessory is generally larger, the box dimension is used as a calculation mode of the fractal dimension, and the fractal dimension is used for drawing comparison.
When drawings are compared, the drawings are divided into P multiplied by Q areas respectively, the calculation of box pixels is carried out by utilizing a fractal dimension calculation method, judgment is carried out according to reference threshold values and the absolute values of fractal dimension difference values of two drawings, if the absolute values are smaller than the threshold values, the judgment is consistent, otherwise, the judgment is inconsistent. Thereby realizing the final comparison, examination and judgment.
In addition, the standard process library is the key of the method. According to the embodiment, basic information is classified and stored by collecting cable accessory drawings and data parameters of various manufacturers and information needing to be compared in the later period, and a standard process library with powerful use function and huge information amount is designed.
And comparing the processed data information of the cable accessories with the stored information of the standard process library through a consistency detection algorithm, collecting different information, and recording the different information in an analysis report, thereby providing convenience for subsequent auditing work.
The embodiment also provides a high-voltage cable accessory drawing comparison system based on image recognition, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program to execute the steps of the high-voltage cable accessory drawing comparison method based on image recognition.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A high-voltage cable accessory drawing comparison method based on image recognition is characterized by comprising the following steps:
obtaining a high-voltage cable accessory drawing;
performing characteristic identification on the high-voltage cable accessory drawing to obtain a cable accessory characteristic diagram;
performing character recognition on the cable accessory characteristic diagram, enhancing character patterns, and acquiring a cable accessory character enhancement diagram;
and comparing the cable accessory character enhanced drawing with a corresponding manufacturer template drawing in a preset standard process library, carrying out consistency judgment, and outputting a consistency judgment result of the high-voltage cable accessory drawing.
2. The image recognition-based high-voltage cable accessory drawing comparison method as claimed in claim 1, wherein an LBP algorithm is adopted to perform feature recognition on the high-voltage cable accessory drawing.
3. The image recognition-based drawing comparison method for high-voltage cable accessories according to claim 2, wherein the determination of the window size of the LBP algorithm comprises the following steps:
the parameter k is set and initialized, and,
setting an active window of each pixel according to the parameter k, and setting a calculation formula of the pixel average intensity value of the active window of each pixel;
for each pixel, calculating the pixel average intensity difference between two non-overlapping windows of the pixel in the horizontal direction and the vertical direction respectively,
acquiring a k value which can enable the value of the pixel average intensity difference between two non-overlapping windows in the horizontal direction or the pixel average intensity difference between two non-overlapping windows in the vertical direction to reach the maximum for each pixel;
the size of the active window is determined as the window size of the LBP algorithm, based on the determined k value for each pixel.
4. The image recognition-based high-voltage cable accessory drawing comparison method as claimed in claim 3, wherein the calculation expression of the pixel average intensity value is as follows:
wherein x is the abscissa of the pixel, y is the ordinate of the pixel, Ak(x, y) is the pixel average intensity value of pixel (x, y) in an active window, and g (i, j) is the pixel value with coordinate (i, j) in the image.
5. The image recognition-based high-voltage cable accessory drawing comparison method as claimed in claim 4, wherein the pixel average intensity difference E between two non-overlapping windows in the horizontal directionk，hThe computational expression of (x, y) is:
Ek，h(x，y)＝|Ak(x+2k-1，y)-Ak(x-2k-1，y)|
the pixel average intensity difference E between two non-overlapping windows in the vertical directionk，vThe computational expression of (x, y) is:
Ek，v(x，y)＝|Ak(x，y+2k-1)-Ak(x，y-2k-1)|。
6. the image recognition-based high-voltage cable accessory drawing comparison method according to claim 1, wherein character recognition is performed on the cable accessory feature map by an optical character recognition method to enhance character patterns, the optical character recognition method comprises the steps of preprocessing the cable accessory feature map, loading the preprocessed cable accessory feature map into a pre-trained character recognition engine to perform character recognition, and finally performing image enhancement on character recognition results.
7. The method as claimed in claim 6, wherein the character recognition engine employs an open source OCR engine Tesseract.
8. The image-recognition-based high-voltage cable accessory drawing comparison method as claimed in claim 1, wherein the consistency judgment process specifically comprises: dividing the cable accessory character enhancement diagram and the corresponding factory template drawing into a plurality of areas, respectively calculating fractal dimension values of the two corresponding areas, obtaining an absolute value of a fractal dimension difference value, outputting a judgment result that the drawings are consistent if the absolute value of the fractal dimension difference value is smaller than a preset reference threshold, and otherwise, outputting a judgment result that the drawings are inconsistent.
9. The method as claimed in claim 8, wherein if the drawings are determined to be inconsistent, a corresponding region label is output.
10. A high voltage cable accessory drawing comparison system based on image recognition, comprising a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program to execute the steps of the method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110869656.7A CN113591698A (en) | 2021-07-30 | 2021-07-30 | High-voltage cable accessory drawing comparison method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110869656.7A CN113591698A (en) | 2021-07-30 | 2021-07-30 | High-voltage cable accessory drawing comparison method and system based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591698A true CN113591698A (en) | 2021-11-02 |
Family
ID=78252379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110869656.7A Pending CN113591698A (en) | 2021-07-30 | 2021-07-30 | High-voltage cable accessory drawing comparison method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591698A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109858452A (en) * | 2019-02-15 | 2019-06-07 | 滨州建筑工程施工图审查中心 | Architectural drawing automatic comparison method and device |
| CN109978072A (en) * | 2019-04-03 | 2019-07-05 | 青岛伴星智能科技有限公司 | A kind of character comparison method and Compare System based on deep learning |
| CN110599131A (en) * | 2019-09-18 | 2019-12-20 | 国网重庆市电力公司电力科学研究院 | Electric drawing identification and examination method, device and readable storage medium |
| CN111046462A (en) * | 2019-11-27 | 2020-04-21 | 湖南城市学院 | Drawing display system and method for outdoor building design |
| CN111382710A (en) * | 2020-03-12 | 2020-07-07 | 湖南力光信息技术有限公司 | Drawing comparison method based on image recognition |
| CN111639717A (en) * | 2020-06-04 | 2020-09-08 | 网易（杭州）网络有限公司 | Image character recognition method, device, equipment and storage medium |
-
2021
- 2021-07-30 CN CN202110869656.7A patent/CN113591698A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109858452A (en) * | 2019-02-15 | 2019-06-07 | 滨州建筑工程施工图审查中心 | Architectural drawing automatic comparison method and device |
| CN109978072A (en) * | 2019-04-03 | 2019-07-05 | 青岛伴星智能科技有限公司 | A kind of character comparison method and Compare System based on deep learning |
| CN110599131A (en) * | 2019-09-18 | 2019-12-20 | 国网重庆市电力公司电力科学研究院 | Electric drawing identification and examination method, device and readable storage medium |
| CN111046462A (en) * | 2019-11-27 | 2020-04-21 | 湖南城市学院 | Drawing display system and method for outdoor building design |
| CN111382710A (en) * | 2020-03-12 | 2020-07-07 | 湖南力光信息技术有限公司 | Drawing comparison method based on image recognition |
| CN111639717A (en) * | 2020-06-04 | 2020-09-08 | 网易（杭州）网络有限公司 | Image character recognition method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 王佳琳: ""基于图像分割的车牌检测方法研究"", 《CNKI硕士学位论文》, pages 1 - 48 * |
| 王辉，王晗主编: "《基于计算机数字图像处理技术木材表面纹理特征提取和分类识别方法》", 30 June 2020, 北京理工大学出版社, pages: 20 - 24 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086656B (en) | Airport foreign matter detection method, device, computer equipment and storage medium | |
| Raghunandan et al. | Riesz fractional based model for enhancing license plate detection and recognition | |
| US9542752B2 (en) | Document image compression method and its application in document authentication | |
| CN110569341B (en) | Method and device for configuring chat robot, computer equipment and storage medium | |
| US7653244B2 (en) | Intelligent importation of information from foreign applications user interface | |
| CN114004984A (en) | High-voltage cable accessory process library drawing comparison method and system | |
| US20140301608A1 (en) | Chemical structure recognition tool | |
| CN111652233A (en) | Text verification code automatic identification method for complex background | |
| CN112861865A (en) | OCR technology-based auxiliary auditing method | |
| CN110969154A (en) | Text recognition method and device, computer equipment and storage medium | |
| CN110942067A (en) | Text recognition method and device, computer equipment and storage medium | |
| Dergachov et al. | Data pre-processing to increase the quality of optical text recognition systems | |
| CN113139535A (en) | OCR document recognition method | |
| CN113537184A (en) | OCR (optical character recognition) model training method and device, computer equipment and storage medium | |
| CN112633200A (en) | Human face image comparison method, device, equipment and medium based on artificial intelligence | |
| CN116797602A (en) | Surface defect identification method and device for industrial product detection | |
| CN113591698A (en) | High-voltage cable accessory drawing comparison method and system based on image recognition | |
| KR102613387B1 (en) | Apparatus and method for generating image for iris recognition | |
| CN114332915A (en) | Human body attribute detection method and device, computer equipment and storage medium | |
| TWI775038B (en) | Method and device for recognizing character and storage medium | |
| CN112967166A (en) | OpenCV-based automatic image watermark identification processing method and system | |
| Amelia | Age Estimation on Human Face Image Using Support Vector Regression and Texture-Based Features | |
| Chen et al. | A fast skin region detector for colour images | |
| CN117095418B (en) | Table comparison method and device based on picture pixel difference | |
| CN117649358B (en) | Image processing method, device, equipment and storage medium |
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 |