CN109636793A - The detection system and its detection method of display - Google Patents
The detection system and its detection method of display Download PDFInfo
- Publication number
- CN109636793A CN109636793A CN201811533505.9A CN201811533505A CN109636793A CN 109636793 A CN109636793 A CN 109636793A CN 201811533505 A CN201811533505 A CN 201811533505A CN 109636793 A CN109636793 A CN 109636793A
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- screen
- module
- display
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000012805 post-processing Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 11
- 241000208340 Araliaceae Species 0.000 claims description 8
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 8
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 8
- 235000008434 ginseng Nutrition 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 206010044565 Tremor Diseases 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 239000004575 stone Substances 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000001568 sexual effect Effects 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The detection system and its detection method of display, its detection system includes image acquisition units and image processing unit, described image acquisition unit is acquired the image of tested display, transimission and storage works, the graphics processing unit is used for the blank screen and screen shaking detection of indicator screen comprising camera calibration module, image pre-processing module, image detection module and post processing of image module.Pass through the image content on image capture device real-time capture display, whether there is the frequency that flashing etc. is abnormal and occurs extremely with image processing algorithm intelligent decision display again, replaced with intelligent detection equipment and manually checked, reduces human cost while improving detection efficiency, detection accuracy.
Description
Technical field
The present invention relates to display detection technique field more particularly to the detection systems and its detection method of display.
Background technique
Display is also generally referred to as monitor, and display is the I/O equipment for belonging to computer, i.e. input-output equipment, it
It is a kind of show tools that certain electronic document is shown to by specific transmission device and is re-reflected into human eye on screen.
It is high to the reliability requirement of screen applied to the display in the fields such as military aviation, formulate the detection for having profession
Standard, and current scientific and technological level can not also avoid in the fabrication process the generations of various defects in display, result in display
On device the problems such as flating, flashing, blank screen.Indicator screen reliability is detected, since abnormal appearance form has
It is sporadic, and most of blank screen, flashing and shake only are likely to be perceived as after observing the long duration, and at this time due to
This kind of duration tended to occur extremely is extremely short, it is difficult to capture in time, this is also to flating on display, flashing, black
Screen carries out visual identity and brings difficulty.Current relies primarily on artificial eye identification to the anomalous identification of indicator screen, deposits
Great work intensity, recognition efficiency is low and human cost is high the problems such as.
Therefore, it for disadvantages described above, needs effectively to innovate the prior art.
Summary of the invention
Display is monitored using intelligent image identification technology and is detected with reliability.It is real-time by image capture device
The image content on display is captured, then flashing etc. whether occur different with image processing algorithm intelligent decision display
Often and extremely the frequency occurred is replaced with intelligent detection equipment and is manually checked, and is dropped while improving detection efficiency, detection accuracy
Low human cost.
To achieve the above object, the present invention adopts the following technical scheme:
The detection system of display, including image acquisition units and image processing unit, described image acquisition unit is to quilt
The image for surveying display is acquired, transimission and storage work, and the graphics processing unit includes that camera calibration module, image are pre-
Processing module, image detection module and post processing of image module, the camera calibration module are ideally monitored for calculating
The internal reference of camera and outer ginseng, set out standard picture, and described image preprocessing module carries out the original image of system acquisition
Denoising, filtering, binary conversion treatment, to improve the effect of test image, described image detection module includes connected region detection mould
Block and characteristic matching module are respectively used to the blank screen detection of screen and tremble screen detection, and described image post-processing module is mainly pair
The connected region and matching matrix extracted is compared with the threshold values in reliability examination criteria, and judging whether to have occurred can
By sexual abnormality；
Correspondingly, image acquisition units include monitoring camera, image pick-up card and computer, monitoring camera is to aobvious
Show that the screen of device is monitored shooting, image pick-up card collects in computer the picture signal of monitoring shooting, and with data
The form of file is stored；
Correspondingly, monitoring camera includes industrial camera；
Correspondingly, creating the detection system of graphics processing unit using VisualStudio as development platform, OpenCV makees
For image library.
In another aspect of this invention, a kind of detection method of display, the detection method packet of the display are also provided
Include following steps:
S1 customizes a scaling board as calibration object and obtains by adjusting the camera angle of calibration object or monitoring camera
The photo for demarcating object different angle, using photo the estimation ideally internal reference of monitoring camera and outer ginseng, then estimate with it is excellent
Change the distortion factor under physical presence radial distortion；
S2, acquires indicator screen image with monitoring camera, image data is obtained using image pick-up card, to acquisition
Image data is pre-processed, and pretreated image section carries out connection region detection, acquires largest connected region area, should
Connected region area is compared with the ratio of entire picture area with threshold values in reliability examination criteria, judges whether screen goes out
Existing blank screen phenomenon obtains the pulse that picture flashes by the time occurred to blank screen phenomenon, and is judged according to test stone
Whether unusual condition is belonged to；
S3 carries out feature point extraction to the screen original image of acquisition, and two adjacent frame characteristic points is carried out characteristic point
Matching, calculates match point number, obtains matching matrix, the threshold value in matching matrix and reliability examination criteria is compared
Compared with, judge two frame pictures with the presence or absence of shake；
Correspondingly, sequencing is not present in S1 and S3；
Correspondingly, in S1, X-comers are extracted from photo come estimate the ideally internal reference of monitoring camera and
Outer ginseng estimates the distortion factor under physical presence radial distortion using least square method, and with maximum-likelihood method to estimation result
It optimizes, promotes the precision of estimation；
Correspondingly, in S2, the pretreatment of image includes being denoised, being filtered and binarization operation to image；
Correspondingly, if the fiducial value is greater than the threshold value in reliability examination criteria, it is existing that blank screen occurs in screen in S2
As；
Correspondingly, being matched using SIFT feature extraction method to two adjacent frame characteristic points in S3；
Correspondingly, rejecting the match point of mistake, and binding model using RANSAC algorithm (RANSAC) in S3
Parameter measures the matching degree between adjacent two frames characteristic point, calculates correct match point number；
Correspondingly, in S3, when matching matrix is greater than the threshold value in reliability examination criteria, it is believed that this two frames picture exists
Shake.
The invention has the benefit that
1) this project has filled up the blank that display reliability detection field lacks intelligent measurement mode, uses machine vision
Instead of visual inspection, there is discrimination accuracy and speed more higher than naked eyes, significantly reduce the working strength of personnel, save
About human cost has huge economic value and far-reaching Industry Effect power；
2) the anomalous events incidence such as blank screen and screen shake is low, and naked eyes detection observation is easy to missing inspection, and is using this
System can the stable exception for capturing each frame, and in the form of image and data, prompt the frequency occurred extremely, pulse,
Amount of jitter etc., makes testing result have good grounds；
3) detection algorithm proposed by the present invention is simple and reliable, realizes that speed is fast, and detection efficiency is high, may be implemented completely in real time
Property detection, take into account detection speed and detection accuracy.
Detailed description of the invention
Fig. 1 is detection system structure described in one embodiment of the invention；
In figure:
1, industrial camera；2, image pick-up card；3, computer.
Specific embodiment
As shown in Figure 1, in one embodiment of the invention, the detection system of display includes image acquisition units and figure
As processing unit, image acquisition units include monitoring camera, image pick-up card and computer, and the monitoring in the present embodiment is taken the photograph
Picture head is industrial camera 1, such as the industrial CCD of Basler brand, industrial camera 1 are monitored shooting to the screen of display,
The picture signal of 2 pairs of image pick-up card monitoring shootings collects in computer 3, and is stored in the form of data file, with
Detection system of the VisualStudio as development platform creation graphics processing unit, OpenCV is as image library, graphics process
Unit includes camera calibration module, image pre-processing module, image detection module and post processing of image module, camera calibration module
For calculating the ideally internal reference of industrial camera and outer ginseng, standard picture is set out, image pre-processing module adopts system
The original image of collection denoised, filtered, binary conversion treatment, for the purpose of the effect for improving test image, image detection module
Including connected region detection module and characteristic matching module, it is respectively used to the blank screen detection of screen and trembles screen detection, after image
Mainly the connected region and matching matrix that extract are compared with the threshold values in reliability examination criteria for reason module, sentence
The blank screen that occurs in disconnected screen trembles whether screen is abnormal.
The detection system of a display as described in the examples according to the present invention, provides a kind of detection side of display
Method includes the following steps:
1) camera calibration module, customizes scaling board as calibration object, by adjusting taking the photograph for calibration object or industrial camera 1
Image angle degree obtains the photo of calibration object different angle, extracts X-comers from photo to estimate ideally industrial phase
The internal reference of machine 1 and outer ginseng estimate the distortion factor under physical presence radial distortion using least square method, and use maximum-likelihood method
Estimation result is optimized, the precision of estimation is promoted；
2) image pre-processing module is acquired indicator screen image with industrial camera 1, is obtained and schemed using image pick-up card 2
As data, the image data of acquisition is denoised, is filtered and the pretreatment of binaryzation；
3) connected region detection module, pretreated image section carry out connection region detection, acquire largest connected area
Domain area obtains the ratio of connected region area and entire picture area；
4) post processing of image module, by the ratio of connected region area and entire picture area in reliability examination criteria
Threshold values is compared, and judges whether screen blank screen phenomenon occurs, if the fiducial value is greater than the threshold values, blank screen occurs in screen
Phenomenon obtains the pulse that picture flashes by the time occurred to blank screen phenomenon, and judges whether to belong to according to test stone
In unusual condition；
5) characteristic matching module, without the figure pretreatment stage in 2), and with 2) in image preprocessing regardless of elder generation
Sequence afterwards carries out feature point extraction to the screen original image of acquisition, using SIFT feature extraction method to two adjacent frame features
Point is matched, and the match point of mistake is rejected using RANSAC algorithm (RANSAC), and binding model parameter is surveyed
Matching degree between fixed adjacent two frames characteristic point, calculates correct match point number, obtains matching matrix；
6) threshold value in matching matrix and reliability examination criteria is compared by post processing of image module, when matching square
When battle array is greater than the threshold value in reliability examination criteria, it is believed that this two frames picture has shake.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (12)
1. the detection system of display, it is characterised in that: including image acquisition units and image processing unit, described image acquisition
Unit is acquired the image of tested display, transimission and storage works, and the graphics processing unit includes camera calibration mould
Block, image pre-processing module, image detection module and post processing of image module, the camera calibration module is for calculating ideal shape
The internal reference of monitoring camera and outer ginseng under state, set out standard picture, described image preprocessing module is to the original of system acquisition
Image denoised, filtered, binary conversion treatment, and to improve the effect of test image, described image detection module includes connected region
Domain detection module and characteristic matching module are respectively used to the blank screen detection of screen and tremble screen detection, described image post-processing module
The connected region and matching matrix that extract are compared with the threshold values in reliability examination criteria mainly, judged whether
Reliable sexual abnormality has occurred.
2. the detection system of display according to claim 1, it is characterised in that: described image acquisition unit includes monitoring
Camera, image pick-up card and computer, monitoring camera are monitored shooting, image pick-up card pair to the screen of display
The picture signal of monitoring shooting collects in computer, and is stored in the form of data file.
3. the detection system of display according to claim 2, it is characterised in that: the monitoring camera includes industrial phase
Machine.
4. the detection method of display according to claim 1 to 3, feature includes: to include the following steps,
S1 customizes a scaling board as calibration object and is demarcated by adjusting the camera angle of calibration object or monitoring camera
The photo of object different angle estimates the ideally internal reference of monitoring camera and outer ginseng using photo, then estimates and optimize real
There are the distortion factors under radial distortion on border；
S2, acquires indicator screen image with monitoring camera, image data is obtained using image pick-up card, to the image of acquisition
Data are pre-processed, and pretreated image section carries out connection region detection, acquire largest connected region area, the connection
Region area is compared with the fiducial value of entire picture area with threshold values in reliability examination criteria, judges whether screen occurs
Blank screen phenomenon obtains the pulse that picture flashes by the time occurred to blank screen phenomenon, and is according to test stone judgement
It is no to belong to unusual condition；
S3 carries out feature point extraction to the screen original image of acquisition, and two adjacent frame characteristic points is carried out Feature Points Matching,
Match point number is calculated, matching matrix is obtained, the threshold value in matching matrix and reliability examination criteria is compared, is judged
Two frame pictures are with the presence or absence of shake.
5. the detection method of display according to claim 4, it is characterised in that: sequencing is not present in S1 and S3.
6. the detection method of display according to claim 4, it is characterised in that: in S1, gridiron pattern is extracted from photo
Angle point estimates the ideally internal reference of monitoring camera and outer ginseng, estimates physical presence radial distortion using least square method
Under distortion factor, and estimation result is optimized with maximum-likelihood method, promotes the precision of estimation.
7. the detection method of display according to claim 4, it is characterised in that: in S2, the pretreatment of image includes pair
Image denoised, is filtered and binarization operation.
8. the detection method of display according to claim 4, it is characterised in that: in S2, if the fiducial value be greater than can
Threshold value in property examination criteria, then there is blank screen phenomenon in screen.
9. the detection method of display according to claim 4, it is characterised in that: in S3, use S I FT feature extraction
Method matches two adjacent frame characteristic points.
10. the detection method of display according to claim 4, it is characterised in that: in S3, use random sampling consistency
Algorithm (RANSAC) rejects the match point of mistake, and binding model parameter measures the matching journey between adjacent two frames characteristic point
Degree, calculates correct match point number.
11. the detection method of display according to claim 4, it is characterised in that: in S3, when matching matrix is greater than reliably
Property examination criteria in threshold value when, it is believed that this two frames picture exist shake.
12. a kind of computer readable storage medium is stored thereon with computer program, realization when described program is executed by processor
Such as the step of any one of claim 4-11 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811533505.9A CN109636793A (en) | 2018-12-14 | 2018-12-14 | The detection system and its detection method of display |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811533505.9A CN109636793A (en) | 2018-12-14 | 2018-12-14 | The detection system and its detection method of display |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636793A true CN109636793A (en) | 2019-04-16 |
Family
ID=66074089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811533505.9A Pending CN109636793A (en) | 2018-12-14 | 2018-12-14 | The detection system and its detection method of display |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636793A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102762A (en) * | 2020-09-30 | 2020-12-18 | 卡莱特（深圳）云科技有限公司 | Method and device for identifying abnormal light points of LED screen |
| CN112508894A (en) * | 2020-11-27 | 2021-03-16 | 江苏徐工工程机械研究院有限公司 | Spraying flame flow online detection method, device and system, industrial personal computer and storage medium |
| CN112731696A (en) * | 2020-12-29 | 2021-04-30 | 江苏奥斯汀光电科技股份有限公司 | Intelligent equipment for analyzing black picture light leakage problem of narrow and long vehicle-mounted liquid crystal screen |
| CN114910733A (en) * | 2022-07-15 | 2022-08-16 | 深圳益实科技有限公司 | Display fault intelligent diagnosis analysis system based on artificial intelligence |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458156A (en) * | 2013-08-27 | 2013-12-18 | 宁波海视智能系统有限公司 | Preprocessing method for traffic accident detection video signals on severe weather conditions |
| CN103473771A (en) * | 2013-09-05 | 2013-12-25 | 上海理工大学 | Method for calibrating camera |
| CN104408701A (en) * | 2014-12-03 | 2015-03-11 | 中国矿业大学 | Large-scale scene video image stitching method |
| CN105657548A (en) * | 2016-01-07 | 2016-06-08 | Tcl通力电子（惠州）有限公司 | Fault test method and system for video playing equipment |
| CN106231295A (en) * | 2016-08-04 | 2016-12-14 | 惠州市德赛西威汽车电子股份有限公司 | A kind of display screen image quality automatic checkout system, detection method and application thereof |
| CN106695792A (en) * | 2017-01-05 | 2017-05-24 | 中国计量大学 | Tracking and monitoring system and method of stacking robot based on machine vision |
| CN107103877A (en) * | 2017-05-15 | 2017-08-29 | 京东方科技集团股份有限公司 | Image element circuit and its driving method, display device |
| CN107330942A (en) * | 2017-06-20 | 2017-11-07 | 成都通甲优博科技有限责任公司 | A kind of calibrating template, scaling method, proving operation method and calibration system |
| CN107424196A (en) * | 2017-08-03 | 2017-12-01 | 江苏钜芯集成电路技术股份有限公司 | A kind of solid matching method, apparatus and system based on the weak more mesh cameras of demarcation |
| CN107977931A (en) * | 2017-12-14 | 2018-05-01 | 元橡科技（北京）有限公司 | Utilize the method for calibrated more mesh cameras generation super-resolution image |
| CN108288294A (en) * | 2018-01-17 | 2018-07-17 | 视缘(上海)智能科技有限公司 | A kind of outer ginseng scaling method of a 3D phases group of planes |
| CN108593989A (en) * | 2018-05-23 | 2018-09-28 | 国网天津市电力公司 | 10kV transformer efficiencies and current methods are calculated using ammeter pulse flicker interval |
| CN108632591A (en) * | 2018-04-04 | 2018-10-09 | 安徽海青智能科技有限公司 | A kind of blackboard information regeneration share system |
-
2018
- 2018-12-14 CN CN201811533505.9A patent/CN109636793A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458156A (en) * | 2013-08-27 | 2013-12-18 | 宁波海视智能系统有限公司 | Preprocessing method for traffic accident detection video signals on severe weather conditions |
| CN103473771A (en) * | 2013-09-05 | 2013-12-25 | 上海理工大学 | Method for calibrating camera |
| CN104408701A (en) * | 2014-12-03 | 2015-03-11 | 中国矿业大学 | Large-scale scene video image stitching method |
| CN105657548A (en) * | 2016-01-07 | 2016-06-08 | Tcl通力电子（惠州）有限公司 | Fault test method and system for video playing equipment |
| CN106231295A (en) * | 2016-08-04 | 2016-12-14 | 惠州市德赛西威汽车电子股份有限公司 | A kind of display screen image quality automatic checkout system, detection method and application thereof |
| CN106695792A (en) * | 2017-01-05 | 2017-05-24 | 中国计量大学 | Tracking and monitoring system and method of stacking robot based on machine vision |
| CN107103877A (en) * | 2017-05-15 | 2017-08-29 | 京东方科技集团股份有限公司 | Image element circuit and its driving method, display device |
| CN107330942A (en) * | 2017-06-20 | 2017-11-07 | 成都通甲优博科技有限责任公司 | A kind of calibrating template, scaling method, proving operation method and calibration system |
| CN107424196A (en) * | 2017-08-03 | 2017-12-01 | 江苏钜芯集成电路技术股份有限公司 | A kind of solid matching method, apparatus and system based on the weak more mesh cameras of demarcation |
| CN107977931A (en) * | 2017-12-14 | 2018-05-01 | 元橡科技（北京）有限公司 | Utilize the method for calibrated more mesh cameras generation super-resolution image |
| CN108288294A (en) * | 2018-01-17 | 2018-07-17 | 视缘(上海)智能科技有限公司 | A kind of outer ginseng scaling method of a 3D phases group of planes |
| CN108632591A (en) * | 2018-04-04 | 2018-10-09 | 安徽海青智能科技有限公司 | A kind of blackboard information regeneration share system |
| CN108593989A (en) * | 2018-05-23 | 2018-09-28 | 国网天津市电力公司 | 10kV transformer efficiencies and current methods are calculated using ammeter pulse flicker interval |
Non-Patent Citations (2)
| Title |
|---|
| 万刚 等编著: "《无人机测绘技术及应用》", 31 December 2015, 测绘出版社 * |
| 王佩军 等编著: "《摄影测量学》", 31 May 2016, 武汉大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102762A (en) * | 2020-09-30 | 2020-12-18 | 卡莱特（深圳）云科技有限公司 | Method and device for identifying abnormal light points of LED screen |
| CN112508894A (en) * | 2020-11-27 | 2021-03-16 | 江苏徐工工程机械研究院有限公司 | Spraying flame flow online detection method, device and system, industrial personal computer and storage medium |
| CN112508894B (en) * | 2020-11-27 | 2023-10-03 | 江苏徐工工程机械研究院有限公司 | Spraying flame flow online detection method, device and system, industrial personal computer and storage medium |
| CN112731696A (en) * | 2020-12-29 | 2021-04-30 | 江苏奥斯汀光电科技股份有限公司 | Intelligent equipment for analyzing black picture light leakage problem of narrow and long vehicle-mounted liquid crystal screen |
| CN114910733A (en) * | 2022-07-15 | 2022-08-16 | 深圳益实科技有限公司 | Display fault intelligent diagnosis analysis system based on artificial intelligence |
| CN114910733B (en) * | 2022-07-15 | 2022-09-30 | 深圳益实科技有限公司 | Display fault intelligent diagnosis analysis system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636793A (en) | The detection system and its detection method of display | |
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| CN109100370A (en) | A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis | |
| CN109886918A (en) | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice | |
| CN103308523B (en) | Method for detecting multi-scale bottleneck defects, and device for achieving method | |
| CN108663382A (en) | The method and device of the paper surface defects detection of view-based access control model conspicuousness | |
| CN109345524A (en) | A kind of bearing open defect detection system of view-based access control model | |
| CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN108827979A (en) | A kind of module group lens appearance detecting method | |
| CN106846304B (en) | Electrical equipment detection method and device based on infrared detection | |
| CN110378902A (en) | A kind of scratch detection method under strong noise background | |
| CN109813728A (en) | A kind of circuit board solder joint detection method and system | |
| CN109060842A (en) | Citrus detection method of surface flaw, computer program based on surface fitting correction | |
| CN108174198B (en) | Video image quality diagnosis analysis detection device and application system | |
| CN114820439A (en) | PCB bare board defect detection system and method based on AOI | |
| CN109409181A (en) | A kind of finger lower edges independent detection method referring to vein image for low quality | |
| CN111665199A (en) | Wire and cable color detection and identification method based on machine vision | |
| CN110321944A (en) | A kind of construction method of the deep neural network model based on contact net image quality evaluation | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN116703909A (en) | Intelligent detection method for production quality of power adapter | |
| CN207366475U (en) | A kind of relief pattern Online Video detection device | |
| CN116311211A (en) | Detection and identification method and system of gas detector and storage medium | |
| CN116380918A (en) | Defect detection method, device and equipment | |
| CN115100095B (en) | PCB detection method based on non-supervision algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |