CN103473778A - Detecting algorithm for eccentrically-inserting defect of LED luminous chip - Google Patents
Detecting algorithm for eccentrically-inserting defect of LED luminous chip Download PDFInfo
- Publication number
- CN103473778A CN103473778A CN 201310432371 CN201310432371A CN103473778A CN 103473778 A CN103473778 A CN 103473778A CN 201310432371 CN201310432371 CN 201310432371 CN 201310432371 A CN201310432371 A CN 201310432371A CN 103473778 A CN103473778 A CN 103473778A
- Authority
- CN
- China
- Prior art keywords
- image
- luminescence chip
- straight line
- fitting
- carried out
- 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.)
- Granted
Links
Images
Landscapes
- Led Devices (AREA)
Abstract
The invention discloses a detecting algorithm for an eccentrically-inserting defect of an LED luminous chip. A colorful image I of the LED luminous chip is collected; the colorful image I of the LED luminous chip which is to be detected is read by a computer; grayscale processing and de-noising processing are conducted on the colorful image I, and an image I1 is obtained; binarization processing is conducted on the image I1, and an image I2 is obtained after the binarization processing; refining processing is conducted on the image I2 obtained after the binarization processing, and an image I3 is obtained after the refining processing; linear fitting is conducted on the image I3 obtained after the refining processing, and a fit straight line is obtained; whether the eccentrically-inserting defect of the LED luminous chip exists is judged according to the fit straight line. The detecting algorithm for the eccentrically-inserting defect of the LED luminous chip can carry out real-time detection on the eccentrically-inserting defect of LED luminous chips in a production line, and is efficient and accurate and can be applied to real-time on-site operation.
Description
Technical field
The invention belongs to the computer image processing technology field, refer to especially the detection algorithm of the slotting inclined to one side defect of a kind of LED luminescence chip.
Background technology
In recent years, under the comprehensive universal condition of full-automatic packaging line, the LED luminescence chip detects online package quality in the encapsulation production run, the inevitable demand that become and improved package level, guarantees package quality.But because the LED chip size is little, the packaging technology requirement is high, line speed is fast, is difficult to carry out real-time quality testing in encapsulation process.Due to the limitation of existing sorting technology, in the LED of encapsulation after sorting, only have a small amount of product can meet the requirement of a certain client (as high-end LED display manufacturer), all the other major parts will become the stock in warehouse.If the waste product/defect rate still existed after LED encapsulation sorting is 0.1%, in annual trillion the LED encapsulating products in the whole nation, just may produce several hundred million waste product/substandard products, cause the direct economic loss of nearly hundred million yuan.Therefore, in order to meet the requirement to LED encapsulation defect sorting quality, the research of LED encapsulation defect sorting technology is become to the important topic of LED industry development.
The properties of product of LED luminescence chip are mainly reflected in Luminescence Uniformity and brightness characteristics aspect.Due to the main determining positions in sealing by luminescence chip of the Luminescence Uniformity of LED and brightness characteristics; and usually can there be slotting inclined to one side defect in luminescence chip in sealing; if insert inclined to one side numerical value in micron level; it can't obviously exert an influence to LED average spectrum intensity and complete spectrum irradiance; but can appreciable impact be arranged to the equalization of intensity of LED, thereby affect the LED optical property.
Existing screening installation is as light splitting machine, color scanner, can only average spectrum intensity and the complete spectral irradiance of LED luminescence chip from energising be detected and be classified, can't distinguish the light distribution uniformity coefficient of LED lamp pearl, therefore, use these equipment None-identifieds to go out trickle slotting inclined to one side defect, thereby can't guarantee colour temperature aberration and the Luminescence Uniformity (being the discreteness of directivity characteristics) of LED display.In addition, for detection of existing screening installations such as the integrating sphere of LED equalization of intensity, photomultipliers, owing to detecting principle, limit, can't realize the online quick continuous sorting of LED equalization of intensity, carry out the contact sorting for these defects and be difficult to especially realize.
To sum up, study a kind of detection method that can accurately detect the slotting inclined to one side defect of LED luminescence chip, thereby the light distribution uniformity coefficient that guarantees the LED luminescence chip is guaranteed to LED luminescence chip product quality is very important.
Summary of the invention
For the defect existed in above-mentioned prior art or deficiency, the object of the invention is to, provide a kind of LED luminescence chip to insert the detection algorithm of inclined to one side defect, this algorithm can detect trickle slotting inclined to one side defect to the LED luminescence chip on production line, thereby can guarantee the light distribution uniformity coefficient of LED luminescence chip.This algorithm counting yield is high, accuracy of detection is high.
The method is efficient, accurate, is suitable for generating on-the-spot true-time operation.
In order to achieve the above object, the present invention adopts following technical scheme to be solved:
A kind of LED luminescence chip is inserted the detection algorithm of inclined to one side defect, specifically comprises the steps:
Step 1: the coloured image I that gathers LED luminescence chip to be measured; Computing machine reads the coloured image I of LED luminescence chip to be measured; The collection direction of image meets in coloured image I that two pins of light emitting diode are vertical direction and two pins are overlapping;
Step 2: coloured image I is carried out to gray processing processing and denoising, obtain image I 1;
Step 3: image I 1 is carried out to binary conversion treatment, obtain the image I 2 after binary conversion treatment;
Step 4: the image I 2 after binaryzation is carried out to thinning processing, obtain the image I 3 after thinning processing;
Step 5: the image I 3 after thinning processing is carried out to fitting a straight line, obtain fitting a straight line;
Step 6: the angle theta of digital simulation straight line and y axle;
Step 7: the pitch angle Φ that tries to achieve this fitting a straight line according to the slope of fitting a straight line;
Step 8: the insertion angle beta that calculates luminescence chip, according to the angle threshold scope of inserting angle beta and setting relatively, judging whether to fall in the angle threshold scope, is to think the slotting inclined to one side defect of luminescence chip of LED lamp, return to step 1, the luminescence chip to be detected to the next one detected; Otherwise, think that the luminescence chip of LED lamp has the inclined to one side defect of inserting, perform step 9; :
When Φ ∈ [0,1.57], β=Φ+θ;
When Φ ∈ (1.57,3.14] time, β=Φ-θ;
Step 9: there is the value of inserting inclined to one side defect and showing β in the current luminescence chip of Computer display; Return to step 1.
Further, in described step 2, coloured image I is carried out to gray processing and can adopt component method, maximum value process, mean value method or method of weighted mean.
Further, in described step 3, image I 1 being carried out to binary conversion treatment specifically comprises the steps:
1) set initial segmentation threshold value T1=(fmax+fmin)/2, wherein, fmax and fmin be maximum gradation value and the minimum gradation value of presentation video I1 respectively;
2) with initial segmentation threshold value T1, image I 1 is carried out to Region Segmentation, obtain gray-scale value and be greater than the image-region G1 of initial segmentation threshold value and the image-region G2 that gray-scale value is not more than segmentation threshold;
The gray average u2 of the gray average u1 of the pixel that 3) computed image zone G1 comprises and image-region G2 and the pixel comprised;
4) calculate new segmentation threshold Tm=(u1+u2)/2; Judge whether | Tm-T (m-1) | >=1, wherein, m is the sequence number of cutting apart average, for initial segmentation average, m=0; To return to step 2) with new segmentation threshold Tm, replace initial segmentation threshold value T1 to carry out Region Segmentation to image I 1; Otherwise the segmentation threshold Tm that this is new is as final segmentation threshold;
5) the segmentation threshold Tm obtained by step 4) carries out binary conversion treatment to image I 1; Then scan the image I 1 after binary conversion treatment, if the capable j column element of i I1(i, j in image I 1) >=Tm, giving this element assignment is 255; Otherwise give this pixel assignment 0; Obtain the image I 2 after binary conversion treatment.
Further, in described step 5, the image I 3 after thinning processing being carried out to fitting a straight line specifically comprises the steps:
At first, the image I 3 after the scanning thinning processing, the pixel that is 255 for each gray-scale value, be kept at its horizontal ordinate and ordinate respectively in one dimension matrix A and one dimension matrix B; Secondly, take the one dimension matrix A as horizontal ordinate, one dimension matrix B as ordinate carries out fitting a straight line, obtain fitting a straight line, it is true origin that the coordinate system of this fitting a straight line be take the upper left corner of image I 3, usings true origin to the right as x axle forward, downwards as y axle forward.
Further, the angle threshold scope in described step 8 is [1.553,1.587].
Compared with prior art, algorithm of the present invention has the following advantages:
1,, without artificial participation, the labour intensity that has overcome manual detection is large, inefficiency and the lower shortcoming of detection degree of accuracy.Take machine vision technique to luminescence chip the slotting inclined to one side defect in sealing carry out online detection, sorting, guarantee the consistance of LED chip on equalization of intensity after sorting.Through check, insert inclined to one side accuracy of detection and can reach tens microns.Compare the defect rate of decrease LED luminescence chip with existing screening installation.
2, the shooting caused due to DE Camera Shake or other reasons just all can not affect final accuracy of detection, the image scanning of this algorithm after by thinning processing obtains fitting a straight line, and the deviation of the both direction of fitting a straight line is considered and obtains inserting angle, guaranteed the detection degree of accuracy.
3, adopt process of iteration to carry out Threshold segmentation, fast convergence rate, the target and background of differentiate between images exactly.
Below in conjunction with the drawings and specific embodiments, the present invention is further explained to explanation.
The accompanying drawing explanation
Fig. 1 is the general flow chart of method of the present invention.
The process flow diagram of step 3 binary image in Fig. 2 method of the present invention.
Image in Fig. 3 method of the present invention after step 5 pair thinning processing carries out the process flow diagram of fitting a straight line.
Embodiment
Be below the specific embodiment that the inventor provides, it should be noted that, the embodiment provided further explains to of the present invention, and protection scope of the present invention is not limited to given embodiment.
Referring to Fig. 1-Fig. 3, the LED luminescence chip of the present embodiment is inserted the detection algorithm of inclined to one side defect, specifically comprises the steps:
Step 1: the coloured image I that gathers LED luminescence chip to be measured; Computing machine reads the coloured image I of LED luminescence chip to be measured; The collection direction of image meets in coloured image I that two pins of light emitting diode are vertical direction and two pins are overlapping;
Step 2: coloured image I is carried out to gray processing processing and denoising, obtain image I 1;
Coloured image is carried out to gray processing and can adopt component method, maximum value process, mean value method or method of weighted mean.
Step 3: image I 1 is carried out to binary conversion treatment, obtain the image I 2 after binary conversion treatment;
Step 4: the image I 2 after binaryzation is carried out to thinning processing, obtain the image I 3 after thinning processing;
Step 5: the image I 3 after thinning processing is carried out to fitting a straight line, obtain fitting a straight line;
As shown in Figure 3, the image I 3 after thinning processing being carried out to fitting a straight line specifically comprises the steps:
At first, the image I 3 after the scanning thinning processing, the pixel that is 255 for each gray-scale value, be kept at its horizontal ordinate and ordinate respectively in one dimension matrix A and one dimension matrix B; Secondly, take the one dimension matrix A as horizontal ordinate, one dimension matrix B as ordinate carries out fitting a straight line, obtain fitting a straight line y=ax+b, it is true origin that the coordinate system of this fitting a straight line be take the upper left corner of image I 3, using true origin to the right as x axle forward, downwards as y axle forward;
Step 6: the angle theta of digital simulation straight line and y axle;
Step 7: the pitch angle Φ that tries to achieve fitting a straight line according to the slope of fitting a straight line;
Step 8: the insertion angle beta that calculates luminescence chip:
When Φ ∈ [0,1.57], β=Φ+θ;
When Φ ∈ (1.57,3.14] time, β=Φ-θ;
If β is ∈ [1.553,1.587], think that the luminescence chip of LED lamp is not inserted inclined to one side defect, return to step 1, the luminescence chip to be detected to the next one detected; Otherwise, think that the luminescence chip of LED lamp has the inclined to one side defect of inserting, perform step 9.
Step 9: there is the value of inserting inclined to one side defect and showing β in the current luminescence chip of Computer display; Return to step 1.
Be below the embodiment that the inventor provides, the protection domain of algorithm of the present invention is not limited to this embodiment.
Embodiment:
Step 1: gather the coloured image I of LED luminescence chip to be measured, two pins that the attention shooting angle is light emitting diode are vertical direction and two pins overlap;
Step 2: adopt mean value method to carry out the gray processing processing to coloured image I, the image denoising after then adopting median filtering method to gray processing, choose filter window and be of a size of 3*3 in median filtering method, obtain image I 1;
Step 3: as shown in Figure 2, adopt the process of iteration Threshold segmentation to carry out binary conversion treatment to image I 1, obtain the image I 2 after binary conversion treatment; Concrete steps are as follows:
1) set initial segmentation threshold value T1=(fmax+fmin)/2, wherein, fmax and fmin be maximum gradation value and the minimum gradation value of presentation video I1 respectively;
2) with initial segmentation threshold value T1, image I 1 is carried out to Region Segmentation, obtain gray-scale value and be greater than the image-region G1 of initial segmentation threshold value and the image-region G2 that gray-scale value is not more than segmentation threshold;
The gray average u2 of the gray average u1 of the pixel that 3) computed image zone G1 comprises and image-region G2 and the pixel comprised;
4) calculate new segmentation threshold Tm=(u1+u2)/2; Judge whether | Tm-T (m-1) | >=1, wherein, m is the sequence number of cutting apart average, for initial segmentation average, m=0; To return to step 2) with new segmentation threshold Tm, replace initial segmentation threshold value T1 to carry out Region Segmentation to image I 1; Otherwise the segmentation threshold Tm that this is new is as final segmentation threshold;
5) the segmentation threshold Tm obtained by step 4) carries out binary conversion treatment to image I 1; Then scan the image I 1 after binary conversion treatment, if the capable j column element of i I1(i, j in image I 1) >=Tm, giving this element assignment is 255; Otherwise give this pixel assignment 0; Obtain the image I 2 after binary conversion treatment.
Step 4: the image I 2 of the bwmorph () function that adopts the MATLAB tool box after to binary conversion treatment carried out thinning processing, obtains the image I 3 after thinning processing, i.e. I3=bwmorth (I2, ' thin ', n).
Step 5: the image I 3 after thinning processing is carried out to fitting a straight line, obtain fitting a straight line;
As shown in Figure 3, the image I 3 after thinning processing being carried out to fitting a straight line specifically comprises the steps:
At first, the image I 3 after the scanning thinning processing, the pixel that is 255 for each gray-scale value, be kept at its horizontal ordinate and ordinate respectively in one dimension matrix A and one dimension matrix B; Secondly, take the one dimension matrix A as horizontal ordinate, one dimension matrix B as ordinate carries out fitting a straight line, obtain fitting a straight line y=4.75x-3545, it is true origin that the coordinate system of this fitting a straight line be take the upper left corner of image I 3, using true origin to the right as x axle forward, downwards as y axle forward;
Step 6: the angle theta of digital simulation straight line and y axle obtains θ=0.087;
Step 7: according to the slope of fitting a straight line, try to achieve the pitch angle Φ of this fitting a straight line=1.36;
Step 8: Φ=1.36 ∈ [0,1.57]; β=Φ+θ=1.36+0.087=1.447, do not belong to [1.553,1.587], therefore thinks that there is slotting inclined to one side defect in this LED luminescence chip.
Step 9: there is the value of inserting inclined to one side defect and showing β in the current luminescence chip of Computer display; Return to step 1.
Claims (5)
1. a LED luminescence chip is inserted the detection algorithm of inclined to one side defect, it is characterized in that, specifically comprises the steps:
Step 1: the coloured image I that gathers LED luminescence chip to be measured; Computing machine reads the coloured image I of LED luminescence chip to be measured; The collection direction of image meets in coloured image I that two pins of light emitting diode are vertical direction and two pins are overlapping;
Step 2: coloured image I is carried out to gray processing processing and denoising, obtain image I 1;
Step 3: image I 1 is carried out to binary conversion treatment, obtain the image I 2 after binary conversion treatment;
Step 4: the image I 2 after binaryzation is carried out to thinning processing, obtain the image I 3 after thinning processing;
Step 5: the image I 3 after thinning processing is carried out to fitting a straight line, obtain fitting a straight line;
Step 6: the angle theta of digital simulation straight line and y axle;
Step 7: the pitch angle Φ that tries to achieve this fitting a straight line according to the slope of fitting a straight line;
Step 8: the insertion angle beta that calculates luminescence chip, according to the angle threshold scope of inserting angle beta and setting relatively, judging whether to fall in the angle threshold scope, is to think the slotting inclined to one side defect of luminescence chip of LED lamp, return to step 1, the luminescence chip to be detected to the next one detected; Otherwise, think that the luminescence chip of LED lamp has the inclined to one side defect of inserting, perform step 9; :
When Φ ∈ [0,1.57], β=Φ+θ;
When Φ ∈ (1.57,3.14] time, β=Φ-θ;
Step 9: there is the value of inserting inclined to one side defect and showing β in the current luminescence chip of Computer display; Return to step 1.
2. insert the detection algorithm of inclined to one side defect as 1 LED luminescence chip claimed in claim 1, it is characterized in that, in described step 2, coloured image I is carried out to gray processing and can adopt component method, maximum value process, mean value method or method of weighted mean.
3. LED luminescence chip as claimed in claim 1 is inserted the detection algorithm of inclined to one side defect, it is characterized in that, in described step 3, image I 1 is carried out to binary conversion treatment and specifically comprises the steps:
1) set initial segmentation threshold value T1=(fmax+fmin)/2, wherein, fmax and fmin be maximum gradation value and the minimum gradation value of presentation video I1 respectively;
2) with initial segmentation threshold value T1, image I 1 is carried out to Region Segmentation, obtain gray-scale value and be greater than the image-region G1 of initial segmentation threshold value and the image-region G2 that gray-scale value is not more than segmentation threshold;
The gray average u2 of the gray average u1 of the pixel that 3) computed image zone G1 comprises and image-region G2 and the pixel comprised;
4) calculate new segmentation threshold Tm=(u1+u2)/2; Judge whether | Tm-T (m-1) | >=1, wherein, m is the sequence number of cutting apart average, for initial segmentation average, m=0; To return to step 2) with new segmentation threshold Tm, replace initial segmentation threshold value T1 to carry out Region Segmentation to image I 1; Otherwise the segmentation threshold Tm that this is new is as final segmentation threshold;
5) the segmentation threshold Tm obtained by step 4) carries out binary conversion treatment to image I 1; Then scan the image I 1 after binary conversion treatment, if the capable j column element of i I1(i, j in image I 1) >=Tm, giving this element assignment is 255; Otherwise give this pixel assignment 0; Obtain the image I 2 after binary conversion treatment.
4. LED luminescence chip as claimed in claim 1 is inserted the detection algorithm of inclined to one side defect, it is characterized in that, in described step 5, the image I 3 after thinning processing is carried out to fitting a straight line and specifically comprises the steps:
At first, the image I 3 after the scanning thinning processing, the pixel that is 255 for each gray-scale value, be kept at its horizontal ordinate and ordinate respectively in one dimension matrix A and one dimension matrix B; Secondly, take the one dimension matrix A as horizontal ordinate, one dimension matrix B as ordinate carries out fitting a straight line, obtain fitting a straight line, it is true origin that the coordinate system of this fitting a straight line be take the upper left corner of image I 3, usings true origin to the right as x axle forward, downwards as y axle forward.
5. LED luminescence chip as claimed in claim 1 is inserted the detection algorithm of inclined to one side defect, it is characterized in that, the angle threshold scope in described step 8 is [1.553,1.587].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310432371.2A CN103473778B (en) | 2013-09-18 | 2013-09-18 | Detecting method for eccentrically-inserting defect of LED luminous chip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310432371.2A CN103473778B (en) | 2013-09-18 | 2013-09-18 | Detecting method for eccentrically-inserting defect of LED luminous chip |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103473778A true CN103473778A (en) | 2013-12-25 |
| CN103473778B CN103473778B (en) | 2017-01-11 |
Family
ID=49798612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310432371.2A Active CN103473778B (en) | 2013-09-18 | 2013-09-18 | Detecting method for eccentrically-inserting defect of LED luminous chip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473778B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484659A (en) * | 2014-12-30 | 2015-04-01 | 南京巨鲨显示科技有限公司 | Method for automatically identifying and calibrating medical color images and medical gray scale images |
| CN105389802A (en) * | 2015-10-20 | 2016-03-09 | 无锡日联科技股份有限公司 | IC component defect detection method based on X-Ray image |
| CN109118497A (en) * | 2018-08-17 | 2019-01-01 | 珠海格力智能装备有限公司 | Method and device for determining graph, storage medium and processor |
| CN110211184A (en) * | 2019-06-25 | 2019-09-06 | 珠海格力智能装备有限公司 | Method and device for positioning lamp beads in LED display screen |
| CN111754538A (en) * | 2019-06-29 | 2020-10-09 | 浙江大学 | Threshold segmentation method for USB surface defect detection |
| CN111948209A (en) * | 2019-05-14 | 2020-11-17 | 华为技术有限公司 | Selective wave soldering equipment and nozzle detection method and device thereof |
| CN109378279B (en) * | 2018-11-12 | 2020-12-18 | 武汉新芯集成电路制造有限公司 | Wafer detection method and wafer detection system |
| CN113298769A (en) * | 2021-05-20 | 2021-08-24 | 佛山职业技术学院 | FPC flexible flat cable appearance defect detection method, system and medium |
| CN117252876A (en) * | 2023-11-17 | 2023-12-19 | 江西斯迈得半导体有限公司 | LED support defect detection method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551230A (en) * | 2009-05-26 | 2009-10-07 | 上海理工大学 | Detecting device for resist-nailed seat of anastomat and detecting method thereof |
| CN102207467B (en) * | 2011-04-02 | 2013-08-07 | 云南昆船设计研究院 | Method and device for online detection and rejection of unembossed coins |
-
2013
- 2013-09-18 CN CN201310432371.2A patent/CN103473778B/en active Active
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484659B (en) * | 2014-12-30 | 2018-08-07 | 南京巨鲨显示科技有限公司 | A method of to Color medical and gray scale image automatic identification and calibration |
| CN104484659A (en) * | 2014-12-30 | 2015-04-01 | 南京巨鲨显示科技有限公司 | Method for automatically identifying and calibrating medical color images and medical gray scale images |
| CN105389802A (en) * | 2015-10-20 | 2016-03-09 | 无锡日联科技股份有限公司 | IC component defect detection method based on X-Ray image |
| CN105389802B (en) * | 2015-10-20 | 2018-07-03 | 无锡日联科技股份有限公司 | A kind of IC component defect inspection methods based on X-Ray images |
| CN109118497A (en) * | 2018-08-17 | 2019-01-01 | 珠海格力智能装备有限公司 | Method and device for determining graph, storage medium and processor |
| CN109378279B (en) * | 2018-11-12 | 2020-12-18 | 武汉新芯集成电路制造有限公司 | Wafer detection method and wafer detection system |
| CN111948209A (en) * | 2019-05-14 | 2020-11-17 | 华为技术有限公司 | Selective wave soldering equipment and nozzle detection method and device thereof |
| CN110211184A (en) * | 2019-06-25 | 2019-09-06 | 珠海格力智能装备有限公司 | Method and device for positioning lamp beads in LED display screen |
| CN111754538A (en) * | 2019-06-29 | 2020-10-09 | 浙江大学 | Threshold segmentation method for USB surface defect detection |
| CN113298769A (en) * | 2021-05-20 | 2021-08-24 | 佛山职业技术学院 | FPC flexible flat cable appearance defect detection method, system and medium |
| CN113298769B (en) * | 2021-05-20 | 2023-01-24 | 佛山职业技术学院 | FPC flexible flat cable appearance defect detection method, system and medium |
| CN117252876A (en) * | 2023-11-17 | 2023-12-19 | 江西斯迈得半导体有限公司 | LED support defect detection method and system |
| CN117252876B (en) * | 2023-11-17 | 2024-02-09 | 江西斯迈得半导体有限公司 | LED support defect detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103473778B (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103473778A (en) | Detecting algorithm for eccentrically-inserting defect of LED luminous chip | |
| CN204359710U (en) | A kind of glass surface defects pick-up unit | |
| CN109084957B (en) | Defect detection and color sorting method and system for photovoltaic solar crystalline silicon cell | |
| CN102854192B (en) | Method for detecting apple surface defect based on apple surface defect detecting system | |
| CN104504388B (en) | A kind of pavement crack identification and feature extraction algorithm and system | |
| CN102288613B (en) | Surface defect detecting method for fusing grey and depth information | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN104118609B (en) | Labeling quality determining method and device | |
| WO2014139231A1 (en) | System and method for testing and regulating uniformity of light intensity of light source | |
| CN104135660A (en) | Detection method of contamination of image pickup module and detection system | |
| CN103792705A (en) | Detecting method and detecting device for detecting substrate defects | |
| CN104537651A (en) | Proportion detecting algorithm and system for cracks in road surface image | |
| CN104568989A (en) | Glass substrate defect detecting method | |
| CN202974891U (en) | Automatic detector for optical glass surface defects | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN102854195B (en) | Method for detecting defect coordinates on color filter | |
| CN105158273A (en) | Optical cable surface defect detecting system based on planar array CMOS cameras | |
| CN111665251A (en) | Visual detection method for surface defects | |
| CN203908956U (en) | System for detecting surface defects of workpiece | |
| CN104766310A (en) | Light source detecting system and method | |
| CN102507008B (en) | Multi-template automatic optical color detection method | |
| CN101676040A (en) | Optical detecting system and method for classifying solar cells | |
| CN104101614B (en) | A kind of detection method and device | |
| CN115115643A (en) | Method for detecting production defects of photovoltaic cell panel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Detecting method for eccentrically-inserting defect of LED luminous chip Effective date of registration: 20171221 Granted publication date: 20170111 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: Shaanxi Zhonglai Energy-saving Co., Ltd. Registration number: 2017990001199 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20190102 Granted publication date: 20170111 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: Shaanxi Zhonglai Energy-saving Co., Ltd. Registration number: 2017990001199 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |