CN109255785A - A kind of bearing open defect detection system - Google Patents

A kind of bearing open defect detection system Download PDF

Info

Publication number
CN109255785A
CN109255785A CN201811126357.9A CN201811126357A CN109255785A CN 109255785 A CN109255785 A CN 109255785A CN 201811126357 A CN201811126357 A CN 201811126357A CN 109255785 A CN109255785 A CN 109255785A
Authority
CN
China
Prior art keywords
bearing
image
infrared
detected
denoising
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Withdrawn
Application number
CN201811126357.9A
Other languages
Chinese (zh)
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Source Guang'an Intelligent Technology Co Ltd
Original Assignee
Shenzhen Source Guang'an Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Source Guang'an Intelligent Technology Co Ltd filed Critical Shenzhen Source Guang'an Intelligent Technology Co Ltd
Priority to CN201811126357.9A priority Critical patent/CN109255785A/en
Publication of CN109255785A publication Critical patent/CN109255785A/en
Withdrawn legal-status Critical Current

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
    • G01N21/8806—Specially adapted optical and illumination features
    • 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
    • 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
    • G06T2207/10048—Infrared 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
    • 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
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • 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
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The present invention provides a kind of bearing open defect detection system, which includes: the infrared polarization image and infrared intensity image that image capture module obtains bearing image to be detected；Image denoising module carries out denoising to infrared polarization image and infrared intensity image respectively；Image co-registration module to after denoising infrared polarization image and infrared intensity image merge, obtain the blending image of bearing to be detected；Bearing external appearance characteristic extraction module extracts the external appearance characteristic information of bearing to be detected from blending image, obtains the external appearance characteristic vector of bearing to be detected；The standard external appearance characteristic vector for the corresponding bearing that bearing open defect identification module is prestored according to the external appearance characteristic vector sum of bearing to be detected judges bearing to be detected with the presence or absence of 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

A kind of bearing open defect detection system
Technical field
The present invention relates to Bearing testing technical fields, and in particular to a kind of bearing open defect detection 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.
The purpose of the present invention is realized using following technical scheme:
A kind of bearing open defect detection system, the detection system include image capture module, image denoising module, image Fusion Module, bearing external appearance characteristic extraction module and bearing open defect identification module；Image capture module, it is to be checked for obtaining Survey the infrared polarization image and infrared intensity image of bearing image；Image denoising module, for respectively to infrared polarization image and Infrared intensity image carries out denoising, infrared polarization image and infrared intensity image after being denoised；Image co-registration module, For to after denoising infrared polarization image and infrared intensity image merge, obtain the blending image of bearing to be detected；Axis External appearance characteristic extraction module is held, for extracting the external appearance characteristic information of bearing to be detected from blending image, obtains axis to be detected The external appearance characteristic vector held；Bearing open defect identification module, for being prestored according to the external appearance characteristic vector sum of bearing to be detected Corresponding bearing standard external appearance characteristic vector, judge bearing to be detected with the presence or absence of open 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.
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 the structure chart of bearing open defect detection system of the present invention；
Fig. 2 is the frame construction drawing of image co-registration module；
Fig. 3 is the frame construction drawing of high-frequency sub-band coefficient integrated unit.
Appended drawing reference: image capture module 1；Image denoising module 2；Image co-registration module 3；Bearing external appearance characteristic extracts mould Block 4；Bearing open defect identification module 5；Alarm module 6；NSCT converter unit 7；Low frequency sub-band coefficient integrated unit 8；High frequency Sub-band coefficients integrated unit 9；NSCT inverse transformation unit 10；Liveness computation subunit 11；Collocation degree computation subunit 12；Decision Merge subelement 13.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of bearing open defect detection system, the detection system includes image capture module 1, image denoising Module 2,5. image capture module of image co-registration module 3, bearing external appearance characteristic extraction module 4 and bearing open defect identification module 1, for obtaining the infrared polarization image and infrared intensity image of bearing image to be detected；Image denoising module 2, for right respectively Infrared polarization image and infrared intensity image carry out denoising, infrared polarization image and infrared plot of light intensity after being denoised Picture；Image co-registration module 3, for after denoising infrared polarization image and infrared intensity image merge, obtain to be detected The blending image of bearing；Bearing external appearance characteristic extraction module 4, for extracting the external appearance characteristic of bearing to be detected from blending image Information obtains the external appearance characteristic vector of bearing to be detected；Bearing open defect identification module 5, for according to bearing to be detected The standard external appearance characteristic vector for the corresponding bearing that external appearance characteristic vector sum prestores judges that bearing to be detected is lacked with the presence or absence of appearance It falls into.
The utility model has the advantages that realizing the intelligence of bearing open defect detection, defect recognition rate is improved, unqualified bearing produces The removal rate of product also improves the overall quality of factory product；Simultaneously to the intellectualized detection of bearing open defect, also subtract significantly Small cost of labor, improves yield and efficiency.
Preferably, which further includes warning module 6, warning module 6 and 5 phase of bearing open defect identification module Even, for passing through mould of alarming when the judging result of bearing open defect identification module 5 is that bearing to be detected has open defect Block 6 is sounded an alarm to staff, and staff is reminded to reject the bearing for having open defect.
Preferably, image capture module 1 includes infrared polarization camera and thermal infrared imager, and infrared polarization camera is for obtaining The infrared polarization image of bearing to be detected, thermal infrared imager are used to obtain the infrared intensity image of bearing to be detected.
Preferably, described that denoising is carried out to infrared polarization image and infrared intensity image, it is infrared after being denoised Polarization image and infrared intensity image, specifically:
(1) the attenuation degree value of each pixel gray value in the infrared polarization image is calculated using attenuation function, In, the attenuation function are as follows:
In formula, h (x, y) is attenuation function, and indicates coordinate is the attenuation degree value of the pixel p gray value of (x, y), and θ is The lower limit value of attenuation function, α, ε are the shape control constant of attenuation curve,For centered on pixel p (x, y), size M The mean value of all pixels point gray value, g (x, y) are the gray values of pixel p (x, y) in × M rectangular window；
(2) according to the gray value attenuation degree value of obtained each pixel, each pixel is calculated using following formula and is denoised Gray value afterwards, the set that all denoising pixel gray values are constituted are the infrared polarization image after denoising；Wherein, pixel Gray value after p (x, y) denoising are as follows:
In formula,For the gray value at the pixel p (x, y) after denoising, gp(x, y) is the infrared polarization figure Gray value as at pixel p (x, y)；hp(x, y) is the attenuation degree value of pixel p gray value；
(3) the infrared intensity image is denoised using step 1 and step 2, the infrared light after denoising can be obtained Strong image.
The utility model has the advantages that successively calculating each pixel gray value in infrared polarization image and intensity image using attenuation function Attenuation degree value, before which not only allows for denoising in image pixel gray value, while having also contemplated its square Other pixels filter out random noise to that need to denoise this influence factor of pixel so as to adaptive in shape window, To which it is high to obtain clarity while retaining the marginal information in infrared polarization image and infrared intensity image, texture information Denoising after infrared polarization image and infrared intensity image.
Preferably, as shown in Fig. 2, image co-registration module 3 includes NSCT converter unit 7, low frequency sub-band coefficient integrated unit 8, high-frequency sub-band coefficient integrated unit 9 and NSCT inverse transformation unit 10.
NSCT converter unit 7 is used to the infrared polarization image after denoising and infrared intensity image carrying out NSCT change respectively It changes, the sub-band coefficients of infrared polarization image and infrared intensity image after respectively obtaining denoising, which includes low frequency Band coefficient and high-frequency sub-band coefficient；
Low frequency sub-band coefficient integrated unit 8 is used for the low frequency according to infrared polarization image and infrared intensity image after denoising Sub-band coefficients calculate the low frequency sub-band coefficient of blending image using average weighted algorithm；
High-frequency sub-band coefficient integrated unit 9 is used for the high frequency according to infrared polarization image and infrared intensity image after denoising Sub-band coefficients calculate the high-frequency sub-band coefficient of blending image based on Algorithm of Multi-scale Fusion；
NSCT inverse transformation unit 10 is used for according to low frequency sub-band coefficient integrated unit 8 and high-frequency sub-band coefficient integrated unit 9 The low frequency sub-band coefficient and high-frequency sub-band coefficient of resulting blending image carry out NSCT inverse transformation, obtain blending image.
Preferably, according to the low frequency sub-band coefficient of infrared polarization image and infrared intensity image after denoising, using average Weighting algorithm calculates the low frequency sub-band coefficient of blending image, specifically being calculated using average weighted algorithm every in blending image The low frequency sub-band coefficient of a pixel, wherein the low frequency sub-band coefficient of pixel (m, n) in blending imageIt is as follows:
In formula,It is the low frequency sub-band coefficient of the infrared polarization image after denoising,It is after denoising The low frequency sub-band coefficient of infrared intensity image.
Preferably, as shown in figure 3, high-frequency sub-band coefficient integrated unit 9 includes liveness computation subunit 11, collocation degree meter Operator unit 12 and Decision fusion subelement 13.
Liveness computation subunit 11, for high frequency according to infrared polarization image and infrared intensity image after denoising Band coefficient, the high-frequency sub-band coefficient of each pixel of infrared polarization image and infrared intensity image after calculating denoising enliven Angle value, wherein for the infrared polarization image and each pixel of infrared intensity image after denoising, calculate each picture according to the following formula Each high-frequency sub-band coefficient of vegetarian refreshments enlivens angle value:
In formula,High-frequency sub-band coefficient for pixel (a, b) in the infrared polarization image after denoising enlivens Angle value,High-frequency sub-band coefficient for pixel (a, b) in the infrared intensity image after denoising enlivens angle value, N × Q For the Size of Neighborhood of preset pixel (a, b), P is the neighborhood of pixel (a, b), and (a ', b ') is the neighborhood of pixel (a, b) Interior any pixel point, wpol(a ', b ') be denoising after infrared polarization image in weight of the pixel (a ', b ') in neighborhood, wint(a ', b ') is weight of the pixel (a ', b ') in neighborhood in infrared intensity image after denoising, wherein wpol(a′,b′) =wint(a ', b '), and meet ∑(a′,b′)∈Pwpol(a ', b ')=1,For picture in the infrared polarization image after denoising High-frequency sub-band coefficient of the vegetarian refreshments (a ', b ') on j scale, the direction k,For picture in the infrared intensity image after denoising High-frequency sub-band coefficient of the vegetarian refreshments (a ', B ') on j scale, the direction k.
The utility model has the advantages that enlivening angle value by calculating high-frequency sub-band coefficient, this, which enlivens angle value, can measure corresponding high frequency Significance degree with coefficient, while solving when enlivening angle value of each high-frequency sub-band coefficient, it is contemplated that position (a, b) in image Neighborhood window in influence of the high-frequency sub-band coefficient to high-frequency sub-band coefficient liveness at position (a, b) at other positions, make Obtaining each high-frequency sub-band coefficient adaptive can be adjusted, and can more accurately describe the aobvious of each high-frequency sub-band coefficient Work degree is conducive to the subsequent high-frequency sub-band coefficient for solving blending image.
Matching degree computation subunit 12, for high frequency according to infrared polarization image and infrared intensity image after denoising Band coefficient calculates matching of the high-frequency sub-band coefficient in each pixel of infrared polarization image and infrared intensity image after denoising Angle value, whereinWithThe calculating formula of matching angle value at pixel (a, b) are as follows:
In formula, mj,k(a, b) is indicated at pixel (a, b)WithMatching angle value.
The utility model has the advantages that the matching degree computation subunit 12 considers in two images high-frequency sub-band coefficient at same position Matching degree, the way more remain marginal information and texture information in two images, while being conducive in subsequent The useful letter in infrared polarization image and infrared intensity image while being merged, after capable of effectively integrating denoising Breath, improves subsequent syncretizing effect.
Decision fusion subelement 13, based on being obtained to liveness computation subunit 11 and matching degree computation subunit 12 It calculates result and carries out comprehensive analysis and judgement, and to the high-frequency sub-band coefficient of infrared polarization image and infrared intensity image after denoising It is merged, obtains the high-frequency sub-band coefficient of blending image, wherein pixel (a, b) is in j scale, the direction k in blending image On high-frequency sub-band coefficient can be obtained using the fusion formula of lower section:
In formula,For the high-frequency sub-band system on j scale, the direction k in blending image at pixel (a, b) Number,For the high-frequency sub-band coefficient on j scale, the direction k at the infrared polarization picture position (a, b) after denoising Weight coefficient, ρ are the matching degree threshold value of setting.
The utility model has the advantages that by the matching degree threshold value of setting, to the infrared polarization image after the denoising of pending fusion treatment Judged with the matching degree of infrared intensity image, when matching degree is greater than the threshold value of setting, further using active Angle value further judges, the way can significant information in reserved high-frequency sub-band coefficients, while after further suppressing denoising Infrared polarization image and infrared intensity image in residual noise bring interference.Improve to infrared polarization image after denoising and The syncretizing effect of infrared intensity image improves the subsequent discrimination identified to bearing open defect, unqualified bearing products Removal rate, also improve factory product overall quality.
Preferably, the standard external appearance characteristic of the corresponding bearing prestored according to the external appearance characteristic vector sum of bearing to be detected to Amount judges that bearing to be detected whether there is open defect, specifically, ifThen bearing to be detected has appearance Defect, conversely, then bearing to be detected is without open defect, whereinFor the external appearance characteristic vector of bearing to be detected,To prestore Corresponding bearing standard external appearance characteristic vector,For the similarity factor of setting.
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 (5)

1. a kind of bearing open defect detection system, which is characterized in that including image capture module, image denoising module, image Fusion Module, bearing external appearance characteristic extraction module and bearing open defect identification module；
Described image acquisition module, for obtaining the infrared polarization image and infrared intensity image of bearing image to be detected；
Described image denoises module, for carrying out denoising to the infrared polarization image and infrared intensity image respectively, obtains Infrared polarization image and infrared intensity image after to denoising；
Described image Fusion Module, for after the denoising infrared polarization image and infrared intensity image merge, obtain To the blending image of bearing to be detected；
The bearing external appearance characteristic extraction module, for extracting the external appearance characteristic of the bearing to be detected from the blending image Information obtains the external appearance characteristic vector of the bearing to be detected；
The bearing open defect identification module, it is corresponding for being prestored according to the external appearance characteristic vector sum of the bearing to be detected The standard external appearance characteristic vector of bearing judges bearing to be detected with the presence or absence of open defect.
2. 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 working as the judgement knot of the bearing open defect identification module When fruit is that the bearing to be detected has open defect, is sounded an alarm by the alarm module to staff, remind work Personnel reject the bearing for having open defect.
3. bearing open defect detection system according to claim 1, which is characterized in that described image acquisition module includes Infrared polarization camera and thermal infrared imager, the infrared polarization camera are used to obtain the infrared polarization image of bearing to be detected, institute Thermal infrared imager is stated for obtaining the infrared intensity image of bearing to be detected.
4. bearing open defect detection system according to claim 1, which is characterized in that it is described to infrared polarization image and Infrared intensity image progress denoising, infrared polarization image and infrared intensity image after being denoised, specifically:
(1) the attenuation degree value of each pixel gray value in the infrared polarization image is calculated using attenuation function, wherein institute State attenuation function are as follows:
In formula, h (x, y) is attenuation function, and indicates coordinate is the attenuation degree value of the pixel p gray value of (x, y), and θ is decaying The lower limit value of function, α, ε are the shape control constant of attenuation curve,For centered on pixel p (x, y), size is M × M square The mean value of all pixels point gray value, g (x, y) are the gray values of pixel p (x, y) in shape window；
(2) according to the gray value attenuation degree value of obtained each pixel, after calculating each pixel denoising using following formula Gray value, the set that all denoising pixel gray values are constituted are the infrared polarization image after denoising；Wherein, pixel p (x, Y) gray value after denoising are as follows:
In formula,For the gray value at the pixel p (x, y) after denoising, gp(x, y) is picture in the infrared polarization image Gray value at vegetarian refreshments p (x, y)；hp(x, y) is the attenuation degree value of pixel p gray value；
(3) the infrared intensity image is denoised using step 1 and step 2, the infrared plot of light intensity after denoising can be obtained Picture.
5. bearing open defect detection system according to claim 1, which is characterized in that described according to the axis to be detected The standard external appearance characteristic vector for the corresponding bearing that the external appearance characteristic vector sum held prestores judges bearing to be detected with the presence or absence of appearance Defect, specifically, ifThen bearing to be detected has open defect, conversely, then bearing to be detected is lacked without appearance It falls into, whereinFor the external appearance characteristic vector of bearing to be detected,Standard external appearance characteristic vector for the corresponding bearing prestored, For the similarity factor of setting.
CN201811126357.9A 2018-09-26 2018-09-26 A kind of bearing open defect detection system Withdrawn CN109255785A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811126357.9A CN109255785A (en) 2018-09-26 2018-09-26 A kind of bearing open defect detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811126357.9A CN109255785A (en) 2018-09-26 2018-09-26 A kind of bearing open defect detection system

Publications (1)

Publication Number Publication Date
CN109255785A true CN109255785A (en) 2019-01-22

Family

ID=65047912

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811126357.9A Withdrawn CN109255785A (en) 2018-09-26 2018-09-26 A kind of bearing open defect detection system

Country Status (1)

Country Link
CN (1) CN109255785A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110132983A (en) * 2019-05-28 2019-08-16 朱清 A kind of online hierarchical detection device and method of injecting products
CN110174408A (en) * 2019-06-12 2019-08-27 复旦大学 A kind of increasing material manufacturing process senses off-axis monitoring system more
CN110441312A (en) * 2019-07-30 2019-11-12 上海深视信息科技有限公司 A kind of surface defects of products detection system based on multispectral imaging
CN114612384A (en) * 2022-01-30 2022-06-10 扬州长青树体育用品有限公司 Method and system for detecting defects of appearance material of sport protector
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

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110132983A (en) * 2019-05-28 2019-08-16 朱清 A kind of online hierarchical detection device and method of injecting products
CN110174408A (en) * 2019-06-12 2019-08-27 复旦大学 A kind of increasing material manufacturing process senses off-axis monitoring system more
CN110441312A (en) * 2019-07-30 2019-11-12 上海深视信息科技有限公司 A kind of surface defects of products detection system based on multispectral imaging
CN114612384A (en) * 2022-01-30 2022-06-10 扬州长青树体育用品有限公司 Method and system for detecting defects of appearance material of sport protector
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
CN109255785A (en) A kind of bearing open defect detection system
CN110268190B (en) Underground pipe gallery leakage detection method based on static infrared thermography processing
CN108009531B (en) Multi-strategy anti-fraud face recognition method
CN109870461B (en) Electronic components quality detection system
WO2016107474A1 (en) Vehicle checking method and system
CN109684925B (en) Depth image-based human face living body detection method and device
CN109490316A (en) A kind of surface defects detection algorithm based on machine vision
CN106023185A (en) Power transmission equipment fault diagnosis method
CN104851086B (en) A kind of image detecting method for cable surface defect
CN109345524A (en) A kind of bearing open defect detection system of view-based access control model
CN111650205B (en) Part surface defect detection method and system based on structured light image matching
CN113252568A (en) Lens surface defect detection method, system, product and terminal based on machine vision
CN107798279A (en) Face living body detection method and device
CN109117855A (en) Abnormal power equipment image identification system
CN109446913A (en) A kind of detection method for judging vehicle bottom and whether reequiping
CN106897999A (en) Apple image fusion method based on Scale invariant features transform
CN113608378A (en) Full-automatic defect detection method and system based on LCD (liquid crystal display) process
CN110222661A (en) It is a kind of for motion estimate and the feature extracting method of tracking
CN113313107A (en) Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge
CN107316285A (en) The image interfusion method detected towards apple quality
CN107832696B (en) A kind of electric operating object in situ security feature identifying system
CN109815784A (en) A kind of intelligent method for classifying based on thermal infrared imager, system and storage medium
CN110222647A (en) A kind of human face in-vivo detection method based on convolutional neural networks
Jeffrey Kuo et al. Self-organizing map network for automatically recognizing color texture fabric nature
CN109345788A (en) A kind of monitoring early-warning system of view-based access control model feature

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

Application publication date: 20190122

WW01 Invention patent application withdrawn after publication