CN107067013A - One kind is based on many instrument hawkeye fuzzy detection system and methods - Google Patents
One kind is based on many instrument hawkeye fuzzy detection system and methods Download PDFInfo
- Publication number
- CN107067013A CN107067013A CN201710278840.8A CN201710278840A CN107067013A CN 107067013 A CN107067013 A CN 107067013A CN 201710278840 A CN201710278840 A CN 201710278840A CN 107067013 A CN107067013 A CN 107067013A
- Authority
- CN
- China
- Prior art keywords
- instrument
- image
- hawkeye
- many
- gray
- 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
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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/30—Noise filtering
-
- 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
Abstract
One kind is based on many instrument hawkeye fuzzy detection system and methods, and the present invention relates to based on many instrument hawkeye fuzzy detection system and methods.The invention aims to solve existing manually to detect meter status, efficiency is low, and influenceed by people's Subjective fatigue factor so that the accuracy rate of instrument detection is low and when many instrument are run simultaneously, and the problem of problematic instrument also has difficulty is found rapidly.System includes：For being acquired by ccd video camera to the general image of row's instrument, the meter information acquisition module of the characteristic value of instrument is extracted；For distinguishing metered quantity and determining the analysis module of the independent image of each instrument；For the gauge pointer registration computing module for the pointer registration for calculating each instrument；For the comparing module that the pointer registration of each instrument and critical field are compared.The present invention is used for instrument detection field.
Description
Technical field
The present invention relates to based on many instrument hawkeye fuzzy detection system and methods.
Background technology
Using manually being detected to meter status more than present Workshop Production, efficiency is low, and by people's Subjective fatigue because
Element influence so that the accuracy rate of instrument detection is low and when many instrument are run simultaneously, and problematic instrument is found rapidly and is also deposited
In difficulty.
The content of the invention
The invention aims to solve it is existing manually meter status is detected, efficiency is low, and by people master
See fatigue factor influence so that the accuracy rate of instrument detection is low and when many instrument are run simultaneously, finds rapidly problematic
The problem of also there is difficulty in instrument, and propose to be based on many instrument hawkeye fuzzy detection methods.
One kind is included based on many instrument hawkeye fuzzy detection systems：
For being acquired by ccd video camera to the general image of row's instrument, the instrument of the characteristic value of instrument is extracted
Information instrument information acquisition module；
For distinguishing metered quantity and determining the analysis module of the independent image of each instrument；
Binarization of gray value is carried out for the independent image to each instrument, carrying out feature to the image after binarization of gray value carries
Take, calculate the gauge pointer registration computing module of the pointer registration of each instrument；
For the comparing module that the pointer registration of each instrument and critical field are compared.
One kind is based on many instrument hawkeye fuzzy detection method detailed processes：
Step one：Meter information acquisition module is acquired by ccd video camera to the general image of row's instrument, is extracted
The characteristic value of instrument；
The one row instrument refers to more than or equal to two instrument；
Step 2：Because instrument color is black, background is white, and analysis module carries out upright projection to the pixel of image
And transverse projection；Black picture element Wave crest and wave trough shape occurs, and is exactly one piece of instrument from the coordinate of trough to the coordinate of next trough
The position of table；By that analogy, the coordinate for calculating all instrument in image is interval；
Step 3：The coordinate of all instrument calculated according to step 2 is interval, is partitioned into the independent image of each instrument；
Step 4：Gauge pointer registration computing module carries out binarization of gray value to the independent image of each instrument, to gray scale
Image after binaryzation carries out feature extraction, calculates the pointer registration of each instrument；
Step 5：The pointer registration of each instrument is compared comparing module with critical field；If qualified continue to monitor,
Perform step one；It is unqualified to be alarmed.
Beneficial effects of the present invention are：
The present invention is based on many instrument hawkeye fuzzy detection system and methods using a kind of, solves existing artificial to instrument shape
State is detected that efficiency is low, and is influenceed by people's Subjective fatigue factor so that the accuracy rate of instrument detection is low and in many instrument
Table is run simultaneously when, the problem of problematic instrument also has difficulty is found rapidly.By ccd video camera to the whole of row's instrument
Body image is acquired；Because instrument color is black, background is white or light color, the pixel of image is carried out upright projection with
Transverse projection；Black picture element Wave crest and wave trough shape occurs, and is exactly one piece of instrument from the coordinate of trough to the coordinate of next trough
Position；By that analogy, the coordinate for calculating all instrument in image is interval；According to the coordinate area of all instrument calculated
Between, it is partitioned into the independent image of each instrument；Gray processing binaryzation is carried out to the independent image of each instrument, to gray processing two-value
Image after change carries out the steps such as feature extraction, calculates the pointer registration of each instrument；By the pointer registration of each instrument with
Critical field is compared；If qualified continue to monitor, unqualified to be alarmed；Manually meter status need not be detected,
Detection efficiency is high, and the accuracy rate of detection is high, can find problematic instrument rapidly when many instrument are run simultaneously.
Brief description of the drawings
Fig. 1 is smear design sketch of the present invention；
Fig. 2 is flow chart of the present invention.
Embodiment
Embodiment one：One kind of present embodiment, which is based on many instrument hawkeye fuzzy detection systems, to be included：
For being acquired by ccd video camera to the general image of row's instrument, the instrument of the characteristic value of instrument is extracted
Information instrument information acquisition module；
For distinguishing metered quantity and determining the analysis module of the independent image of each instrument；
Binarization of gray value is carried out for the independent image to each instrument, carrying out feature to the image after binarization of gray value carries
Take, calculate the gauge pointer registration computing module of the pointer registration of each instrument；
For the comparing module that the pointer registration of each instrument and critical field are compared.
Embodiment two：Present embodiment from unlike embodiment one：Described image treatment technology has
Body is：
The Instrument image of collection is first changed into gray level image, then Binary Sketch of Grey Scale Image is obtained binary image, is set
Threshold value, pixel of the gray scale in threshold range is feature to be extracted.
Other steps and parameter are identical with embodiment one.
Embodiment three：Present embodiment from unlike embodiment one or two：The feature of the instrument
It is worth the contour line for instrument, internal pointer profile, scale line profile.
Other steps and parameter are identical with embodiment one or two.
Embodiment four：One kind of present embodiment is based on many instrument hawkeye fuzzy detection method detailed processes：
Step one：Meter information acquisition module is acquired by ccd video camera to the general image of row's instrument, is extracted
The characteristic value of instrument；
The one row instrument refers to more than or equal to two instrument；
Step 2：Because instrument color is black, background is white or light color, and analysis module is hung down to the pixel of image
Deliver directly shadow and transverse projection；Such as Fig. 1.There is the region black picture element occurrence number of table many, and the interval region between table and table is
The light pixel of background, almost occurs without black picture element.So, black picture element Wave crest and wave trough shape occurs, from the seat of trough
The coordinate of next trough is marked, is exactly the position of one piece of instrument；By that analogy, the coordinate area of all instrument in image is calculated
Between；
Step 3：The coordinate of all instrument calculated according to step 2 is interval, is partitioned into the independent image of each instrument；
Step 4：Gauge pointer registration computing module carries out binarization of gray value to the independent image of each instrument, to gray scale
Image after binaryzation carries out feature extraction, calculates the pointer registration of each instrument；
Step 5：The pointer registration of each instrument is compared comparing module with critical field；If qualified continue to monitor,
Perform step one；It is unqualified to be alarmed.
Embodiment five, stupid embodiment from unlike embodiment four：Instrument refers in the step 4
Pin registration computing module carries out gray processing binaryzation to the independent image of each instrument；Detailed process is：
The independent image of each instrument is converted into gray level image, Gaussian smoothing is carried out to gray level image, ash disposal is gone
The noise spent in image；
Gray level image is divided into multiple images block, according to the grayscale distribution information of each image block, using between maximum kind
Variance method calculates the segmentation threshold of image block, and image block is divided into two portions of foreground image and background image according to segmentation threshold
Point, the grey level histogram of foreground image and background image is set up respectively, by analyzing the foreground image of histogram adjusting mistake point, is obtained
To final binary image.
Other steps and parameter are identical with embodiment four.
Claims (5)
1. one kind is based on many instrument hawkeye fuzzy detection systems, it is characterised in that：One kind is based on many instrument hawkeye fuzzy detection systems
System includes：
For being acquired by ccd video camera to the general image of row's instrument, the meter information of the characteristic value of instrument is extracted
Acquisition module；
For distinguishing metered quantity and determining the analysis module of the independent image of each instrument；
Binarization of gray value is carried out for the independent image to each instrument, feature extraction is carried out to the image after binarization of gray value,
Calculate the gauge pointer registration computing module of the pointer registration of each instrument；
For the comparing module that the pointer registration of each instrument and critical field are compared.
2. a kind of according to claim 1 be based on many instrument hawkeye fuzzy detection systems, it is characterised in that：Described image processing
Technology is specially：
The Instrument image of collection is first changed into gray level image, then Binary Sketch of Grey Scale Image is obtained binary image, threshold value is set,
Pixel of the gray scale in threshold range is feature to be extracted.
3. a kind of according to claim 2 be based on many instrument hawkeye fuzzy detection systems, it is characterised in that：The spy of the instrument
Value indicative is the contour line of instrument, internal pointer profile, scale line profile.
4. a kind of method of many instrument hawkeye fuzzy detection systems based on claim 1, it is characterised in that：One kind is based on many instrument
Table hawkeye fuzzy detection method detailed process is：
Step one：Meter information acquisition module is acquired by ccd video camera to the general image of row's instrument, extracts instrument
Characteristic value；
The one row instrument refers to more than or equal to two instrument；
Step 2：Because instrument color is black, background is white, and analysis module carries out upright projection and horizontal stroke to the pixel of image
To projection；Black picture element Wave crest and wave trough shape occurs, from the coordinate of trough to the coordinate of next trough, one piece of instrument
Position；By that analogy, the coordinate for calculating all instrument in image is interval；
Step 3：The coordinate of all instrument calculated according to step 2 is interval, is partitioned into the independent image of each instrument；
Step 4：Gauge pointer registration computing module carries out binarization of gray value to the independent image of each instrument, to gray scale two-value
Image after change carries out feature extraction, calculates the pointer registration of each instrument；
Step 5：The pointer registration of each instrument is compared comparing module with critical field；If qualified continue to monitor, perform
Step one；It is unqualified to be alarmed.
5. a kind of according to claim 4 be based on many instrument hawkeye fuzzy detection methods, it is characterised in that：In the step 4
Gauge pointer registration computing module carries out gray processing binaryzation to the independent image of each instrument；Detailed process is：
The independent image of each instrument is converted into gray level image, Gaussian smoothing is carried out to gray level image, gray-scale map is removed
Noise as in；
Gray level image is divided into multiple images block, according to the grayscale distribution information of each image block, using maximum between-cluster variance
Method calculates the segmentation threshold of image block, and image block is divided into two parts of foreground image and background image according to segmentation threshold,
The grey level histogram of foreground image and background image is set up respectively, by analyzing the foreground image of histogram adjusting mistake point, is obtained
Final binary image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710278840.8A CN107067013A (en) | 2017-04-25 | 2017-04-25 | One kind is based on many instrument hawkeye fuzzy detection system and methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710278840.8A CN107067013A (en) | 2017-04-25 | 2017-04-25 | One kind is based on many instrument hawkeye fuzzy detection system and methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107067013A true CN107067013A (en) | 2017-08-18 |
Family
ID=59604048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710278840.8A Pending CN107067013A (en) | 2017-04-25 | 2017-04-25 | One kind is based on many instrument hawkeye fuzzy detection system and methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107067013A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942419A (en) * | 2019-11-22 | 2020-03-31 | 航天科技控股集团股份有限公司 | Fuzzy processing method for full liquid crystal instrument ground glass |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001236181A (en) * | 2000-02-22 | 2001-08-31 | Fuji Electric Co Ltd | Pointing device |
| CN101403632A (en) * | 2008-11-13 | 2009-04-08 | 中国石化江汉油田分公司江汉采油厂 | Dynamic multipath synchronization detection apparatus and method for metering device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN103196480A (en) * | 2013-03-27 | 2013-07-10 | 王文博 | Automatic detection device and detection method of motor meter |
| CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
| CN105488506A (en) * | 2016-01-11 | 2016-04-13 | 无锡市计量检定测试中心 | Automatic verification system for pointer meters and simple digital meters |
| CN106218409A (en) * | 2016-07-20 | 2016-12-14 | 长安大学 | A kind of can the bore hole 3D automobile instrument display packing of tracing of human eye and device |
| CN106529519A (en) * | 2016-09-19 | 2017-03-22 | 国家电网公司 | Automatic number identification method and system of power pointer type instrument |
-
2017
- 2017-04-25 CN CN201710278840.8A patent/CN107067013A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001236181A (en) * | 2000-02-22 | 2001-08-31 | Fuji Electric Co Ltd | Pointing device |
| CN101403632A (en) * | 2008-11-13 | 2009-04-08 | 中国石化江汉油田分公司江汉采油厂 | Dynamic multipath synchronization detection apparatus and method for metering device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
| CN103196480A (en) * | 2013-03-27 | 2013-07-10 | 王文博 | Automatic detection device and detection method of motor meter |
| CN105488506A (en) * | 2016-01-11 | 2016-04-13 | 无锡市计量检定测试中心 | Automatic verification system for pointer meters and simple digital meters |
| CN106218409A (en) * | 2016-07-20 | 2016-12-14 | 长安大学 | A kind of can the bore hole 3D automobile instrument display packing of tracing of human eye and device |
| CN106529519A (en) * | 2016-09-19 | 2017-03-22 | 国家电网公司 | Automatic number identification method and system of power pointer type instrument |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942419A (en) * | 2019-11-22 | 2020-03-31 | 航天科技控股集团股份有限公司 | Fuzzy processing method for full liquid crystal instrument ground glass |
| CN110942419B (en) * | 2019-11-22 | 2023-09-22 | 航天科技控股集团股份有限公司 | Fuzzy processing method for frosted glass of full liquid crystal instrument |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| CN104408460B (en) | A kind of lane detection and tracking detection method | |
| CN104990925B (en) | One kind is based on gradient multi thresholds optimization defect inspection method | |
| CN104331876B (en) | Method for detecting straight line and processing image and related device | |
| CN106446894B (en) | A method of based on outline identification ball-type target object location | |
| CN109087286A (en) | A kind of detection method and application based on Computer Image Processing and pattern-recognition | |
| CN115222733A (en) | Metal component surface defect detection method based on image recognition | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN109084350A (en) | A kind of kitchen ventilator and oil smoke concentration detection method having filtering functions vision-based detection module | |
| CN109409181B (en) | Independent detection method for upper and lower edges of fingers for low-quality finger vein image | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
| CN111665199A (en) | Wire and cable color detection and identification method based on machine vision | |
| CN104966283A (en) | Imaging layered registering method | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN114170165A (en) | Chip surface defect detection method and device | |
| CN114155226A (en) | Micro defect edge calculation method | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| US20190333212A1 (en) | Visual cardiomyocyte analysis | |
| Gong et al. | An improved Canny algorithm based on adaptive 2D-Otsu and Newton Iterative | |
| CN107067013A (en) | One kind is based on many instrument hawkeye fuzzy detection system and methods | |
| CN115294119B (en) | Machine vision-based method for detecting stains in inner grooves of heads of plum-blossom-shaped threads | |
| CN115184362A (en) | Rapid defect detection method based on structured light projection | |
| CN110349133B (en) | Object surface defect detection method and device | |
| CN112784922A (en) | Extraction and classification method of intelligent cloud medical images |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170818 |
|
| WD01 | Invention patent application deemed withdrawn after publication |