CN113378814A - Method and system for automatically identifying instrument - Google Patents
Method and system for automatically identifying instrument Download PDFInfo
- Publication number
- CN113378814A CN113378814A CN202110643925.8A CN202110643925A CN113378814A CN 113378814 A CN113378814 A CN 113378814A CN 202110643925 A CN202110643925 A CN 202110643925A CN 113378814 A CN113378814 A CN 113378814A
- Authority
- CN
- China
- Prior art keywords
- center
- pointer
- acquiring
- image
- scale
- 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
Images
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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method and a system for automatically identifying a meter, belonging to the technical field of image processing, wherein the method comprises the following steps: collecting an image of the instrument; carrying out distortion correction on the image; acquiring the circle center of a dial plate in the image; acquiring a pointer position based on a Hough transform, annular template matching or radius gray level matching method; positioning the scale marks of the dial plate to obtain the positions of the scale marks; obtaining the measuring range of the instrument; and calculating the reading of the instrument according to the pointer, the circle center, the measuring range and the scale mark. The center, the pointer, the measuring range and the scale mark of the instrument are identified through an image processing technology of machine vision, and the counting of the instrument is calculated to replace manual counting, so that the identification efficiency and the accuracy are improved, and manpower and material resources are saved; and reading errors caused by matching errors of the instrument template are avoided.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a system for automatically identifying a meter.
Background
Mechanical instruments such as pointer instruments are widely applied to various processing fields such as petroleum and coal, have the advantages of strong anti-interference performance, dust prevention, water prevention, long service life and the like, and are particularly preferred for fireproof and explosion-proof occasions and occasions with severe environment such as electric power, petroleum, chemical industry and the like.
At present, instruments for measuring parameters such as drilling fluid friction force, mud pump pressure, riser pressure, drilling pressure and the like of a drilling crew at a well site are all analog pointer instruments, and operators need to read and record current numerical values at regular time, so that on one hand, errors are easy to occur and reading errors are generated; on the other hand, a large amount of manpower and material resources are needed to be consumed, the reading efficiency is low, and the misjudgment rate is high.
At present, automatic identification of an instrument needs preselection to establish an instrument model library, collected images are matched with instrument models to identify the type of the instrument, and then reading is carried out, but the types of the instruments are more, characteristic values are fewer, and the method is easy to cause matching errors in the automatic template matching process, so that reading errors occur, and generally, a template needs to be corrected manually, and the efficiency is lower.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a method and a system for automatically identifying a meter, which calculate the reading of the meter by reading a pointer, a circle center, a measuring range and a scale mark, avoid the occurrence of template matching errors and improve the accuracy of the reading.
The invention discloses a method for automatically identifying an instrument, which comprises the following steps: collecting an image of the instrument; carrying out distortion correction on the image; acquiring the circle center of a dial plate in the image; acquiring a pointer position based on a Hough transform, annular template matching or radius gray level matching method; positioning the scale marks of the dial plate to obtain the positions of the scale marks; obtaining the measuring range of the instrument; and calculating the reading of the instrument according to the pointer, the circle center, the measuring range and the scale mark.
Preferably, the center of the dial is obtained through hough transform.
Preferably, the method for obtaining the center of the dial through hough transform includes: calculating gradient vectors of non-zero pixel points in multiple directions; voting the intersection points of the gradient vectors, and selecting the point with the highest vote number as a circle center; zooming the radius based on the circle center to obtain a point passing through each circle; based on the number of the points, a dial circle is screened out, and the dial circle comprises a dial circle center.
Preferably, the method for acquiring the center of the dial comprises: calculating the longitudinal gradient of the image to obtain a longitudinal gradient map; after the binarization operation is carried out on the longitudinal gradient map, extracting a contour; taking three points from the contour as a circle at random for multiple times, wherein the circle comprises a circle center and a radius; and taking the average position of the circle center as the circle center of the dial.
Preferably, the method of acquiring the position of the scale mark comprises: acquiring the outline of an image;
screening the contour through screening conditions to obtain a scale contour,
the screening conditions include: the point density of the contour is greater than a first threshold; the aspect ratio is 1:2-1: 5; the center of the minimum outline bounding rectangle is used as the outline center, and the distance between the outline center and the circle center is larger than a second threshold value; the difference between the inclination angle of the minimum outline rectangle and the inclination angle of the center of the outline and the circle center connecting line is smaller than a third threshold value;
taking the connecting line of the center of the scale outline and the circle center as a scale mark;
acquiring a minimum included angle between the scale marks according to the angle of the scale marks;
and completing or redrawing the scale mark according to the minimum included angle, and acquiring the position of the scale mark.
Preferably, the method for obtaining the pointer position based on the circular template matching includes: acquiring a matching area of the image; establishing a template pointer by taking the circle center of the matching area as a center, traversing the template pointer in an anticlockwise direction, and generating a sub-graph by rotating for each angle; calculating the similarity between the matching region and the subgraph, and acquiring the most similar subgraph; and taking the template pointer of the most similar subgraph as the pointer of the image, and acquiring the position of the pointer.
Preferably, the method for obtaining the pointer position based on radius gray scale matching includes: extracting the gray value of the matching area in the image; establishing a scanning line, and rotating the scanning line by taking the circle center as the center; sequentially calculating the sum of the gray values of the scanning lines in the radial direction; and taking the scanning line at the maximum value of the sum of the gray values as a pointer and acquiring the position of the pointer.
Preferably, the formula for calculating the meter reading is:
wherein, data is the reading, R is the measuring range, beta is the pointer angle, alpha is the included angle of the starting position and the ending position of the scale mark.
Preferably, the method of obtaining the range of the meter comprises: reading characters and text boxes thereof in the image based on an OCR technology; screening numerical values in the characters; reading the distance between the center of the numerical text box and the circle center, and voting the distance; acquiring the diameter of a scale text box according to the voting data; acquiring a scale value according to the diameter of the text box; obtaining the measuring range of the instrument according to the scale value; and presetting a dictionary of a meter unit, and matching the numerical values in the dictionary to obtain a reading unit.
The invention also provides a system for realizing the method, which comprises an acquisition module, a preprocessing module, a circle identification module, a pointer identification module, a scale mark identification module, a measuring range module and a reading module, wherein the acquisition module is used for acquiring the image of the instrument; the preprocessing module is used for carrying out distortion correction on the image; the circle identification module is used for acquiring the circle center of the dial plate in the image; the pointer identification module is used for acquiring the position of a pointer based on a Hough transform, annular template matching or radius gray matching method; the scale mark identification module is used for positioning the scale marks of the dial plate to obtain the positions of the scale marks; the measuring range module is used for obtaining the measuring range of the instrument; the reading module is used for calculating the reading of the instrument according to the positions of the pointer, the circle center, the measuring range and the scale mark.
Compared with the prior art, the invention has the beneficial effects that: the center, the pointer, the measuring range and the scale mark of the instrument are identified through an image processing technology of machine vision, and the counting of the instrument is calculated to replace manual counting, so that the identification efficiency and the accuracy are improved, and manpower and material resources are saved; and reading errors caused by matching errors of the instrument template are avoided.
Drawings
FIG. 1 is a flow chart of a method of automatic meter identification of the present invention;
FIG. 2 is a flow chart of a method for obtaining the center of a circle of a dial by Hough transform;
FIG. 3 is a flow chart of another method for obtaining the center of a circle of a dial;
FIG. 4 is a flow chart of a method of obtaining a position of a scale;
FIG. 5 is a flowchart of a method for obtaining a pointer location based on circumferential template matching;
FIG. 6 is a flowchart of a method for obtaining pointer position based on radius grayscale matching;
FIG. 7 is a flow chart of a method of obtaining a range of a meter from an image;
FIG. 8 is a logical block diagram of the system of the present invention;
FIG. 9 is a schematic view of a meter dial;
fig. 10 is a schematic diagram of the effect of dial image screening.
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. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
a method for automatic identification of a meter, as shown in fig. 1, the method comprising:
step 101: an image of the meter is collected. The camera can be installed in front of the instrument to collect images of the instrument, and the camera can be carried to transmit the images to the background system in a wireless transmission mode after the images are shot.
Step 102: and carrying out distortion correction on the image.
The image captured by the camera is not usually a front view, so that the image needs to be preprocessed, such as but not limited to, distortion correction, and the preprocessing may further include one or a combination of the following: image scaling, graying, denoising, smoothing, dilation, and erosion.
Step 103: and acquiring the circle center of the dial plate in the image. The center of a circle of the dial can be obtained through Hough transformation.
Step 104: and acquiring the position of the pointer based on a Hough transform, annular template matching or radius gray matching method. The hough transform detection straight line is the prior art, and is not described in detail in the application.
Step 105: and positioning the scale marks of the dial plate to obtain the positions of the scale marks.
Step 106: and acquiring the measuring range of the instrument. The image can be set manually or read from the image.
Step 107: and calculating the reading of the instrument according to the pointer, the circle center, the measuring range and the scale mark.
According to the invention, the circle center, the pointer, the measuring range and the scale mark of the instrument are identified through an image processing technology of machine vision, and the counting of the instrument is calculated to replace manual counting, so that the identification efficiency and accuracy are improved, and manpower and material resources are saved; reading errors caused by matching errors of the instrument template are avoided; the acquired images can be sent to a remote background for reading.
As shown in fig. 2, the method for obtaining the center of a dial by hough transform includes:
step 201: and calculating gradient vectors of the nonzero pixel points in all directions. For example, the gradient vectors in the horizontal and vertical directions, the gradient vectors of the pixel points on a circle will intersect at a point.
Step 202: and voting the intersection points of the gradient vectors, and selecting the point with the highest vote number as a circle center.
Step 203: and scaling the radius based on the circle center, and calculating a point passing through each circle.
Step 204: based on the number of the points, a dial circle is screened out, and the dial circle comprises a dial circle center. For a meter provided with a scale mark inscribed arc, the number of points passed by a dial circle is usually the largest, while for a meter not provided with an inscribed arc, a plurality of circles can be recognized to have the same or similar number of points.
As shown in fig. 3, the present invention further provides another method for obtaining the center of a dial:
step 301: and calculating the longitudinal gradient of the image to obtain a longitudinal gradient map.
Step 302: and after the binarization operation is carried out on the longitudinal gradient map, extracting the contour.
Step 304: and taking three points from the contour at random for a plurality of times to form a circle, wherein the circle comprises a circle center and a radius. The horizontal distances of the three points may have a certain span, for example, the horizontal distances differ by 10 points.
Step 305: and taking the average position of the circle center as the circle center of the dial. But not limited to, the center of the dial or the circle of the dial can be determined by voting. The number of points passed by the dial circle is the largest, so that the probability of obtaining the dial circle by the circle obtained by any three points is also the largest, and the error range of the circle center can be set, such as 5 points.
As shown in fig. 4, in step 105, the method for acquiring the position of the scale mark includes:
step 401: the contour of the image is acquired. The method for obtaining the image contour is as described in steps 301 and 302.
Step 402: and screening the contour according to the point density, the aspect ratio, the distance between the center of the contour and the circle center and the angle of the contour to obtain the scale contour. The screening conditions are as follows: the point density of the outline is greater than a first threshold value, the aspect ratio is 1:2-1:5, the center of the minimum outline bounding rectangle is used as the outline center, the distance between the outline center and the circle center is greater than a second threshold value, and the difference between the inclination angle of the minimum outline bounding rectangle and the inclination angle of the connecting line between the outline center and the circle center is less than a third threshold value.
The number of dots and/or area of the outline is greater than the blank area of the dial, so that a first threshold value of dot density can be set, for example 10 dots/mm2Thereby playing a role of noise reduction; the scale marks of the dial have certain aspect ratio, but the aspect ratio is different according to the different types of the dial; the distance between the contour center and the circle center is larger than a second threshold value, such as larger than 50 points, so that information such as the type and the type of the instrument in the inner circle of the dial plate is filtered; the connecting line between the center of the outline and the center of the circle is taken as a pre-scale line, the minimum circumscribed rectangle of the outline should point to the center of the circle, i.e. the inclination angles of the minimum circumscribed rectangle and the center of the circle should be the same, and the third threshold is usually set to ± 0.5 degree in consideration of the error, but is not limited thereto.
Step 403: and taking the connecting line of the center of the scale outline and the circle center as a scale mark. In one embodiment, the effect graph of the tick marks is shown in FIG. 10.
Step 404: and acquiring the minimum included angle between the scale marks according to the angle of the scale marks.
Step 405: and completing or redrawing the scale mark according to the minimum included angle, and acquiring the position of the scale mark. Wherein the tick marks comprise a start tick mark and an end tick mark.
As shown in fig. 5, in step 104, the method for obtaining the pointer position based on the circular template matching includes:
step 501: a matching region of the image is acquired. The matching area of the image can be obtained by cutting, for example, a fan-shaped matching area is obtained by using a circle center as a reference and using a certain single path, and a pointer is reserved in the matching area.
Step 502: and establishing a template pointer by taking the circle center of the matching area as a center, traversing the template pointer in a counterclockwise direction, and generating a sub-graph by rotating for each angle.
Step 503: and calculating the similarity of the matching region and the subgraph, and acquiring the most similar subgraph.
Step 504: and taking the template pointer of the most similar subgraph as the pointer of the image, and acquiring the position of the pointer.
Namely, pictures of template pointers of multiple angles are established, and when the template pointers coincide with the pointers to be detected, the similarity between the sub-picture and the equal matching area is the highest.
As shown in fig. 6, in step 104, the method for obtaining the pointer position based on the radius grayscale matching includes:
step 601: and extracting the gray value of the matching area in the image.
Step 602: establishing a scanning line, and rotating the scanning line by taking the circle center as the center.
Step 603: and sequentially calculating the sum of the gray values of the scanning lines in the radial direction.
Step 604: and taking the scanning line at the maximum value of the sum of the gray values as a pointer and acquiring the position of the pointer.
For example, each time the rotation is 1 degree, a plurality of second sub-graphs are obtained, and the gray value of the radial direction of the scanning line of each second sub-graph is calculated. But is not limited thereto, the angle of each rotation may be set according to the type of meter, the type of pointer, and the accuracy of the meter.
In step 107, the meter reading formula is calculated as:
wherein, data is the reading, R is the measuring range, beta is the pointer angle, alpha is the included angle of the starting position and the ending position of the scale mark.
As shown in fig. 7, in step 106, the method for obtaining the range of the meter from the image includes:
step 701: based on OCR technology, the text and its text box in the image are read. The OCR technology is used to recognize characters in an image, and is not described in detail in the present invention for the prior art.
Step 702: and screening the numerical values in the characters. The numerical values in the dial can be scale marks, serial numbers, units.
Step 703: and reading the distance between the center of the numerical text box and the circle center, and voting the distance. The scale marks are generally located inside or outside the scale lines and distributed around the circular arc, and the number of the scale marks is more than the serial number unit, so that the scale marks are determined by voting.
Step 704: and acquiring a scale text box and the diameter thereof according to the voting data.
Step 705: and acquiring the scale text box and the scale value thereof according to the diameter of the text box. As shown in fig. 9, for a dual-scale dashboard, there are two sizes of text box diameters, with the scale values being categorized or filtered by text box diameter. The scale value is identified by OCR techniques.
Step 706: and obtaining the measuring range of the instrument according to the scale value. The range includes a maximum reading and a minimum reading.
Step 707: and presetting a dictionary of an instrument unit, and matching the characters in the dictionary to obtain the units of the characters in the reading or scale text box. Such as preset units V, × 1000RPM, degree or MP, etc.
The invention also provides a system for realizing the method, as shown in fig. 8, comprising an acquisition module 1, a preprocessing module 2, a circle identification module 3, a pointer identification module 4, a scale mark identification module 5, a measuring range module 6 and a reading module 7,
the acquisition module 1 is used for acquiring an image of the instrument;
the preprocessing module 2 is used for carrying out distortion correction on the image;
the circle identification module 3 is used for acquiring the circle center of the dial plate in the image;
the pointer identification module 4 is used for acquiring the position of a pointer based on a Hough transform, annular template matching or radius gray matching method;
the scale mark identification module 5 is used for positioning the scale marks of the dial plate to obtain the positions of the scale marks;
the measuring range module 6 is used for obtaining the measuring range of the instrument;
the reading module 7 is used for calculating the reading of the instrument according to the positions of the pointer, the circle center, the measuring range and the scale mark.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for automatic identification of a meter, the method comprising:
collecting an image of the instrument;
carrying out distortion correction on the image;
acquiring the circle center of a dial plate in the image;
acquiring a pointer position based on a Hough transform, annular template matching or radius gray level matching method;
positioning the scale marks of the dial plate to obtain the positions of the scale marks;
obtaining the measuring range of the instrument;
and calculating the reading of the instrument according to the pointer, the circle center, the measuring range and the scale mark.
2. The method for automatically identifying meters in claim 1, wherein the center of the dial is obtained by Hough transform.
3. The method for automatically identifying the instrument as claimed in claim 2, wherein the method for obtaining the center of the dial by Hough transform comprises the following steps:
calculating gradient vectors of non-zero pixel points in multiple directions;
voting the intersection points of the gradient vectors, and selecting the point with the highest vote number as a circle center;
zooming the radius based on the circle center to obtain a point passing through each circle;
based on the number of the points, a dial circle is screened out, and the dial circle comprises a dial circle center.
4. The method for automatically identifying meters in claim 1, wherein the method for acquiring the center of the dial comprises the following steps:
calculating the longitudinal gradient of the image to obtain a longitudinal gradient map;
after the binarization operation is carried out on the longitudinal gradient map, extracting a contour;
taking three points from the contour as a circle at random for multiple times, wherein the circle comprises a circle center and a radius;
and taking the average position of the circle center as the circle center of the dial.
5. The method of automatic identification of a meter according to claim 1, wherein the method of obtaining the position of the scale mark comprises:
acquiring the outline of an image;
screening the contour through screening conditions to obtain a scale contour,
the screening conditions include: the point density of the contour is greater than a first threshold; the aspect ratio is 1:2-1: 5; the center of the minimum outline bounding rectangle is used as the outline center, and the distance between the outline center and the circle center is larger than a second threshold value; the difference between the inclination angle of the minimum outline rectangle and the inclination angle of the center of the outline and the circle center connecting line is smaller than a third threshold value;
taking the connecting line of the center of the scale outline and the circle center as a scale mark;
acquiring a minimum included angle between the scale marks according to the angle of the scale marks;
and completing or redrawing the scale mark according to the minimum included angle, and acquiring the position of the scale mark.
6. The method for automatically identifying meters in claim 1, wherein the method for obtaining the position of the pointer based on the circumferential template matching comprises:
acquiring a matching area of the image;
establishing a template pointer by taking the circle center of the matching area as a center, traversing the template pointer in an anticlockwise direction, and generating a sub-graph by rotating for each angle;
calculating the similarity between the matching region and the subgraph, and acquiring the most similar subgraph;
and taking the template pointer of the most similar subgraph as the pointer of the image, and acquiring the position of the pointer.
7. The method for automatically identifying meters in claim 1, wherein the method for obtaining the position of the pointer based on radius gray scale matching comprises:
extracting the gray value of the matching area in the image;
establishing a scanning line, and rotating the scanning line by taking the circle center as the center;
sequentially calculating the sum of the gray values of the scanning lines in the radial direction;
and taking the scanning line at the maximum value of the sum of the gray values as a pointer and acquiring the position of the pointer.
8. The method of automatic meter identification according to claim 1, wherein the meter reading is calculated by the formula:
wherein, data is the reading, R is the measuring range, beta is the pointer angle, alpha is the included angle of the starting position and the ending position of the scale mark.
9. The method of claim 1, wherein the method of obtaining the range of the meter comprises:
reading characters and text boxes thereof in the image based on an OCR technology;
screening numerical values in the characters;
reading the distance between the center of the numerical text box and the circle center, and voting the distance;
acquiring a scale text box and the diameter thereof according to the voting data;
obtaining the range classification and scale value thereof according to the diameter of the text box;
obtaining the measuring range of the instrument according to the scale value;
and presetting a dictionary of an instrument unit, and matching the numerical values in the dictionary to obtain units of characters in the reading or scale text box.
10. A system for realizing the automatic identification method of the meter according to any one of the claims 1 to 9, which is characterized by comprising an acquisition module, a preprocessing module, a circle identification module, a pointer identification module, a scale mark identification module, a measuring range module and a reading module,
the acquisition module is used for acquiring an image of the instrument;
the preprocessing module is used for carrying out distortion correction on the image;
the circle identification module is used for acquiring the circle center of the dial plate in the image;
the pointer identification module is used for acquiring the position of a pointer based on a Hough transform, annular template matching or radius gray matching method;
the scale mark identification module is used for positioning the scale marks of the dial plate to obtain the positions of the scale marks;
the measuring range module is used for obtaining the measuring range of the instrument;
the reading module is used for calculating the reading of the instrument according to the positions of the pointer, the circle center, the measuring range and the scale mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643925.8A CN113378814A (en) | 2021-06-09 | 2021-06-09 | Method and system for automatically identifying instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643925.8A CN113378814A (en) | 2021-06-09 | 2021-06-09 | Method and system for automatically identifying instrument |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113378814A true CN113378814A (en) | 2021-09-10 |
Family
ID=77573287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110643925.8A Pending CN113378814A (en) | 2021-06-09 | 2021-06-09 | Method and system for automatically identifying instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378814A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115841666A (en) * | 2023-02-17 | 2023-03-24 | 江西小马机器人有限公司 | Instrument reading identification method and system |
-
2021
- 2021-06-09 CN CN202110643925.8A patent/CN113378814A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115841666A (en) * | 2023-02-17 | 2023-03-24 | 江西小马机器人有限公司 | Instrument reading identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460327B (en) | Automatic identification method for reading of pointer instrument based on image processing | |
| JP3799408B1 (en) | Image processing apparatus and image processing method | |
| CN103759758B (en) | A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification | |
| CN110210477B (en) | Digital instrument reading identification method | |
| CN107609451A (en) | A kind of high-precision vision localization method and system based on Quick Response Code | |
| CN110874596B (en) | Intelligent recognition early warning method and system for instrument | |
| CN104392206A (en) | Image processing method for automatic pointer-type instrument reading recognition | |
| CN112149667B (en) | Automatic reading method of pointer instrument based on deep learning | |
| CN111368906B (en) | Pointer type oil level meter reading identification method based on deep learning | |
| CN111476246B (en) | Robust and efficient intelligent reading method for pointer instrument applied to complex environment | |
| CN107301412B (en) | Pointer instrument reading method based on image processing | |
| CN107145890A (en) | A kind of pointer dashboard automatic reading method under remote various visual angles environment | |
| CN109034170B (en) | Reading method for circular pointer type instrument of switch cabinet detection device | |
| CN102750531A (en) | Method for detecting handwriting mark symbols for bill document positioning grids | |
| CN112734729A (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN114399677A (en) | Pointer instrument identification method based on text region reading | |
| CN113378814A (en) | Method and system for automatically identifying instrument | |
| CN116758045A (en) | Surface defect detection method and system for semiconductor light-emitting diode | |
| CN117037132A (en) | Ship water gauge reading detection and identification method based on machine vision | |
| CN112036391B (en) | Electronic inspection method and system based on shale gas field production station | |
| CN114898347A (en) | Machine vision identification method for pointer instrument | |
| CN106778515B (en) | Automatic identification method for axial magnetic flux leakage array signal of flange | |
| CN113191351B (en) | Reading identification method and device of digital electric meter and model training method and device | |
| CN114898198A (en) | Image processing method for automatic reading of pointer type pressure gauge | |
| CN108509845B (en) | Visual inspection method for transformer substation instrument equipment inspection based on feature fitting |
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 |