CN106446903A - Recognition method for position of wave-band switch of instrument - Google Patents
Recognition method for position of wave-band switch of instrument Download PDFInfo
- Publication number
- CN106446903A CN106446903A CN201610832507.2A CN201610832507A CN106446903A CN 106446903 A CN106446903 A CN 106446903A CN 201610832507 A CN201610832507 A CN 201610832507A CN 106446903 A CN106446903 A CN 106446903A
- Authority
- CN
- China
- Prior art keywords
- band switch
- image
- pixel
- computer
- profile
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a recognition method for the position of a wave-band switch of an instrument. The recognition method comprises the following steps: inputting an acquired original image into a computer, and converting the original image into a gray scale image; performing binarization processing on the gray scale image; respectively establishing rectangles outside a profile; calculating a center of a wave-band switch knob; calculating a gray-scale valve of a central image of the wave-band switch knob by the computer, and differencing gray-scale values of M pixel points of an image in a rectangular area where the profile of the wave-band switch knob is positioned and the gray-scale valve of the center of the wave-band switch knob, wherein an area formed by P pixel points with maximum difference values is an indicator of the wave-band switch; converting planimetric rectangular coordinates of the M pixel points of the image in the rectangular area where the profile of the wave-band switch knob is positioned into polar coordinates, and differentiating the M pixel points to obtain Y pixel points with maximum derivative values, wherein the derivative values of the Y pixel points are identical, and a closed area among the Y pixel points is an indicator of the wave-band switch.
Description
Technical field
The present invention relates to a kind of instrument band switch location recognition method.
Background technology
Indicating value identification currently for pointer instrument is substantially for instrument dial scale and pointer, but many instrument
Various band switches, the function of being selected by band switch and range is also had to combine gauge outfit ability especially on analogue instrument panel
Correct reading.Existing recognition methodss cannot be identified to the position of band switch.
Content of the invention
The present invention is in order to overcome the shortcomings of above technology, there is provided a kind of instrument band switch position can accurately be extracted
Method.
The present invention overcomes its technical problem be employed technical scheme comprise that:
A kind of instrument band switch location recognition method, comprises the steps:
A) outer surface of instrument is carried out with original image collection, and the original image input computer by collection;
B) using computer, original image is carried out with gray processing process and original image is converted to gray level image by coloured image;
C) using computer, binary conversion treatment is carried out to gray level image;
D) obtain the N number of profile in bianry image by the searching profile function algorithm in opencv function library using computer,
Set up rectangle outside N number of profile respectively, each profile is located within corresponding rectangle respectively;
E) rectangular area being located using the profile that computer navigates to band switch knob, computer is in this rectangular area
The coordinate figure of M pixel makees mean value calculation, calculates the midpoint of this rectangle, is defined as the center of band switch knob;
If the sign f) on band switch is inside the knob of band switch, execution step g), if on band switch
Sign outside the knob of band switch, then execution step h);
g)Computer calculates the gray value of the image at center of band switch knob, the square that the profile of band switch knob is located
The gray value at the gray value of M pixel of the image in shape region and the center of band switch knob asks poor, the maximum P of difference
The region that individual pixel is formed is the sign of band switch.
H) M pixel of the image in the rectangular area that the profile of band switch knob is located by computer is straight by plane
Angular coordinate is converted to polar coordinate and M pixel is differentiated, obtain the maximum pixel of Y derivative value and Y pixel that
This derivative value is identical, and the enclosed region between Y pixel is the sign of band switch.
For the definition reducing picture noise and improve image, the image in above-mentioned steps b) is converted into gray level image
Afterwards, also include by greyscale image transitions for Mat type Image image, computer carried out using OpenCV function pair Image image
The step of smooth and Edge contrast.
In order to exclude the interference that illumination leads to, it is additionally included in step g) and increases the P maximum using computer calculating difference
The step of the distance at center of individual pixel and band switch knob, when Q pixel in P maximum pixel of difference and
When the distance at the center of band switch knob is more than the radius of band switch knob, Q pixel is removed by computer.
The invention has the beneficial effects as follows.
Brief description
Fig. 1 structural representation inside the knob of band switch for the sign on band switch;
Fig. 2 structural representation outside the knob of band switch for the sign on band switch.
Specific embodiment
Below in conjunction with the accompanying drawings 1, the present invention will be further described for accompanying drawing 2.
A kind of instrument band switch location recognition method, comprises the steps:A) original graph is carried out to the outer surface of instrument
As collection, and the original image input computer by collection.B) using computer, original image being carried out with gray processing process will be former
Beginning image is converted to gray level image by coloured image, and because coloured image is usually rgb format, that is, each pixel is by R(Red)、
G(Green)、B(Blue)Three component compositions, for 24 true color, each component 1 byte representation, memory data output
Big and be difficult to process it is therefore necessary to coloured image is converted to gray level image.Gray level image only comprises monochrome information, does not comprise
Color information, therefore reduces the data processing amount of computer.C) using computer, binary conversion treatment is carried out to gray level image,
Greyscale image transitions are conducive to improving processing speed for bianry image, meet requirement of real-time.Bianry image refers to view picture figure
Picture only 0, the image of 255 two gray values, there are not other gray values between them.D) passed through using computer
Searching profile function algorithm in opencv function library obtains the N number of profile in bianry image, sets up respectively outside N number of profile
Rectangle, each profile is located within corresponding rectangle respectively.E) it is located using the profile that computer navigates to band switch knob
Rectangular area, computer makees mean value calculation to the coordinate figure of M pixel in this rectangular area, calculates this rectangle
Midpoint, is defined as the center O point of band switch knob.F) as shown in Figure 1, if the sign on band switch is opened in wave band
Inside the knob closing, then execution step g), as shown in Figure 2, if the sign on band switch is in the knob of band switch
Outside, then execution step h).g)Computer calculates the gray value of the image at center of band switch knob, by band switch knob
Profile be located rectangular area in the gray value of M pixel of image and band switch knob center O point gray scale
Value asks poor, and the region that P maximum pixel of difference is formed is the sign of band switch, a-quadrant as shown in Figure 1,
It is achieved thereby that the accurately identifying of the position of sign of band switch on band switch for the sign.H) computer will
M pixel of the image in rectangular area that the profile of band switch knob is located is converted to polar coordinate by plane rectangular coordinates
And M pixel is differentiated, derivative value is identical each other to obtain the maximum pixel of Y derivative value and Y pixel, Y picture
Enclosed region between vegetarian refreshments is the sign of band switch, B region as shown in Figure 2, it is achieved thereby that sign
In accurately identifying of the position of the sign of the band switch in outside.
After image in above-mentioned steps b) is converted into gray level image, also include by greyscale image transitions for Mat type Image
Image, computer carries out smooth and Edge contrast step using OpenCV function pair Image image.Because OpenCV is processed
Picture is Mat type matrix, therefore first image is entered row format conversion, and computer first carries out smothing filtering, Gu Mingsi to image
It is exactly that the part more than burr of a ripple or a certain frequency is removed on adopted signal, be exactly briefly low-pass filtering.It is reacted to
It is exactly noise reduction and image blurring process on image(Because high frequency has reacted details, so removing details to obtain fuzzy profile),
Edge due to image is typically in HFS, so this smothing filtering will result in edge blurry, i.e. image and background
Will not make a clear distinction between good and evil but blurred transition.It is thus desirable to carrying out image sharpening again to fuzzy image, the edge of image is made to become
Clearly.The purpose that image sharpening is processed is the Jing Guoping in order that the details of the edge of image, contour line and image is apparent from
The basic reason that sliding image thickens is because that image receives average or integral operation, and therefore it can be carried out with inverse fortune
Calculating (such as differentiating) can be so that image be apparent from.Differentiate the rate of change being to seek signal, micro- by Fourier transform
Divide property to understand, differentiate and there is stronger high fdrequency components effect.To consider from frequency domain, image blurring essence is because it
High fdrequency components are attenuated, and therefore can make image clearly with high pass filter.By increasing the place to image smoothing and sharpening
Reason, further increases the definition in subsequent step and accuracy.
Further, it is additionally included in step g) and increase the P pixel maximum using computer calculating difference and wave band
The step of the distance at the center of switching knob, when Q pixel in P maximum pixel of difference and band switch knob
When the distance at center is more than the radius of band switch knob, Q pixel is removed by computer.When light application ratio is stronger,
The higher region of brightness value that it is surveyed in Instrument image surface row may interfere to sign region, therefore by with
The radius of band switch knob is compared and can remove it, and effectively prevents illumination interference from causing sign Position location accuracy
The drawbacks of decline.
Claims (4)
1. a kind of instrument band switch location recognition method is it is characterised in that comprise the steps:
A) outer surface of instrument is carried out with original image collection, and the original image input computer by collection;
B) using computer, original image is carried out with gray processing process and original image is converted to gray level image by coloured image;
C) using computer, binary conversion treatment is carried out to gray level image;
D) obtain the N number of profile in bianry image by the searching profile function algorithm in opencv function library using computer,
Set up rectangle outside N number of profile respectively, each profile is located within corresponding rectangle respectively;
E) rectangular area being located using the profile that computer navigates to band switch knob, computer is in this rectangular area
The coordinate figure of M pixel makees mean value calculation, calculates the midpoint of this rectangle, is defined as the center of band switch knob;
If the sign f) on band switch is inside the knob of band switch, execution step g), if on band switch
Sign outside the knob of band switch, then execution step h);
g)Computer calculates the gray value of the image at center of band switch knob, the square that the profile of band switch knob is located
The gray value at the gray value of M pixel of the image in shape region and the center of band switch knob asks poor, the maximum P of difference
The region that individual pixel is formed is the sign of band switch.
2.h) M pixel of the image in the rectangular area that the profile of band switch knob is located by computer is by flat square
Coordinate Conversion is polar coordinate M pixel is differentiated, and obtains the pixel of Y derivative value maximum and Y pixel each other
Derivative value is identical, and the enclosed region between Y pixel is the sign of band switch.
3. instrument band switch location recognition method according to claim 1 it is characterised in that:Figure in described step b)
As after being converted into gray level image, also include by greyscale image transitions for Mat type Image image, computer utilizes OpenCV letter
Several Image image is carried out with smooth and Edge contrast step.
4. instrument band switch location recognition method according to claim 1 it is characterised in that:It is additionally included in step g)
Increase using P maximum pixel of computer calculating difference and the step of the distance at center of band switch knob, work as difference
The distance at the center of Q pixel in P maximum pixel and band switch knob is more than the radius of band switch knob
When, Q pixel is removed by computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610832507.2A CN106446903B (en) | 2016-09-20 | 2016-09-20 | A kind of instrument band switch location recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610832507.2A CN106446903B (en) | 2016-09-20 | 2016-09-20 | A kind of instrument band switch location recognition method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106446903A true CN106446903A (en) | 2017-02-22 |
CN106446903B CN106446903B (en) | 2019-04-23 |
Family
ID=58165584
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610832507.2A Active CN106446903B (en) | 2016-09-20 | 2016-09-20 | A kind of instrument band switch location recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106446903B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106952277A (en) * | 2017-03-21 | 2017-07-14 | 中国人民解放军国防科学技术大学 | A kind of two-value rocker switch method for detecting position based on image procossing |
CN112116540A (en) * | 2020-09-11 | 2020-12-22 | 福建省海峡智汇科技有限公司 | Gear identification method and system for knob switch |
CN112178706A (en) * | 2020-10-14 | 2021-01-05 | 宁波方太厨具有限公司 | Method and system for identifying fire gear of stove and method and system for linking smoke stove |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
CN102262734A (en) * | 2011-01-07 | 2011-11-30 | 浙江省电力公司 | Method and system for determining turning-on or turning-off of switch |
CN102609712A (en) * | 2012-02-24 | 2012-07-25 | 山东鲁能智能技术有限公司 | Reading method of round-like pointer instrument used for mobile robot |
CN103324943A (en) * | 2013-06-18 | 2013-09-25 | 中国人民解放军第二炮兵工程大学 | Identification method of complex device panel image multi-sub zone state |
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 |
CN104573702A (en) * | 2014-12-01 | 2015-04-29 | 长沙众治电气技术有限公司 | Method for automatically identifying sulfur hexafluoride pressure instrument image |
CN105260716A (en) * | 2015-10-13 | 2016-01-20 | 长沙威胜信息技术有限公司 | Fault indicator state identification method and fault indicator state identification device |
-
2016
- 2016-09-20 CN CN201610832507.2A patent/CN106446903B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
CN102262734A (en) * | 2011-01-07 | 2011-11-30 | 浙江省电力公司 | Method and system for determining turning-on or turning-off of switch |
CN102609712A (en) * | 2012-02-24 | 2012-07-25 | 山东鲁能智能技术有限公司 | Reading method of round-like pointer instrument used for mobile robot |
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 |
CN103324943A (en) * | 2013-06-18 | 2013-09-25 | 中国人民解放军第二炮兵工程大学 | Identification method of complex device panel image multi-sub zone state |
CN104573702A (en) * | 2014-12-01 | 2015-04-29 | 长沙众治电气技术有限公司 | Method for automatically identifying sulfur hexafluoride pressure instrument image |
CN105260716A (en) * | 2015-10-13 | 2016-01-20 | 长沙威胜信息技术有限公司 | Fault indicator state identification method and fault indicator state identification device |
Non-Patent Citations (3)
Title |
---|
李静: "《基于图像处理的指针式水表检定系统的研究与设计》", 《中国优秀硕士学位全文数据库 工程科技II辑》 * |
邵剑雄等: "《基于霍夫森林的变电站开关设备检测及状态识别》", 《电力系统自动化》 * |
陈安伟等: "《基于机器人的变电站开关状态图像识别方法》", 《电力系统自动化》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106952277A (en) * | 2017-03-21 | 2017-07-14 | 中国人民解放军国防科学技术大学 | A kind of two-value rocker switch method for detecting position based on image procossing |
CN106952277B (en) * | 2017-03-21 | 2019-10-25 | 中国人民解放军国防科学技术大学 | A kind of two-value rocker switch method for detecting position based on image procossing |
CN112116540A (en) * | 2020-09-11 | 2020-12-22 | 福建省海峡智汇科技有限公司 | Gear identification method and system for knob switch |
CN112116540B (en) * | 2020-09-11 | 2023-09-22 | 福建省海峡智汇科技有限公司 | Gear identification method and system for knob switch |
CN112178706A (en) * | 2020-10-14 | 2021-01-05 | 宁波方太厨具有限公司 | Method and system for identifying fire gear of stove and method and system for linking smoke stove |
CN112178706B (en) * | 2020-10-14 | 2021-11-05 | 宁波方太厨具有限公司 | Method and system for identifying fire gear of stove and method and system for linking smoke stove |
Also Published As
Publication number | Publication date |
---|---|
CN106446903B (en) | 2019-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
CN115272346A (en) | PCB production process online detection method based on edge detection | |
CN105654445B (en) | A kind of handset image denoising method based on wavelet transformation edge detection | |
CN108805023A (en) | A kind of image detecting method, device, computer equipment and storage medium | |
CN105260693A (en) | Laser two-dimensional code positioning method | |
CN106446903A (en) | Recognition method for position of wave-band switch of instrument | |
CN115331119B (en) | Solid waste identification method | |
CN116704516B (en) | Visual inspection method for water-soluble fertilizer package | |
CN113609984A (en) | Pointer instrument reading identification method and device and electronic equipment | |
CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
CN105894474A (en) | Non-linear image enhancement method, and edge detection method using the same | |
CN106599891A (en) | Remote sensing image region-of-interest rapid extraction method based on scale phase spectrum saliency | |
CN111815542B (en) | Tree annual ring image medulla positioning and annual ring measuring method | |
Li et al. | A study of crack detection algorithm | |
CN115294314A (en) | Electronic component surface defect identification method | |
CN110349129B (en) | Appearance defect detection method for high-density flexible IC substrate | |
CN109472766B (en) | Bridge bolt area positioning method and terminal equipment | |
CN112991359A (en) | Pavement area extraction method, pavement area extraction system, electronic equipment and storage medium | |
Li et al. | Segmentation of cDNA microarray image using fuzzy c-mean algorithm and mathematical morphology | |
CN116485924B (en) | Binarization method of CT section image of optical fiber coil containing artifact | |
Shuaishuai et al. | Research on License Plate Recognition Algorithm Based on OpenCV | |
CN108734180A (en) | A kind of SIFT feature gradient generation method based on calculation optimization | |
CN108596194A (en) | A kind of image encoding method of the local binary patterns of Gauss weighting | |
CN113780107B (en) | Radio signal detection method based on deep learning dual-input network model | |
CN108122233A (en) | Color image segmentation method based on local pixel comprehensive characteristics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |