CN109345524A - A kind of bearing open defect detection system of view-based access control model - Google Patents
A kind of bearing open defect detection system of view-based access control model Download PDFInfo
- Publication number
- CN109345524A CN109345524A CN201811126395.4A CN201811126395A CN109345524A CN 109345524 A CN109345524 A CN 109345524A CN 201811126395 A CN201811126395 A CN 201811126395A CN 109345524 A CN109345524 A CN 109345524A
- Authority
- CN
- China
- Prior art keywords
- bearing
- image
- pixel
- open defect
- detected
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
Abstract
The present invention provides a kind of bearing open defect detection system of view-based access control model, which includes: that bearing appearance images acquisition module for acquiring the image of bearing region to be detected in real time obtains an image set;Bearing appearance images preprocessing module is pre-processed for choosing an image from image set;Bearing external appearance characteristic extraction module, for extracting the external appearance characteristic parameter of bearing to be detected from pretreated image;Bearing open defect identification module, the standard external appearance characteristic parameter of external appearance characteristic parameter and the corresponding bearing prestored for treating detection bearing is matched, if matching degree, lower than the threshold value of setting, bearing to be detected has open defect, conversely, then bearing to be detected is without open defect.The present invention realizes the intelligence of bearing open defect detection, improves the removal rate of defect recognition rate, unqualified bearing products, also improves the overall quality of factory product.
Description
Technical field
The present invention relates to Bearing testing technical fields, and in particular to a kind of bearing open defect detection system of view-based access control model
System.
Background technique
The defects of a small amount of bearing outside surface has corrosion, scratches is had during Production of bearing and becomes waste product, substandard products,
These waste products, substandard products must be identified before factory, eliminate and.Traditional bearing surface defects detection is mainly carried out using artificial
Detection, it is easy to appear erroneous detection and missing inspection, not only low efficiency, shortage accuracy and standardization for artificial detection, and cannot will examine
Measured data classification is sent into computer in real time and carries out quality management.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of bearing open defect detection system of view-based access control model.
The purpose of the present invention is realized using following technical scheme:
A kind of bearing open defect detection system of view-based access control model, which includes bearing appearance
Image capture module, bearing appearance images preprocessing module, bearing external appearance characteristic extraction module and bearing open defect identify mould
Block.
Bearing appearance images acquisition module obtains an image for acquiring the image of bearing region to be detected in real time
Collection;Bearing appearance images preprocessing module is pre-processed for choosing an image from image set;Bearing external appearance characteristic mentions
Modulus block, for extracting the external appearance characteristic parameter of bearing to be detected from pretreated image;Bearing open defect identifies mould
The standard external appearance characteristic parameter of block, external appearance characteristic parameter and the corresponding bearing prestored for treating detection bearing is matched,
If matching degree has open defect lower than the threshold value of setting, bearing to be detected, conversely, then bearing to be detected is lacked without appearance
It falls into.
The invention has the benefit that the present invention realizes the intelligence of bearing open defect detection, defect knowledge is improved
Not rate, unqualified bearing products removal rate, also improve factory product overall quality;Simultaneously to the intelligence of bearing open defect
Energyization detection, also significantly reduces cost of labor, improves yield and efficiency.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is a kind of structure chart of bearing open defect detection system of the present invention;
Fig. 2 is the frame construction drawing of bearing appearance images preprocessing module 2.
Appended drawing reference: bearing appearance images acquisition module 1;Bearing appearance images preprocessing module 2;Bearing external appearance characteristic mentions
Modulus block 3;Bearing open defect identification module 4;Warning module 5;Cutting unit 6;Smooth unit 7;Spatial saliency value calculates
Subelement 8;Time significance value computation subunit 9;Conspicuousness merges subelement 10.
Specific embodiment
The invention will be further described with the following Examples.
Fig. 1 shows a kind of bearing open defect detection system of view-based access control model, the bearing open defect detection system packet
It includes outside bearing appearance images acquisition module 1, bearing appearance images preprocessing module 2, bearing external appearance characteristic extraction module 3 and bearing
See defect recognition module 4.
Bearing appearance images acquisition module 1 obtains an image for acquiring the image of bearing region to be detected in real time
Collection;Bearing appearance images preprocessing module 2 is pre-processed for choosing an image from image set;Bearing external appearance characteristic
Extraction module 3, for extracting the external appearance characteristic parameter of bearing to be detected from pretreated image;The identification of bearing open defect
Module 4, the standard external appearance characteristic parameter progress of external appearance characteristic parameter and the corresponding bearing prestored for treating detection bearing
Match, if matching degree is lower than the threshold value of setting, bearing to be detected has open defect, conversely, then bearing to be detected is without appearance
Defect.
The invention has the benefit that the present invention realizes the intelligence of bearing open defect detection, defect knowledge is improved
Not rate, unqualified bearing products removal rate, also improve factory product overall quality;Simultaneously to the intelligence of bearing open defect
Energyization detection, also significantly reduces cost of labor, improves yield and efficiency.
Preferably, bearing appearance images acquisition module 1 is CCD camera.
Preferably, which further includes warning module 5, warning module 5 and bearing open defect
Identification module 4 is connected, for when matching result show bearing to be detected with open defect, by warning module 5 to work
Personnel sound an alarm, and staff is reminded to reject the bearing for having open defect.
Preferably, referring to fig. 2, bearing appearance images preprocessing module 2 includes cutting unit 6 and smooth unit 7.
Cutting unit 6 is used to choose the image of t moment candid photograph from image set, and is split to image, obtain to
Detect bearing image;Smooth unit 7 is smoothed for treating detection bearing image, is removed in bearing image to be detected
Random noise.
Preferably, cutting unit 6 includes spatial saliency value computation subunit 8,9 and of time significance value computation subunit
Conspicuousness merges subelement 10.
Spatial saliency value computation subunit 8 is for the position according to pixel each in t moment image, color characteristic
With the distribution situation of pixel, the spatial saliency value of all pixels point in image is calculated.
Time significance value computation subunit 9 be used for by optical flow method calculate t moment image sports ground, and according to must
The sports ground arrived calculates the time significance value of all pixels point in image using following formula, wherein pixel in t moment image
The calculating formula of the time significance value of point a are as follows:
In formula, HtiIt (a) is the time significance value of pixel a in t moment image, D (Ma,Mw) it is pixel a and picture
The light stream vectors difference of vegetarian refreshments w, | | it indicates to take the amplitude of light stream vectors, pixel w is to remove pixel in t moment image
Any pixel point of a, Ω are the set that all pixels point is constituted in t moment image.
Conspicuousness merges subelement 10 based on to spatial saliency computing module 8 and time conspicuousness computing module 9
It calculates result and carries out fusion treatment, obtain the synthesis significance value of all pixels point in t moment image;Comprehensive significance value is used for
Judge whether the pixel in the image belongs to the pixel of bearing to be detected, deterministic process are as follows: as H (r) >=λ, then as
Vegetarian refreshments r belongs to foreground image pixel, and as H (r) < λ, pixel r belongs to the pixel of background image, and wherein H (r) is t
The synthesis significance value of pixel r in moment image, λ are the threshold values of setting, traverse all pixels point in t moment image, institute
The set for having the pixel for belonging to foreground image to constitute is bearing image to be detected.
Preferably, according to the position of pixel each in t moment image, the distribution situation of color characteristic and pixel,
Calculate the spatial saliency value of all pixels point in image, wherein the spatial saliency value of pixel p can in t moment image
It is calculate by the following formula to obtain:
In formula, Hsp(p) be pixel p in t moment image spatial saliency value, Hsl(p) be description pixel p with
The significance value of spatial position degree of restraint in t moment image between residual pixel point;HcolIt (p) is description and pixel p
Red green, blue/yellow relevant significance value of comparison chromatic value;Hsd(p) be pixel p similitude distribution significance value,
ν1、ν2It is weight factor, respectively indicates Hcol(p) and Hsd(p) significance level when calculating the spatial saliency value of pixel p,
α is penalty coefficient, for compensating the bearing local environment bring collimation error to be detected.
The utility model has the advantages that will be by H according to above formulasl(p)、Hcol(p) and Hsd(p) it is merged, obtains description t moment image
Pixel p spatial saliency value, on the one hand spatial position based on pixel each in image, color are special for the fusion method
It seeks peace the distribution situation of pixel, does not depend on the understanding of the mankind, eliminate artificial detection bring individual difference, on the other hand should
Method also can be more uniform highlight bearing region to be detected in the image, be conducive to it is subsequent image is carried out it is effective
Segmentation so that it is subsequent treat detection bearing carry out defects detection when, it is only necessary to analyze the bearing image to be detected being partitioned into, mention
The high rate of follow-up processing, alleviates the workload of the system, extends the service life of the system, and by setting
It setsThis, so that work as red green, blue/yellow enhancing of comparison coloration or pixel of pixel
When similitude distribution is compact, more attentions can be attracted, be conducive to be partitioned into bearing image to be detected.
Preferably, for describing the spatial position degree of restraint in pixel p and t moment image between residual pixel point
Significance value can be calculate by the following formula to obtain:
In formula, HslIt (p) is the space constraint degree described in pixel p and t moment image between residual pixel point
Significance value, A are normalization coefficients, | | p-q | | it is the space Euclidean distance between pixel p and pixel q, IpIt is pixel
The CIELAB color value of p, IqIt is the CIELAB color value of pixel q, | | Ip-Iq| | indicate IpAnd IqBetween Euclidean distance, xp、
ypIt is the abscissa and ordinate of pixel p, x respectivelyq、yqIt is the abscissa and ordinate of pixel q respectively, Ω is t moment
The set that all pixels point is constituted in image.
The utility model has the advantages that in above formula,The influence of space length between pixel is reflected,The periphery pixel of pixel p is reflected to Hsl(p) percentage contribution, by adopting
H is calculated with above formulasl(p), which can highlight the edge feature of bearing to be detected in the image, while inhibit to belong in the image
In the reduction of bearing pixel to be detected.
Preferably, for describing significance value H relevant to red green, blue/yellow comparison chromatic value of pixel pcol(p)
It can be calculate by the following formula to obtain:
In formula, HcolIt (p) is description significance value relevant to red green, blue/yellow comparison chromatic value of pixel p, RG
(p), BY (p) respectively indicates red green, blue/yellow comparison chromatic value of pixel p, and RG (q), BY (q) respectively indicate pixel q
Red green, blue/yellow comparison chromatic value, NtRepresent the pixel number in t moment image, wherein pixel p it is red green,
Blue/yellow comparison chromatic value can be obtained by following formula:
In formula, r (p) is the value of the r component of pixel p, and g (p) is the value of the g component of pixel p, and b (p) is pixel p
The value of component.
The utility model has the advantages that in view of the corticocerebral neuron of human vision is to the two red green, blue/yellow comparison colour responses
It is most strong, it is based on this, inventor proposes each in t moment image to measure with the two red green, blue/yellow comparison chromatic values
The significant characteristics of pixel, it is convex well which obtain the Bearing inner region to be detected in the frame video image
It is aobvious, be conducive to the subsequent open defect for treating detection bearing and detected.
Preferably, Hsd(p) it can be calculate by the following formula to obtain:
In formula, Hsd(p) be pixel p similitude distribution significance value, B is normalization coefficient, χp,qFor measuring picture
The similitude of color between vegetarian refreshments p and pixel q.
The utility model has the advantages that for any pixel point p inside t moment image axis to be detected can be belonged to using above formula
The pixel held distributes higher significance value, and then reaches the significance value for strengthening the pixel of affiliated bearing to be detected, and
The significance value of background parts is weakened, to be partitioned into complete bearing image to be detected from the image, is treated for subsequent
The open defect of detection bearing is detected.
Preferably, the calculated result to spatial saliency computing module 8 and time conspicuousness computing module 9 is melted
Conjunction processing, obtains the synthesis significance value of all pixels point in t moment image, specifically, to the spatial saliency of pixel p
Value and time significance value, which carry out fusion, to be realized using the fusion formula of lower section:
H (p)=[Hsp(p)]∈+[Hti(p)]1-∈
In formula, H (p) is the synthesis significance value of pixel p, and ∈ is regulatory factor, and meets 0 < ∈ < 1;
The utility model has the advantages that being carried out using spatial saliency value and time significance value of the fusion formula above to pixel p
Fusion, which not only allows for the influence of spatial saliency, such as the position of pixel, color characteristic and distribution situation,
The influence of significant factors on time shaft is had also contemplated simultaneously, such as camera is mobile, bearing to be detected is mobile.The blending algorithm has
Conducive to the accuracy for the synthesis significance value for improving each pixel, and then the accurate segmentation to the image is realized, convenient for subsequent
The open defect for treating detection bearing is detected, while also reducing the complexity of subsequent processes.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of bearing open defect detection system of view-based access control model, which is characterized in that including bearing appearance images acquisition module,
Bearing appearance images preprocessing module, bearing external appearance characteristic extraction module and bearing open defect identification module;
The bearing appearance images acquisition module obtains an image for acquiring the image of bearing region to be detected in real time
Collection;
The bearing appearance images preprocessing module, for concentrating one image of selection to be pre-processed from described image;
The bearing external appearance characteristic extraction module, the external appearance characteristic for extracting bearing to be detected from pretreated image are joined
Number;
The bearing open defect identification module, for treating the external appearance characteristic parameter of detection bearing and the corresponding bearing prestored
Standard external appearance characteristic parameter is matched, if matching degree, lower than the threshold value of setting, bearing to be detected has open defect, instead
It, then bearing to be detected is without open defect.
2. bearing open defect detection system according to claim 1, which is characterized in that the bearing appearance images acquisition
Module is CCD camera.
3. bearing open defect detection system according to claim 1, which is characterized in that it further include warning module, it is described
Warning module is connected with the bearing open defect identification module, for showing that bearing to be detected is lacked with appearance when matching result
It when falling into, is sounded an alarm by the warning module to staff, staff is reminded to reject the bearing for having open defect.
4. bearing open defect detection system according to claim 1, which is characterized in that the bearing appearance images are located in advance
Managing module includes cutting unit and smooth unit;
The cutting unit for concentrating the image choosing t moment and capturing from described image, and divides described image
It cuts, obtains bearing image to be detected;
The smooth unit removes the bearing image to be detected for being smoothed to the bearing image to be detected
In random noise.
5. bearing open defect detection system according to claim 4, which is characterized in that the cutting unit includes space
Significance value computation subunit, time significance value computation subunit and conspicuousness merge subelement;
The spatial saliency value computation subunit, for the position according to pixel each in t moment image, color characteristic
With the distribution situation of pixel, the spatial saliency value of all pixels point in image is calculated;
The time significance value computation subunit, for the sports ground by optical flow method calculating t moment image, and according to
The sports ground arrived calculates the time significance value of all pixels point in described image using following formula, wherein in t moment image
The calculating formula of the time significance value of pixel a are as follows:
In formula, HtiIt (a) is the time significance value of pixel a in t moment image, D (Ma, Mw) it is pixel a and pixel w
Light stream vectors difference, | | indicate to take the amplitudes of the light stream vectors, pixel w is removing pixel a in t moment image
Any pixel point, Ω be t moment image in all pixels point constitute set;
The conspicuousness merges subelement, for the spatial saliency computing module and the time conspicuousness computing module
Calculated result carry out fusion treatment, obtain the synthesis significance value of all pixels point in the t moment image;The synthesis
Significance value is for judging whether the pixel in the image belongs to the pixel of bearing to be detected, deterministic process are as follows: works as H
(r) >=λ when, then pixel r belongs to foreground image pixel, and as H (r) < λ, pixel r belongs to the pixel of background image,
Wherein H (r) is the synthesis significance value of pixel r in t moment image, and λ is the threshold value of setting, is traversed in t moment image
All pixels point, the set that all pixels for belonging to foreground image are constituted is bearing image to be detected.
6. bearing open defect detection system according to claim 5, which is characterized in that described according to t moment image
In the position of each pixel, color characteristic and pixel distribution situation, calculate the significant spatial of all pixels point in image
Property value, wherein the spatial saliency value of pixel p can be calculate by the following formula to obtain in t moment image:
In formula, Hsp(p) be pixel p in t moment image spatial saliency value, HslIt (p) is when describing pixel p and t
The significance value of spatial position degree of restraint in needle drawing picture between residual pixel point;Hcol(p) be description with pixel p it is red/
Green, blue/yellow relevant significance value of comparison chromatic value;Hsd(p) be pixel p similitude distribution significance value, v1、v2
It is weight factor, respectively indicates Hcol(p) and Hsd(p) significance level when calculating the spatial saliency value of pixel p, α are to mend
Coefficient is repaid, for compensating the bearing local environment bring collimation error to be detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811126395.4A CN109345524A (en) | 2018-09-26 | 2018-09-26 | A kind of bearing open defect detection system of view-based access control model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811126395.4A CN109345524A (en) | 2018-09-26 | 2018-09-26 | A kind of bearing open defect detection system of view-based access control model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109345524A true CN109345524A (en) | 2019-02-15 |
Family
ID=65306572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811126395.4A Withdrawn CN109345524A (en) | 2018-09-26 | 2018-09-26 | A kind of bearing open defect detection system of view-based access control model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109345524A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239083A (en) * | 2018-09-26 | 2019-01-18 | 深圳源广安智能科技有限公司 | A kind of cable surface defects detection system based on unmanned plane |
CN109871895A (en) * | 2019-02-22 | 2019-06-11 | 北京百度网讯科技有限公司 | The defect inspection method and device of circuit board |
CN111091557A (en) * | 2019-12-12 | 2020-05-01 | 哈尔滨市科佳通用机电股份有限公司 | Method and system for detecting breakage fault of flange of bearing saddle of railway wagon |
CN111507177A (en) * | 2020-02-19 | 2020-08-07 | 广西云涌科技有限公司 | Identification method and device for metering turnover cabinet |
CN111729775A (en) * | 2020-05-13 | 2020-10-02 | 苏州明池纺织科技有限公司 | Fabric coating multilayer structure manufacturing regulation and control system |
CN112834517A (en) * | 2020-12-31 | 2021-05-25 | 慈溪迅蕾轴承有限公司 | Bearing appearance image detection method |
CN115493843A (en) * | 2022-11-18 | 2022-12-20 | 聊城市义和轴承配件有限公司 | Quality monitoring method and equipment based on bearing retainer |
-
2018
- 2018-09-26 CN CN201811126395.4A patent/CN109345524A/en not_active Withdrawn
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239083A (en) * | 2018-09-26 | 2019-01-18 | 深圳源广安智能科技有限公司 | A kind of cable surface defects detection system based on unmanned plane |
CN109871895A (en) * | 2019-02-22 | 2019-06-11 | 北京百度网讯科技有限公司 | The defect inspection method and device of circuit board |
CN111091557A (en) * | 2019-12-12 | 2020-05-01 | 哈尔滨市科佳通用机电股份有限公司 | Method and system for detecting breakage fault of flange of bearing saddle of railway wagon |
CN111091557B (en) * | 2019-12-12 | 2020-07-31 | 哈尔滨市科佳通用机电股份有限公司 | Method and system for detecting breakage fault of flange of bearing saddle of railway wagon |
CN111507177A (en) * | 2020-02-19 | 2020-08-07 | 广西云涌科技有限公司 | Identification method and device for metering turnover cabinet |
CN111729775A (en) * | 2020-05-13 | 2020-10-02 | 苏州明池纺织科技有限公司 | Fabric coating multilayer structure manufacturing regulation and control system |
CN112834517A (en) * | 2020-12-31 | 2021-05-25 | 慈溪迅蕾轴承有限公司 | Bearing appearance image detection method |
CN112834517B (en) * | 2020-12-31 | 2024-01-16 | 慈溪迅蕾轴承有限公司 | Image detection method for bearing appearance |
CN115493843A (en) * | 2022-11-18 | 2022-12-20 | 聊城市义和轴承配件有限公司 | Quality monitoring method and equipment based on bearing retainer |
CN115493843B (en) * | 2022-11-18 | 2023-03-10 | 聊城市义和轴承配件有限公司 | Quality monitoring method and equipment based on bearing retainer |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109345524A (en) | A kind of bearing open defect detection system of view-based access control model | |
CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
Schmugge et al. | Detection of cracks in nuclear power plant using spatial-temporal grouping of local patches | |
CN109490316A (en) | A kind of surface defects detection algorithm based on machine vision | |
CN109550712A (en) | A kind of chemical fiber wire tailfiber open defect detection system and method | |
CN101957325A (en) | Substation equipment appearance abnormality recognition method based on substation inspection robot | |
CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
CN109255785A (en) | A kind of bearing open defect detection system | |
CN107742307A (en) | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method | |
CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
CN108827979A (en) | A kind of module group lens appearance detecting method | |
CN108537143B (en) | A kind of face identification method and system based on key area aspect ratio pair | |
CN109146859A (en) | A kind of pavement crack detection system based on machine vision | |
CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
CN109886932A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on SVM | |
CN110096980A (en) | Character machining identifying system | |
CN110335233A (en) | Express-way guard-rail plates defect detecting system and method based on image processing techniques | |
CN105844282B (en) | A method of atomizer O-Ring defect is detected with line scan camera | |
CN109117855A (en) | Abnormal power equipment image identification system | |
CN113688817A (en) | Instrument identification method and system for automatic inspection | |
CN109636793A (en) | The detection system and its detection method of display | |
CN115018785A (en) | Hoisting steel wire rope tension detection method based on visual vibration frequency identification |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190215 |