CN111797909B - Pointer type instrument reading method based on machine vision - Google Patents
Pointer type instrument reading method based on machine vision Download PDFInfo
- Publication number
- CN111797909B CN111797909B CN202010571594.7A CN202010571594A CN111797909B CN 111797909 B CN111797909 B CN 111797909B CN 202010571594 A CN202010571594 A CN 202010571594A CN 111797909 B CN111797909 B CN 111797909B
- Authority
- CN
- China
- Prior art keywords
- image
- instrument
- read
- pointer
- meter
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000012545 processing 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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a pointer type pressure instrument reading method based on machine vision, which comprises the following steps: acquiring an instrument standard template image and an instrument image to be read; matching the meter image to be read with the meter standard template image by using a matching algorithm to obtain a corrected meter image to be read; denoising the corrected meter image to be read, performing threshold segmentation on the denoised corrected meter image to be read to obtain a background-removed meter image to be read, and positioning the position of a dial boundary circle in the background-removed meter image to be read; performing expansion operation on the background-removed instrument image to be read to obtain a pointer image; obtaining needle tip coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) The method comprises the steps of carrying out a first treatment on the surface of the According to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) And obtaining the angle position of the pointer, and obtaining the reading of the instrument according to the angle position of the pointer. Compared with the prior art, the meter reading is more accurate.
Description
Technical Field
The invention relates to the field of image monitoring and processing systems, in particular to a pointer instrument reading method based on machine vision.
Background
In the factory verification link of the pointer pressure instrument, verification and adjustment of reading errors of the instrument are required. At present, the pressurization of the instrument is mainly carried out manually, the current reading of the instrument is read through human eye observation, the numerical value of the high-precision digital instrument is compared, and the error of the measured instrument is calculated. The manual mode is used for factory verification of the pointer pressure instrument, the efficiency is low, the accuracy is low, especially, the pointer pressure instrument is continuously interpreted for a long time, visual fatigue is easily caused, and errors are caused. In addition, the instrument is not screwed in place during fixed installation, a camera for collecting an instrument image is not opposite to the instrument, so that the collecting camera cannot better collect an image of the instrument panel, and a certain attitude error exists in the collected instrument image. How to collect the high-efficiency and accurate instrument image of the instrument generating the attitude error and identify the reading of the instrument is a key for guaranteeing the delivery high-efficiency and accurate verification of the pointer type pressure instrument.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a pointer type meter reading method based on machine vision.
The aim of the invention can be achieved by the following technical scheme:
a machine vision based pointer meter reading method, the method comprising the steps of:
step S1: acquiring an instrument standard template image and an instrument image to be read;
step S2: matching the meter image to be read with the meter standard template image by using a matching algorithm to obtain a corrected meter image to be read;
step S3: denoising the corrected meter image to be read, performing threshold segmentation on the denoised corrected meter image to be read to obtain a background-removed meter image to be read, and positioning the position of a dial boundary circle in the background-removed meter image to be read;
step S4: performing expansion operation on the background-removed instrument image to be read to obtain a pointer image;
step S5: obtaining needle tip coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 )；
Step S6: according to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) And obtaining the angle position of the pointer, and obtaining the reading of the instrument according to the angle position of the pointer.
The step S2 uses a feature matching algorithm of a GMS grid movement statistics strategy to match the meter image to be read with the meter standard template image, and the process comprises the following steps:
step S21: detecting characteristic points of a standard template image of the instrument and an image of the instrument to be read and calculating descriptors;
step S22: matching the characteristic points and the calculation descriptors of the instrument standard template image with the characteristic points and the calculation descriptors of the instrument image to be read respectively through a BF violent matching algorithm;
step S23: dividing the standard template image of the instrument and the image of the instrument to be read into a plurality of grids respectively, reserving correctly matched characteristic points, and calculating to obtain a projection matrix between the standard template image of the instrument and the image of the instrument to be read;
step S24: and obtaining an image of the instrument to be read by correction according to the projection matrix.
And the feature points which are correctly matched are feature points with the number of surrounding correct matching points being larger than a threshold value.
And in the step S3, denoising the corrected instrument image to be read by using median filtering.
In the step S3, an OTSU threshold segmentation algorithm is used for threshold segmentation of the corrected instrument image to be read after denoising.
After the background-removed to-be-read number instrument image is obtained in the step S3, edge detection is carried out on the background-removed to-be-read number instrument image by using a Canny operator, then circle detection is carried out by using a Hough transformation algorithm, a dial boundary circle is obtained, and the position of the dial boundary circle is located in the background-removed to-be-read number instrument image.
The process of obtaining the needle point coordinates in the pointer image in the step S5 includes:
step S51: obtaining a pointer position predicted value;
step S52: searching a pointer edge side line around the pointer position predicted value of the pointer image;
step S53: and obtaining the needle point coordinates by utilizing the edge side line.
In the step S6, according to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) The calculation formula for obtaining the pointer angle position theta is as follows:
in the step S6, a calculation formula for obtaining the meter reading N according to the pointer angle position is as follows:
wherein θ is the pointer angle position, θ 0 For the minimum angular position of the meter, θ max For the maximum angular position of the meter, N 0 For minimum meter reading, N max Maximum value for meter reading.
And the instrument standard template image and the instrument image to be read are shot through an industrial camera.
Compared with the prior art, the invention has the following advantages:
(1) The posture of the instrument to be measured is corrected by using a template matching algorithm, so that the measurement error caused by the instrument posture error is reduced, and the recognition accuracy of the algorithm is improved.
(2) The feature matching algorithm of the GMS grid movement statistics strategy is utilized, the feature point pairs which are accurately matched are reserved, the projection matrix between the instrument to be read and the standard template instrument is accurately calculated, and the error of instrument reading is reduced.
(3) After the dial boundary circle is identified, the effective area is determined, and elements affecting the identification pointer such as the instrument frame and the dial can be deleted, so that the calculation cost of the side line detection of the edge of the pointer is reduced.
(4) According to the specificity of pointer instrument detection, pointer edge side line detection is carried out in a certain pressure range (namely around a pointer position predicted value), instead of straight line detection on the whole image, the speed of pointer edge side line detection is greatly reduced, and the algorithm running speed is improved.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is an image of a standard template of an instrument of the present invention;
FIG. 3 is a graph of the matching result of the present invention;
FIG. 4 is an OTSU threshold segmentation diagram of the present invention;
FIG. 5 is a diagram of dial bounding circle detection of the present invention;
FIG. 6 is a pointer image of the present invention;
FIG. 7 is a diagram illustrating a pointer edge side detect according to the present invention;
FIG. 8 is a chart of pointer angular position versus meter reading conversion according to the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
Examples
The embodiment provides a pointer type pressure meter reading method based on machine vision, as shown in fig. 1, comprising the following steps:
(1) Placing a standard instrument on a plane, polishing the instrument by using an annular low-angle light source, and collecting an instrument standard template image by using an industrial camera, wherein the instrument standard template image is shown in fig. 2; placing the instrument to be read in the same illumination environment as the standard instrument, and acquiring an image of the instrument to be read by using an industrial camera;
(2) Template matching is carried out by using a feature matching algorithm of a GMS grid motion statistics strategy, and the flow is as follows:
a. detecting characteristic points of a standard template image of the instrument and an image of the instrument to be read and calculating descriptors;
b. matching the characteristic points and the calculation descriptors of the instrument standard template image with the characteristic points and the calculation descriptors of the instrument image to be read respectively through a BF violent matching algorithm;
c. dividing a standard template image of the instrument and an image of the instrument to be read into a plurality of grids respectively;
d. judging whether the feature points are correctly matched or not by calculating the number of correct matching points near the feature points matched by the BF violent matching algorithm and comparing the number with a set threshold value, reserving the correctly matched feature points, and removing the incorrectly matched feature points, as shown in figure 3;
e. selecting 4 pairs of correctly matched characteristic point pairs to obtain a quaternary one-time equation, calculating to obtain a projection matrix between the standard template image of the instrument and the image of the instrument to be read, and correcting the posture of the image of the instrument to be read through the projection matrix to obtain the image of the instrument to be read;
(3) Performing median filtering on the corrected meter image to be read to remove noise interference; performing threshold segmentation on the instrument image to be read by using an OTSU threshold segmentation algorithm, and removing the instrument panel background as shown in FIG. 4; and (3) carrying out edge detection on the to-be-read instrument image with the background removed by using a Canny operator, then carrying out circle detection by using a Hough transformation algorithm, starting detection from the circle with the largest radius, obtaining a dial boundary circle, and positioning the position of the dial boundary circle, as shown in fig. 5.
(4) And expanding a cross-shaped area with the size of 7 multiplied by 7 on the to-be-read number instrument image with the background removed and the dial boundary circle positioned, removing various interference straight lines in the instrument panel, and only keeping a pointer image, as shown in fig. 6.
(5) The method comprises the steps of detecting the side line of the edge of a pointer, wherein the side line of the edge of the pointer is detected to have certain specificity, the current reading of the pointer is provided by a standard controllable pressure generator, a pressure generating scheme is provided according to the type of the meter, and the current pointer position of the meter to be read is near the provided pressure value. The pointer edge side line detection is carried out according to the prior knowledge, and the specific steps are as follows:
a. obtaining a predicted value of the current pointer position according to the current pressure value provided by the standard controllable pressure generator, wherein the predicted value is 17MPa, the instrument error requirement is within 1MPa, and the pointer edge side line detection is carried out on the instrument pointer between 16MPa and 18 MPa;
b. if the pointer edge side line is not found in the current interval, the pointer edge side line search is performed in the range of 15-16 MPa and 18-19 MPa, as shown in FIG. 7;
c. after finding the pointer edge side line, the needle point coordinate (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 )；
(6) According to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) The angular position of the pointer is obtained and the meter reading is obtained from the angular position of the pointer, as shown in fig. 8.
According to the needle point coordinates (x 1 ,y 1 ) Sum circleHeart coordinates (x) 2 ,y 2 ) The calculation formula for obtaining the pointer angle position theta is as follows:
the calculation formula for obtaining the meter reading N according to the pointer angle position is as follows:
wherein θ is the pointer angle position, θ 0 For the minimum angular position of the meter, θ max For the maximum angular position of the meter, N 0 For minimum meter reading, N max Maximum value for meter reading.
Claims (1)
1. A machine vision based pointer meter reading method, comprising the steps of:
step S1: acquiring an instrument standard template image and an instrument image to be read;
step S2: matching the meter image to be read with the meter standard template image by using a matching algorithm to obtain a corrected meter image to be read;
step S3: denoising the corrected meter image to be read, performing threshold segmentation on the denoised corrected meter image to be read to obtain a background-removed meter image to be read, and positioning the position of a dial boundary circle in the background-removed meter image to be read;
step S4: performing expansion operation on the background-removed instrument image to be read to obtain a pointer image;
step S5: obtaining needle tip coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 )；
Step S6: according to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) Obtaining the angle position of the pointer, and obtaining the reading of the instrument according to the angle position of the pointer；
After the background-removed to-be-read number instrument image is obtained in the step S3, edge detection is carried out on the background-removed to-be-read number instrument image by using a Canny operator, then circle detection is carried out by using a Hough transformation algorithm, a dial boundary circle is obtained, and the position of the dial boundary circle is positioned in the background-removed to-be-read number instrument image;
the process of obtaining the needle point coordinates in the pointer image in the step S5 includes:
step S51: obtaining a pointer position predicted value;
step S52: searching a pointer edge side line around the pointer position predicted value of the pointer image;
step S53: obtaining a needle point coordinate by utilizing an edge side line;
the step S2 uses a feature matching algorithm of a GMS grid movement statistics strategy to match the meter image to be read with the meter standard template image, and the process comprises the following steps:
step S21: detecting characteristic points of a standard template image of the instrument and an image of the instrument to be read and calculating descriptors;
step S22: matching the characteristic points and the calculation descriptors of the instrument standard template image with the characteristic points and the calculation descriptors of the instrument image to be read respectively through a BF violent matching algorithm;
step S23: dividing the standard template image of the instrument and the image of the instrument to be read into a plurality of grids respectively, reserving correctly matched characteristic points, and calculating to obtain a projection matrix between the standard template image of the instrument and the image of the instrument to be read;
step S24: obtaining an image of the instrument to be read through correction according to the projection matrix;
the feature points which are correctly matched are feature points with the number of surrounding correct matching points being larger than a threshold value;
in the step S3, denoising the corrected meter image to be read by using median filtering;
in the step S3, an OTSU threshold segmentation algorithm is used for carrying out threshold segmentation on the corrected instrument image to be read after denoising;
in the step S6, according to the needle point coordinates (x 1 ,y 1 ) And center coordinates (x) 2 ,y 2 ) The calculation formula for obtaining the pointer angle position theta is as follows:
in the step S6, a calculation formula for obtaining the meter reading N according to the pointer angle position is as follows:
wherein θ is the pointer angle position, θ 0 For the minimum angular position of the meter, θ max For the maximum angular position of the meter, N 0 For minimum meter reading, N max Maximum value of meter readings;
and the instrument standard template image and the instrument image to be read are shot through an industrial camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010571594.7A CN111797909B (en) | 2020-06-22 | 2020-06-22 | Pointer type instrument reading method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010571594.7A CN111797909B (en) | 2020-06-22 | 2020-06-22 | Pointer type instrument reading method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111797909A CN111797909A (en) | 2020-10-20 |
| CN111797909B true CN111797909B (en) | 2024-03-29 |
Family
ID=72804487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010571594.7A Active CN111797909B (en) | 2020-06-22 | 2020-06-22 | Pointer type instrument reading method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797909B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549814A (en) * | 2022-01-25 | 2022-05-27 | 福建和盛高科技产业有限公司 | Instrument reading identification method based on yolox detection |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009152418A1 (en) * | 2008-06-13 | 2009-12-17 | University Of Tennessee Research Foundation | Passive microwave assessment of human body core to surface temperature gradients and basal metabolic rate |
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
| CN105913095A (en) * | 2016-05-17 | 2016-08-31 | 杭州申昊科技股份有限公司 | Instrument recognition method for transformer substation patrol inspection robot |
| CN107358237A (en) * | 2017-07-21 | 2017-11-17 | 东南大学 | A kind of more instrument board automatic reading methods for going environmental disturbances |
| CN108491838A (en) * | 2018-03-08 | 2018-09-04 | 南京邮电大学 | Pointer-type gauges registration read method based on SIFT and HOUGH |
| CN108921176A (en) * | 2018-06-22 | 2018-11-30 | 河海大学常州校区 | A kind of pointer instrument positioning and recognition methods based on machine vision |
| CN109029520A (en) * | 2018-06-22 | 2018-12-18 | 杭州摩焕科技有限公司 | A kind of external read out instrument monitoring system based on infrared transmitting tube and reception pipe array |
| CN109034170A (en) * | 2018-07-18 | 2018-12-18 | 东南大学 | A kind of round readings of pointer type meters method of switch cubicle detection device |
| CN109544628A (en) * | 2018-11-23 | 2019-03-29 | 福州大学 | A kind of the accurate reading identifying system and method for pointer instrument |
| CN109740616A (en) * | 2019-01-04 | 2019-05-10 | 山东交通学院 | A method of double pointer meters automatic readings are realized using computer vision |
| CN110543878A (en) * | 2019-08-07 | 2019-12-06 | 华南理工大学 | pointer instrument reading identification method based on neural network |
| CN110807458A (en) * | 2019-10-24 | 2020-02-18 | 深圳市嘉繁科技有限公司 | Automatic reading method for pointer instrument |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4913911B1 (en) * | 2011-02-16 | 2012-04-11 | パナソニック株式会社 | Image processing apparatus and document reading system having the same |
-
2020
- 2020-06-22 CN CN202010571594.7A patent/CN111797909B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009152418A1 (en) * | 2008-06-13 | 2009-12-17 | University Of Tennessee Research Foundation | Passive microwave assessment of human body core to surface temperature gradients and basal metabolic rate |
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
| CN105913095A (en) * | 2016-05-17 | 2016-08-31 | 杭州申昊科技股份有限公司 | Instrument recognition method for transformer substation patrol inspection robot |
| CN107358237A (en) * | 2017-07-21 | 2017-11-17 | 东南大学 | A kind of more instrument board automatic reading methods for going environmental disturbances |
| CN108491838A (en) * | 2018-03-08 | 2018-09-04 | 南京邮电大学 | Pointer-type gauges registration read method based on SIFT and HOUGH |
| CN108921176A (en) * | 2018-06-22 | 2018-11-30 | 河海大学常州校区 | A kind of pointer instrument positioning and recognition methods based on machine vision |
| CN109029520A (en) * | 2018-06-22 | 2018-12-18 | 杭州摩焕科技有限公司 | A kind of external read out instrument monitoring system based on infrared transmitting tube and reception pipe array |
| CN109034170A (en) * | 2018-07-18 | 2018-12-18 | 东南大学 | A kind of round readings of pointer type meters method of switch cubicle detection device |
| CN109544628A (en) * | 2018-11-23 | 2019-03-29 | 福州大学 | A kind of the accurate reading identifying system and method for pointer instrument |
| CN109740616A (en) * | 2019-01-04 | 2019-05-10 | 山东交通学院 | A method of double pointer meters automatic readings are realized using computer vision |
| CN110543878A (en) * | 2019-08-07 | 2019-12-06 | 华南理工大学 | pointer instrument reading identification method based on neural network |
| CN110807458A (en) * | 2019-10-24 | 2020-02-18 | 深圳市嘉繁科技有限公司 | Automatic reading method for pointer instrument |
Non-Patent Citations (10)
| Title |
|---|
| OpenCV-Based Automatic Detection System for Automobile Meter;Ze Long Hao等;《Applied Mechanics and Materials》;20140831;第615卷;149-152 * |
| 优化栅格移动统计的图像匹配算法;贾强汉等;《激光与光电子学进展》;第57卷(第12期);摘要 * |
| 基于图像处理的指针式温湿度计读数识别方法;徐宙等;《国外电子测量技术》;第38卷(第7期);第3节 * |
| 基于机器视觉的圆形指针式仪表自动读数识别关键技术研究;韩绍超;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20190215(第2期);I138-1295 * |
| 基于机器视觉的指针式仪表示数识别方法研究;童伟圆等;《计算机测量与控制》;20180325;第26卷(第3期);162-166 * |
| 基于深度学习的指针式仪表检测与识别研究;徐发兵等;《高技术通讯》;20191231;第29卷(第12期);1206-1215 * |
| 徐宙等.基于图像处理的指针式温湿度计读数识别方法.《国外电子测量技术》.2019,第38卷(第7期),第3节. * |
| 改进ORB与Hough变换的指针式仪表识读方法;高建龙等;《计算机工程与应用》;第54卷(第23期);第3.4、4.1、4.3、5.3节，图3 * |
| 贾强汉等.优化栅格移动统计的图像匹配算法.《激光与光电子学进展》.2019,第57卷(第12期),摘要. * |
| 高建龙等.改进ORB与Hough变换的指针式仪表识读方法.《计算机工程与应用》.2019,第54卷(第23期),第3.4、4.1、4.3、5.3节，图3. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111797909A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110189314B (en) | Automobile instrument panel image positioning method based on machine vision | |
| CN114549835B (en) | Pointer instrument correction identification method and device based on deep learning | |
| CN112686920A (en) | Visual measurement method and system for geometric dimension parameters of circular part | |
| CN110298840B (en) | Yarn defect detection method based on image | |
| CN110189375B (en) | Image target identification method based on monocular vision measurement | |
| CN110111330B (en) | Mobile phone screen detection method | |
| CN113706537A (en) | Irregular workpiece detection method based on machine vision | |
| CN111062940A (en) | Screw positioning and identifying method based on machine vision | |
| CN106599890A (en) | Transformer substation patrol robot digital type instrument identification algorithm | |
| CN111652069B (en) | Target identification and positioning method for mobile robot | |
| CN108709500B (en) | Circuit board element positioning and matching method | |
| CN117250208B (en) | Machine vision-based nano-imprint wafer defect accurate detection system and method | |
| CN111797909B (en) | Pointer type instrument reading method based on machine vision | |
| CN109034170A (en) | A kind of round readings of pointer type meters method of switch cubicle detection device | |
| CN107388991A (en) | A kind of more fillet axial workpiece radius of corner measuring methods in end face | |
| CN116503316A (en) | Chip defect measurement method and system based on image processing | |
| CN111882569A (en) | Machine vision-based pointer type pressure gauge automatic calibrator indication value reading method | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN111815580B (en) | Image edge recognition method and small module gear module detection method | |
| CN113607058B (en) | Straight blade size detection method and system based on machine vision | |
| CN107748897B (en) | Large-size curved part profile quality detection method based on pattern recognition | |
| JP2008152555A (en) | Image recognition method and image recognition device | |
| CN112734779A (en) | Dot calibration plate edge sub-pixel detection method | |
| CN110991233A (en) | Automatic reading method for pointer type pressure gauge | |
| CN114926417B (en) | Microscopic imaging detection method and system for weak scratches on surface of high-density flexible FPC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |