CN109544547A - A kind of bayonet type autobulb lamp cap top open defect detection method - Google Patents
A kind of bayonet type autobulb lamp cap top open defect detection method Download PDFInfo
- Publication number
- CN109544547A CN109544547A CN201811453533.XA CN201811453533A CN109544547A CN 109544547 A CN109544547 A CN 109544547A CN 201811453533 A CN201811453533 A CN 201811453533A CN 109544547 A CN109544547 A CN 109544547A
- Authority
- CN
- China
- Prior art keywords
- lamp
- image
- dirty
- region
- ear
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention proposes open defect detection methods at the top of a kind of bayonet type autobulb lamp cap.The present invention is for lamp cap top tin defects, top is dirty, open defects are respectively set algorithm and are checked in conjunction with image processing techniques at the top of three big kinds of lamp ear defect typical lamp caps, realizes the automatic detection of bayonet type autobulb lamp cap top open defect.The invention has the advantages that the open defect detection that can be automatically performed at the top of bayonet type autobulb lamp cap, detection speed is fast, discrimination is high.
Description
Technical field
The present invention relates to a kind of test technique automatic of light bulb presentation quality more particularly to bayonet type autobulb lamp caps
Top open defect detection method.
Background technique
Bayonet type automobile lamp is accounted for since safety, convenience, stability are more prominent compared to spiral light bulb
According to the bigger market share, it is used widely.Due to the complexity of bulb structure and the precision limitation of Machinery Control System, lamp
Inevitably there are various defects in brewage.The defect of light bulb is divided into functional defect and open defect.Functional defect refers mainly to
Voltage transfinites, electric current transfinites, light bulb does not work or brightness not enough etc. influences the defects of lamp functions.Light bulb open defect can be divided into
Open defect and lamp cap side open defect at the top of lamp holder.These possible defects are assembled in subsequent car light and driving makes
It will lead to serious safety problem in.Therefore, in the quality of the preceding necessary compulsory test light bulb of vehicle light bulb factory.
Bayonet type autobulb lamp cap front view such as Fig. 1 (a), side view such as Fig. 1 (b), lamp cap top area can it is approximate by
Push up tin region, filter glass region, filter glass outer circle ring region, four part of lamp lug areas composition.Bayonet type autobulb lamp cap top
Portion's open defect mainly includes that dirty top tin defects, top, lamp ear missing, lamp ear weigh wounded and lamp ear angle is bad etc. influences lamp
The defect of bubble assembly and appearance mark: top tin defects refer to that the scolding tin positioned at filter glass central area at the top of lamp cap part occurs not
Upper tin, upper tin amount are insufficient；The dirty white that is divided into top is dirty dirty with black, typically occurs in filter glass and its outer ring；Lamp
Ear missing lacks one or all lamp ear, and lamp ear weighs the i.e. lamp ear of defect wounded and has damage；Lamp ear turn to defect, that is, left and right lamp ear with
Angle between the lamp cap line of centres is bad.
Detection to bayonet type autobulb lamp cap top surface defect at present and identification mainly use artificial detection means,
I.e. operator observes by the naked eye the bayonet type autobulb on conveyer belt during the preparation process, lacks by rule of thumb to light bulb
It is trapped into the judgement of pedestrian's work, and then is handled manually accordingly.Which is there are large labor intensity, low efficiency, subjectivity by force and
Error detection rate is high.It is analyzed and is lagged due to quality testing, it is also difficult to the production process of effective on-line optimization bayonet type autobulb.
Summary of the invention
The present invention proposes a kind of bayonet type autobulb lamp cap top open defect automatic testing method, and this method can replace
Artificial range estimation accurately detects that top tin defects at the top of lamp cap, top are dirty, the big typical open defect of lamp ear defect three, makes
Meet appearance criterion of acceptability at the top of lamp cap.The present invention obtains lamp cap top area image by high-speed camera, and particular content is such as
Under:
S100. lamp cap top image is obtained, image is handled, determines lamp cap top position；
S101. threshold value T is obtained using the method based on maximum informational entropy to the image I that top camera obtains, according to the threshold
Value does binary conversion treatment to original image:
In image otherwise pixel of the gray scale greater than this threshold value T is used as background, highlights the wheel at the top of lamp cap as prospect
It is wide；
S102. using Canny operator to the Image Edge-Detection after above-mentioned binaryzation；
S103. filter glass outer region profile, the black glass at the top of prior shape constraint and curve matching detection lamp cap are combined
Glass region inside and outside contour:
Standard lamp top image is obtained in advance as reference picture, it is black at the top of lamp cap in the manual measurement reference picture
The radius r of glass outer ring profile radius r ' filter glass inside and outside circle1' and r2', in the next steps as the known constraints of shape
Condition；It is constraint with radius r ', is obtained for the point of image border obtained in S102 using least square method curve matching circle
The center of circle C (x, y) and filter glass outer ring outer diameter r of filter glass outer ring profile；Centered on C (x, y), respectively with reference picture
Radius r1' and r2' as constraint, for the point of image border obtained in S102, filter glass is fitted using least square method in succession
Inside and outside circle, obtain its filter glass region internal diameter r1With filter glass area outer diameter r2。
S200. positioning top tin saturation degree detection zone extracts spot in region, detection top tin defects:
It S201. is that circle search region, set circle search zone radius r is arranged in the center of circle with C (x, y)aCompare filter glass
Region internal diameter r1Multiple k pixels,
ra=r1+k；
S202. binarization operation, such as Fig. 4 are carried out to detection zone selected in S201 using maximum entropy method (MEM) in S101
(b) shown in, the detailed information of defect is remained；
S203. connection domain information is obtained using canny operator extraction edge, obtains area, the center of gravity parameter of these spots:
S204. judgement top tin saturation degree, pushes up the undesirable judgment criteria of tin saturation degree are as follows: there are the spots that area is greater than threshold value
Or spot center of gravity is to the distance D in the filter glass inner circle center of circleiGreater than threshold value；Wherein,
It is unqualified for top tin saturation degree as long as meeting any bar in above-mentioned two condition；
S300. the dirty detection zone of locator head, and the dirty detection zone of white dirty to black are extracted spot respectively, are examined
It is dirty to survey top:
S301. to acquired image carry out median filtering, centered on lamp cap center C (x, y), with filter glass outer region outside
Diameter r and filter glass internal diameter r1Annulus is set as dirty detection zone；
S302. filter glass and dirty contrast are enhanced to thresholding operation is carried out respectively:
In formula, TwhiteFor the threshold value of the dirty gray scale of white, TblackFor the threshold value of the dirty gray scale of black；
S303. binarization operation is carried out to detection zone selected in S301 using maximum entropy method (MEM) in S101, used
Canny operator is to image IwhiteAnd IblackDetection zone detect edge respectively, obtain area, the length and width of spot,
And be compared with threshold value, there are dirty defects for expression of transfiniting.
S400. positioning lamp ear detection zone extracts the corresponding image-region of lamp ear on the image, judges lamp ear defect:
S401. in advance on the outside of measurement reference picture lamp ear to the distance between circumscribed circle at the top of lamp cap d；
S402. in image after binarization, centered on C (x, y), in internal diameter be r and outer diameter is rb=r+d+ ξ (4 < ξ
< 8) gray scale is found in annulus lamp ear detection zone and is 255 region, and obtains the area S in regioni, center of gravity C (xi,yi) and
The long L of external minimum rectanglei, width Wi(i=1,2,3 ..., n), according to distance, the area surface of regional barycenter and center C (x, y)
The length and width and length-width ratio of long-pending, external minimum rectangle can determine whether the region searched is lamp ear, length and wide hair when region
It indicates dirty there are lamp ear when having given birth to biggish variation and weighs defect wounded.
S403. the steering angle of lamp ear calculates, the steering angle calculation method of lamp ear:
θ is lamp ear steering angle in formula, α is that line and horizontal direction angle, β are right lamp ear between left lamp ear and lamp cap center
Line and horizontal direction angle between lamp cap center；By the area of left and right lamp ear, length and width, lamp ear steering angle and threshold value ratio
Compared with transfiniting indicates defective.
Wherein, S200, S300, S400 detecting step are mutually indepedent, do not distinguish sequence.
The present invention has the advantage that
1) image processing techniques is utilized, to automatically being detected at the top of bayonet base bulb lamp cap, can precisely detect lamp
Overhead top tin defects, top be dirty, lamp ear defect these three typical lamp overhead open defects, makes to meet at the top of lamp cap outer
Appearance quality standard.
2) it realizes that entire detection process is not necessarily to manual intervention, is detected automatically using machine and replace artificial detection, it is a large amount of to save
Human resources；It is fast to detect speed, detection accuracy is high, and system is reliable and stable.
Detailed description of the invention
Fig. 1 is automobile lamp lamp holder structure and defects detection administrative division map.It is specific as follows: Fig. 1 (a), Fig. 1 (b), Fig. 1 (c) point
It is not the detection zone signal of automobile lamp lamp cap top orthogonal view, automobile lamp lamp cap top side view, lamp cap top defect
Figure；
Fig. 2 is flow chart of the method for the present invention；
Fig. 3 is that image is positioned at the top of car light lamp cap.Specific as follows: Fig. 3 (a), Fig. 3 (b), Fig. 3 (c), Fig. 3 (d) are respectively
Binaryzation goes background image, Canny edge-detected image, filter glass outer ring outer diameter fitted figure, the fitting of filter glass zone radius
Figure；
Fig. 4 is top tin saturation degree detection image.Specific as follows: Fig. 4 (a), Fig. 4 (b), Fig. 4 (c) are respectively that region of search shows
It is intended to, image is cut in top tin region, spot extracts image；
Fig. 5 is the dirty detection image in top.It is specific as follows: Fig. 5 (a), Fig. 5 (b), Fig. 5 (c), Fig. 5 (d), Fig. 5 (e), Fig. 5
(f), Fig. 5 (g), Fig. 5 (h) are respectively the dirty area image of white, the dirty region binary image of white, the dirty spot of white
Image, the dirty spot image of white, the dirty area image of black, the dirty region binary image of black, the dirty spot figure of black
The dirty spot of picture, black extracts image；
Fig. 6 is four kinds of lamp ear angle undesirable conditions；
Fig. 7 is lamp ear defects detection image, and specific as follows: Fig. 7 (a), Fig. 7 (b), Fig. 7 (c) are respectively lamp ear region of search
Image, lamp ear image, lamp ear steering angle schematic diagram.
Specific embodiment
The present invention is illustrated by taking the bayonet type auto lamp of model P21WS as an example, using pixel as length in embodiment
It is single, use resolution ratio to obtain detection zone image at the top of lamp cap for 640 × 480 camera.Defects detection administrative division map such as Fig. 1
(a), in Fig. 1 (c) shown in mark, top tin defects detection zone is that tin region A is pushed up in figure；The dirty defects detection region in top is
Filter glass region B, filter glass outer region C in figure；Lamp ear detection zone is lamp ear detection zone D in figure；In conjunction with Fig. 2 method
Flow chart, the specific implementation steps are as follows by the present invention:
S100. positioning at the top of lamp cap:
S101. background is removed by the image I that top camera obtains using the method based on maximum informational entropy, highlights lamp
The profile of overhead: the ratio P of total number of pixels and each gray-scale pixels point in target is calculated separatelyi, threshold value T, background and mesh
Mark the distribution of gray value:
In formula:M indicates the maximum value of gray scale, then the comentropy H (A) of background and target, H (B) are as follows:
The total information entropy of image can be sought by upper two formula are as follows:
Φ (s)=H (A)+H (B),
When Φ (s) is maximized, threshold value T is most ideal, and background and bulb region segmentation effect are best at this time, chooses at this time
Threshold value T to original image carry out binary conversion treatment:
In image otherwise pixel of the gray scale greater than this threshold value T is used as background as prospect, and binaryzation removes the image of background
I1For the elementary contour at the top of lamp cap, as shown in Fig. 3 (a)；
S102. using Canny operator to the Image Edge-Detection after above-mentioned binaryzation, as shown in Fig. 3 (b)；
S103. it combines in the filter glass region B and filter glass outer region C at the top of prior shape constrained fitting detection lamp cap
Outer profile:
Standard lamp top image is obtained in advance as reference picture, it is black at the top of lamp cap in the manual measurement reference picture
Glass outer region C profile radius r '=216, the radius r of filter glass region B inside and outside circle1'=80 and r2'=118, subsequent
As the known constraints condition of shape in step；
Centered on C (x, y), respectively with the radius r of reference picture1' and r2' as constraint, scheme for obtained in S102
As marginal point, it is fitted the inside and outside circle of filter glass region B in succession using least square method, obtains its filter glass region B internal diameter r1=
75 and outer diameter r2=115.
Push up tin defects detection zone A radius namely r1=75；
It is constraint with radius r '=216, for the point of image border obtained in S102, using least square method curve matching
Circle, obtains center of circle C (328,246) and filter glass outer region C outer diameter r=210；
S200. top tin saturation degree detection:
S201. it selectes detection zone: being circle with C (328,246) according to the lamp cap center C (328,246) found in S103
Circle search region, the radius r in set circle search region is arranged in the heartaThan filter glass region B internal diameter r1More k pixels,
ra=r1+k；
K=6 pixel, shown in the tin saturation degree detection zone A such as Fig. 4 (a) of top；
S202. binarization operation is carried out to region A in S201 using maximum entropy method (MEM) in S101, as shown in Fig. 4 (b), retained
The detailed information of defect；
S203. connection domain information is obtained using canny operator extraction edge and obtains these spots as shown in Fig. 4 (c)
Area:
S1=1766, S2=150, S3=80, S4=120, S5=60, S6=175, S7=194；
Center of gravity:
C(x1,y1)=C (318,175), C (x2,y2)=C (311,301), C (x3,y3)=C (307,301),
C(x4,y4)=C (332,298), C (x5,y5)=C (365,272), C (x6,y6)=C (380,249), C (x7,y7)
=C (330,250)；
S204. judgement top tin saturation degree, pushes up the undesirable judgment criteria of tin saturation degree are as follows: (1) there are areas to be greater than threshold value T1
Spot；(2) the distance D in spot center of gravity to the filter glass inner circle center of circle is greater than threshold value T2；It is full that tin is pushed up simply by the presence of any situation
It is unqualified with spending, wherein
There are D in embodiment1=72, D2=58, D3=59, D4=52, D5=45, D6=52, D7=4；
Threshold value T in the present embodiment1For 200 pixel of empirical value, threshold value T2For 73 pixels,
Spot meets condition away from circle center distance D in this light bulb, but there are spot S1Much larger than threshold value, therefore it is full to there is top tin
With degree defect.
S300. dirty detection at the top of lamp cap:
S301. select detection zone: dirty generating region is filter glass region B and filter glass outer region C at the top of lamp cap,
Region B internal diameter and region C outer diameter are respectively r1And r, according to the lamp cap center C (328,246) found in S103, with r1It is set with r
Annulus is set as dirty detection zone, r1It is 210 pixels for 75 pixels, r, if Fig. 5 (a) is that black is dirty and Fig. 5 (e) is
White is dirty；
S302. detection zone thresholding,
To enhance filter glass and dirty contrast, white is dirty and black is dirty as shown in Fig. 5 (b) and 5 (f), this
In embodiment, the threshold value T of the dirty gray scale of blackblackIt is 120, the dirty gray threshold T of whitewhiteIt is 128；
S303. binarization operation, such as Fig. 5 are carried out to detection zone selected in S301 using maximum entropy method (MEM) in S101
(c) and shown in 5 (g)；Using canny operator to image IblackAnd IwhiteDetection zone detect edge respectively, obtain spot
Area, length and width, and be compared with threshold value, there are dirty defects for expression of transfiniting.White dot and black splotch wheel
Wide such as Fig. 5 (d) and 5 (h) is shown.
S400. lamp ear defects detection:
S401. the distance d for arriving filter glass outer ring outer diameter on the outside of the obtained standard lamp image lamp ear of measurement in advance, such as Fig. 7 (a)
It is shown, d=18；
S402. in Fig. 7 (a), centered on C (328,246), in internal diameter be r and outer diameter is rb=r+d+ ξ (4 < ξ < 8)
Lamp ear detection zone D annulus in find the region that gray scale is 255, and obtain the area S in regioni, center of gravity C (xi,yi) and it is outer
Meet the long L of minimum rectanglei, width Wi(i=1,2,3 ..., n)；According to regional barycenter at a distance from center, region area, it is external most
The length and width and length-width ratio of small rectangle can determine whether the region searched is lamp ear, when length and the width in region have occurred it is biggish
It indicates dirty there are lamp ear when variation and weighs defect wounded；As shown in Fig. 7 (b), the center of gravity C of left lamp ear is obtainedL(89,195), long
Spend LL=60, width WL=32 and area SL=1440, right lamp ear center of gravity CR(484,413), length LR=55, width WR=53
With area SR=1375；
S403. the steering angle of lamp ear calculates, according to the relative position of left and right lamp ear, as shown in fig. 6, the steering angle of lamp ear
θ can be divided into four kinds of situations:
As shown in Fig. 7 (c), C (y)-C (y in embodimentL)≥0 and C(y)-C(yR)≤0, has:
In embodiment,θ=+ 180 ° of alpha-beta=149 °, lamp ear turn to
180 ° ± 3 ° of angle threshold value, the lamp bulb ear steering angle is defective.
Implementation through the foregoing embodiment, those skilled in the art are apparent from, and can keep teachings of the present invention content
While many modifications and variation are made to method.Therefore, above disclosure should be considered as only by appended claim
The limitation of range.
Claims (5)
1. open defect detection method at the top of a kind of bayonet type autobulb lamp cap, the method includes at least following step
It is rapid:
S100. lamp cap top image is obtained, image is handled, determines that lamp cap top tin saturation degree detection zone, top are dirty
Defects detection region, lamp ear detection zone position；
S200. positioning top tin saturation degree detection zone extracts spot in region, detection top tin defects；
S300. the dirty detection zone of locator head, and the dirty detection zone of white dirty to black extract spot, detection top respectively
Portion is dirty；
S400. positioning lamp ear detection zone extracts the corresponding image-region of lamp ear on the image, judges lamp ear defect；
Wherein, S200, S300, S400 detecting step are mutually indepedent, do not distinguish sequence.
2. open defect detection method at the top of bayonet base bulb lamp cap according to claim 1, it is characterised in that obtain lamp
Overhead image, handles image, determines lamp cap top tin saturation degree detection zone, the dirty defects detection region in top, lamp
The process of ear detection zone position, at least further comprising the steps of:
S101. threshold value T is obtained using the method based on maximum informational entropy to the image I that top camera obtains, according to the threshold value pair
Original image does binary conversion treatment:
In image otherwise pixel of the gray scale greater than this threshold value T is used as background, highlights the profile at the top of lamp cap as prospect；
S102. using Canny operator to the Image Edge-Detection after above-mentioned binaryzation；
S103. prior shape constraint and the filter glass outer region profile at the top of curve matching detection lamp cap, filter glass area are combined
Domain inside and outside contour:
Filter glass of the standard lamp top image as reference picture, in the manual measurement reference picture at the top of lamp cap is obtained in advance
The radius r of outer ring profile radius r ' filter glass inside and outside circle1' and r2', in the next steps as the known constraints condition of shape；
It is constraint with radius r ', filter glass is obtained using least square method curve matching circle for the point of image border obtained in S102
The center of circle C (x, y) and filter glass outer ring outer diameter r of outer ring profile；Centered on C (x, y), respectively with the radius r of reference picture1′
And r2' as constraint, for the point of image border obtained in S102, it is fitted inside and outside filter glass in succession using least square method
Circle, obtains its filter glass region internal diameter r1With filter glass area outer diameter r2。
3. open defect detection method at the top of bayonet base bulb lamp cap according to claim 1, it is characterised in that positioning top
Tin saturation degree detection zone extracts spot in region, and the process of detection top tin defects is at least further comprising the steps of:
It S201. is that circle search region, set circle search zone radius r is arranged in the center of circle with C (x, y)aThan in filter glass region
Diameter r1Multiple k pixels,
ra=r1+k；
S202. binarization operation, such as Fig. 4 are carried out to detection zone selected in S201 using based on maximum informational entropy method
(b) shown in, the detailed information of defect is remained；
S203. connection domain information is obtained using canny operator extraction edge, obtains area, the center of gravity of these spots；
S204. judgement top tin saturation degree, pushes up the undesirable judgment criteria of tin saturation degree are as follows: there are spots or spot that area is greater than threshold value
Distance D of the point center of gravity to the filter glass inner circle center of circleiGreater than threshold value；Wherein,
It is unqualified for top tin saturation degree as long as meeting any bar in above-mentioned two condition.
4. open defect detection method at the top of bayonet base bulb lamp cap according to claim 1, it is characterised in that positioning top
The dirty detection zone in portion, and white dirty detection zone dirty to black extract spot respectively, detect the dirty process in top, until
It is few further comprising the steps of:
S301. median filtering is carried out to acquired image, centered on lamp cap center C (x, y), with filter glass outer region outer diameter r
With filter glass internal diameter r1Annulus is set as dirty detection zone；
S302. filter glass and dirty contrast are enhanced to thresholding operation is carried out respectively:
In formula, TwhiteFor the threshold value of the dirty gray scale of white, TblackFor the threshold value of the dirty gray scale of black；
S303. binarization operation is carried out to detection zone selected in S301 using based on maximum informational entropy method, used
Canny operator is to image IwhiteAnd IblackDetection zone detect edge respectively, obtain area, the length and width of spot, and
It is compared with threshold value, there are dirty defects for expression of transfiniting.
5. open defect detection method at the top of bayonet base bulb lamp cap according to claim 1, it is characterised in that positioning lamp
Ear detection zone extracts the corresponding image-region of lamp ear on the image, judges the process of lamp ear defect, at least further include following step
It is rapid:
S401. in advance on the outside of measurement reference picture lamp ear to the distance between circumscribed circle at the top of lamp cap d；
S402. in image after binarization, centered on C (x, y), in internal diameter be r and outer diameter is rb=r+d+ ξ's (4 < ξ < 8)
Gray scale is found in annulus lamp ear detection zone and is 255 region, and obtains the area S in regioni, center of gravity C (xi,yi) and it is external most
The long L of small rectanglei, width Wi(i=1,2,3 ..., n), according to the distance of regional barycenter and center C (x, y), region area, external
The length and width and length-width ratio of minimum rectangle can determine whether the region searched is lamp ear, when length and the width in region have occurred it is larger
Variation when indicate that there are lamp ear is dirty and weigh defect wounded.
S403. the steering angle of lamp ear calculates, the steering angle calculation method of lamp ear:
θ is lamp ear steering angle in formula, α is that line and horizontal direction angle, β are right lamp ear and lamp between left lamp ear and lamp cap center
Line and horizontal direction angle between head center；By the area of left and right lamp ear, length and width, lamp ear steering angle and threshold value comparison, transfinite
Indicate defective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811453533.XA CN109544547A (en) | 2018-11-30 | 2018-11-30 | A kind of bayonet type autobulb lamp cap top open defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811453533.XA CN109544547A (en) | 2018-11-30 | 2018-11-30 | A kind of bayonet type autobulb lamp cap top open defect detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109544547A true CN109544547A (en) | 2019-03-29 |
Family
ID=65851822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811453533.XA Pending CN109544547A (en) | 2018-11-30 | 2018-11-30 | A kind of bayonet type autobulb lamp cap top open defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544547A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112781452A (en) * | 2021-03-25 | 2021-05-11 | 湘潭大学 | Bullet primer top appearance defect detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB195194A (en) * | 1922-01-13 | 1923-03-29 | Joseph Theodore Robin | Improvements in or relating to incandescent electric lamps |
| CN104155306A (en) * | 2014-07-22 | 2014-11-19 | 河南工业职业技术学院 | Soldering lug defect detection method for single-soldering-lug lamp cap |
| CN104568974A (en) * | 2013-10-22 | 2015-04-29 | 镇江胡氏光电科技有限公司 | Area-comparison-algorithm-based soldering lug defect and missing detection method |
| CN104568978A (en) * | 2013-10-22 | 2015-04-29 | 镇江胡氏光电科技有限公司 | Lamp holder optical head defect detection method |
| US20150271375A1 (en) * | 2011-11-14 | 2015-09-24 | Tseng-Lu Chien | Light Device has Built-in Digital Data System for Record Image, Sound |
| CN106501278A (en) * | 2016-11-08 | 2017-03-15 | 浙江科技学院 | Surface of the light tube defect classification method and system based on invariable rotary textural characteristics |
-
2018
- 2018-11-30 CN CN201811453533.XA patent/CN109544547A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB195194A (en) * | 1922-01-13 | 1923-03-29 | Joseph Theodore Robin | Improvements in or relating to incandescent electric lamps |
| US20150271375A1 (en) * | 2011-11-14 | 2015-09-24 | Tseng-Lu Chien | Light Device has Built-in Digital Data System for Record Image, Sound |
| CN104568974A (en) * | 2013-10-22 | 2015-04-29 | 镇江胡氏光电科技有限公司 | Area-comparison-algorithm-based soldering lug defect and missing detection method |
| CN104568978A (en) * | 2013-10-22 | 2015-04-29 | 镇江胡氏光电科技有限公司 | Lamp holder optical head defect detection method |
| CN104155306A (en) * | 2014-07-22 | 2014-11-19 | 河南工业职业技术学院 | Soldering lug defect detection method for single-soldering-lug lamp cap |
| CN106501278A (en) * | 2016-11-08 | 2017-03-15 | 浙江科技学院 | Surface of the light tube defect classification method and system based on invariable rotary textural characteristics |
Non-Patent Citations (2)
| Title |
|---|
| 尹立苹 等: "玻壳局部缺陷检测方法的研究", 《计算机与数字工程》 * |
| 王佳炎: "基于机器视觉的车用灯泡检测系统研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112781452A (en) * | 2021-03-25 | 2021-05-11 | 湘潭大学 | Bullet primer top appearance defect detection method |
| CN112781452B (en) * | 2021-03-25 | 2022-10-18 | 湘潭大学 | Bullet primer top appearance defect detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN105488454B (en) | Front vehicles detection and ranging based on monocular vision | |
| CN105334219B (en) | A kind of bottle mouth defect detection method of residual analysis dynamic threshold segmentation | |
| CN105784713B (en) | Sealing ring detection method of surface flaw based on machine vision | |
| JP4942509B2 (en) | Vehicle position detection method and apparatus | |
| EP3036730B1 (en) | Traffic light detection | |
| CN102288613B (en) | Surface defect detecting method for fusing grey and depth information | |
| CN102854192B (en) | Method for detecting apple surface defect based on apple surface defect detecting system | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| CN110647850A (en) | Automatic lane deviation measuring method based on inverse perspective principle | |
| CN104156951B (en) | A kind of white blood cell detection method for BAL fluid smear | |
| CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
| CN107610085A (en) | A kind of welding point defect detecting system based on computer vision | |
| CN107644538B (en) | Traffic signal lamp identification method and device | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN105046700A (en) | Brightness correction and color classification-based fruit surface defect detection method and system | |
| CN115082466B (en) | PCB surface welding spot defect detection method and system | |
| US20190279003A1 (en) | Lane line detection method | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| CN106709529B (en) | Visual detection method for photovoltaic cell color difference classification | |
| CN103759644A (en) | Separating and refining type intelligent optical filter surface defect detecting method | |
| CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
| CN111122590A (en) | Ceramic surface defect detection device and detection method | |
| CN104700423A (en) | Method and device for detecting bottle cap | |
| CN109492544B (en) | Method for classifying animal fibers through enhanced optical microscope |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190329 |