CN108537153A - A kind of detection of log board hole defect and localization method based on ellipse fitting - Google Patents
A kind of detection of log board hole defect and localization method based on ellipse fitting Download PDFInfo
- Publication number
- CN108537153A CN108537153A CN201810260055.4A CN201810260055A CN108537153A CN 108537153 A CN108537153 A CN 108537153A CN 201810260055 A CN201810260055 A CN 201810260055A CN 108537153 A CN108537153 A CN 108537153A
- Authority
- CN
- China
- Prior art keywords
- log board
- hole
- ellipse
- image
- pixel
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The detection of log board hole defect and localization method that the present invention relates to a kind of based on ellipse fitting, include the following steps:S1. it is taken pictures to log board downwards in log board conveyor belts upper vertical using capture apparatus, obtains the image of log board;S2. aberration mean-square value operation is done to each pixel in the image of log board, binary conversion treatment is done to the image of log board according to aberration mean-square value;S3. it utilizes Labeling Connected Component method in demarcating hole edge point in universe the binary image that step S2 is obtained, completes the calibration of each hole edge point and gradually number;S4. ellipse fitting is carried out respectively to each hole edge point that step S3 is obtained, make fitted ellipse energy minimization is completely covered hole;S5. the fixed strip for being painted with calibration line that log board both ends in step S1 are used to be compacted with plank carries out pixel measurement, to realize the Pixel-level positioning in entire image, elliptical centre point is accurately positioned in conjunction with fitted ellipse information, and is sent to numerically-controlled machine tool equipment.
Description
Technical field
The present invention relates to wood processing technique fields, more particularly, to a kind of log board hole based on ellipse fitting
Hole defect detects and localization method.
Background technology
China's forest tree resource is relatively deficient, and it is timber processing and automatic field to improve timber volume recovery and production efficiency
It is crucial.And the mass defects such as the knot of timber, crackle, rotten can make solid wood board have porosity, hierarchy, it can direct shadow
It rings to the use value of log board and economic value etc..Traditional timber processing enterprise detects and positions using artificial mostly,
Artificial detection is low with the efficiency of positioning, and can waste of manpower resource.Wood surface detection refers to obtaining log by lossless manner
The surface defect data of plank, such as surface defect pore quantity, shape, position and size, numerical control is transmitted to by data information
Lathe etc., realization quickly fill up scheme.Solid wood board is detected automatically using image recognition technology and graphics techniques, quickly
Positioning and preferably fill out hole, can not only maximally utilise plank, but can increase substantially log board preferably process it is automatic
Change horizontal.
Invention content
The present invention be solve the prior art by manually to log board hole be detected the existing efficiency of positioning it is low,
The technological deficiency of waste of human resource, provide it is a kind of based on ellipse fitting log board hole defect detection with positioning side
Method.
To realize the above goal of the invention, the technical solution adopted is that:
A kind of detection of log board hole defect and localization method based on ellipse fitting, include the following steps:
S1. it is taken pictures downwards, is obtained to log board in log board conveyor belts upper vertical using capture apparatus
Obtain the image of log board;
S2. aberration mean-square value operation is done to each pixel in the image of log board, it is then square according to aberration
Value does binary conversion treatment to the image of log board, and the pixel that aberration mean-square value is more than to a certain setting value is set as 1, and incite somebody to action
The pixel that aberration mean-square value is less than a certain setting value is set as 0;Thus hole and background are isolated;
S3. the binary image obtained to step S2 is using Labeling Connected Component method in demarcating hole edge in universe
Point is completed the calibration of each hole edge point and is gradually numbered;
S4. ellipse fitting is carried out respectively to each hole edge point that step S3 is obtained, makes fitted ellipse energy minimization
Hole is completely covered;
S5. the fixed strip for being painted with calibration line that log board both ends in step S1 are used to be compacted with plank carries out pixel degree
Elliptical centre point is accurately positioned to realize the Pixel-level positioning in entire image in conjunction with fitted ellipse information by amount, and
It is sent to numerically-controlled machine tool equipment.
Preferably, the detailed process of the step S2 progress aberration mean-square value operation is as follows:
1) each pixel P is first takenx,yThe average value of tri- color values of RBG of (R, G, B)
2) point and three color average values are soughtMean-square value θ:
Preferably, the detailed process that the step S3 numbers hole marginal point is as follows:
It is 0 for background, the bianry image that hole is 1 carries out progressive image scanning from top to bottom, continuous in every a line
Black picture element form sequence and become one group, record its starting position, final position and line number where it;It scans next
When row, the group of continuous black picture element is equally found, if the group with lastrow has overlapping region, by the group mark assignment of lastrow
To it;If it has overlapping region with more than two groups of lastrow, the minimum label of the group that is connected is assigned to current group, and
The group echo write-in of lastrow is of equal value right;By every a line equivalence in the group of identical label to being converted to equivalent sequence, each
For sequence with an identical label is given, label gives one label of each equivalent sequence since 2;Traversal starts the label of group, looks into
Equivalent sequence is looked for, gives equivalent sequence new label, that is, completes hole edge point search and number.
Preferably, the step S4 realizes that the pinpoint detailed process of oval centre point is as follows:
Utilize n marginal point (x for being marked hole1,y1), (x2,y2) ... (xn,yn) one covering cavity of fitting is most
The ellipse of small area asks fitted ellipse method, elliptic curve that can be expressed as according to least square method:
If considering central point offset, it is not in another elliptical description form of origin:
It arranges:
It enables:
Then expansion can be expressed as:
Ax2+By2+ Cxy=1
The formula shows that ellipse long and short shaft is no longer parallel with reference axis, but central point is moved on to (x by center still in origin0,
y0) obtain:
A(x-x0)2+By(y-y0)2+C(x-x0)(y-y0)=1
Expansion has:
Corresponding to ellipse general equation is:
x2+gxy+cy2+ dx+ey+f=0
Wherein Parameter g, c, d is determined, e, f can be obtained by elliptical center (x0,y0), rotation angle
θ and major and minor axis a and b, the least square solution of this five yuan of linear function groups;
If certain point (xi,yj) bring error ε intoi, the principle of least square is exactly with the quadratic sum of minimization error in equation come really
Fixed each index parameter;
ThereforeSingle order local derviation is asked to parameters
Above-mentioned equation is solved to acquire least squares sense parameters g, c, d, e, f, to acquire in ellipse
The heart (x0,y0), rotation angle θ and major and minor axis a and b.
Compared with prior art, the beneficial effects of the invention are as follows:
Image processing techniques and graphics are combined by the present invention, and the log board on conveyer belt is obtained by capture apparatus
Image handles to obtain black and white binary map using aberration mean-square value, and initial gross separation goes out the hole of existing defects, recycles two-value connection
Zone marker method finds hole marginal point in universe, gradually numbers, and is obtained using ellipse fitting according to the marginal point after number
The minimum ellipse of coverage hole;Measurement pixel value is determined according to the calibration line at compacting plank edge, is finally measured and is tied according to pixel
Fruit calculates ellipse center location, realizes being accurately positioned for repairing hole, is sent to numerically-controlled machine tool equipment and completes the operation of original plank filling-up hole.
The present invention completes the detection and positioning to log plate holes and larger color difference block with capture apparatus, contributes to the automatic of numerically-controlled machine tool
Operation.
Description of the drawings
Fig. 1 is the flow diagram of method.
Fig. 2 is the schematic diagram that log board transmitted and obtained image.
Fig. 3 is the image schematic diagram of the log board obtained.
Fig. 4 is the schematic diagram of binary image.
Specific implementation mode
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent;
Below in conjunction with drawings and examples, the present invention is further elaborated.
Embodiment 1
As shown in Figure 1, the detection of log board hole defect and localization method provided by the invention based on ellipse fitting, packet
Include following steps:
S1. it is taken pictures downwards, is obtained to log board in log board conveyor belts upper vertical using capture apparatus
Obtain the image of log board;It is that the larger color of RGB color difference mean-square value is (such as red, green wherein to require the color of conveyor belts
Color, blue etc.), using it as background so that hole forms larger aberration with log board and compares.Log board is in parallel
In the conveyor belts of traveling, capture apparatus is located at right over conveyer belt perpendicular to conveyer belt, as shown in Figure 2.The log of acquisition
The image of plank is as shown in Figure 3.
S2. aberration mean-square value operation is done to each pixel in the image of log board, it is then square according to aberration
Value does binary conversion treatment to the image of log board, and the pixel that aberration mean-square value is more than to a certain setting value is set as 1, and incite somebody to action
The pixel that aberration mean-square value is less than a certain setting value is set as 0;Thus hole and background are isolated.Wherein poor mean-square value is small
For plank true qualities, its two-value array is set as 0, aberration mean-square value is then greatly the corresponding background colour of hole, by its two-value array
It is set as 1.In view of being possible to the noise speckle for occurring tiny in two-value picture, thus using morphological erosion expansion algorithm into
Row smoothing denoising.Example images after binaryzation are as shown in Figure 4.
S3. the binary image obtained to step S2 is using Labeling Connected Component method in demarcating hole edge in universe
Point is completed the calibration of each hole edge point and is gradually numbered;
S4. ellipse fitting is carried out respectively to each hole edge point that step S3 is obtained, makes fitted ellipse energy minimization
Hole is completely covered;
S5. the fixed strip for being painted with calibration line that log board both ends in step S1 are used to be compacted with plank carries out pixel degree
Elliptical centre point is accurately positioned to realize the Pixel-level positioning in entire image in conjunction with fitted ellipse information by amount, and
It is sent to numerically-controlled machine tool equipment.As shown in Figure 2, calibration line is printed on plank compacting item, calibration line is 1 centimetre of equal length black and white
Alternate striped, detects the pixel number of 1 centimetre of black block and 1 centimetre of white blocks of each row black and white strip line, then is averaged
Value, finds out the average value of 1 cm section pixel, then can calculate 1 pixel in place represent how long distance.And then it can be gradually
Find out elliptical center, major and minor axis data materialization.
In the present embodiment, the detailed process that the step S2 carries out aberration mean-square value operation is as follows:
1) each pixel P is first takenx,yThe average value of tri- color values of RBG of (R, G, B)
2) point and three color average values are soughtMean-square value θ:
In the present embodiment, the detailed process that the step S3 numbers hole marginal point is as follows:
It is 0 for background, the bianry image that hole is 1 carries out progressive image scanning from top to bottom, continuous in every a line
Black picture element form sequence and become one group, record its starting position, final position and line number where it;It scans next
When row, the group of continuous black picture element is equally found, if the group with lastrow has overlapping region, by the group mark assignment of lastrow
To it;If it has overlapping region with more than two groups of lastrow, the minimum label of the group that is connected is assigned to current group, and
The group echo write-in of lastrow is of equal value right;By every a line equivalence in the group of identical label to being converted to equivalent sequence, each
For sequence with an identical label is given, label gives one label of each equivalent sequence since 2;Traversal starts the label of group, looks into
Equivalent sequence is looked for, gives equivalent sequence new label, that is, completes hole edge point search and number.
In the present embodiment, the step S4 realizes that the pinpoint detailed process of oval centre point is as follows:
Utilize n marginal point (x for being marked hole1,y1), (x2,y2) ... (xn,yn) one covering cavity of fitting is most
The ellipse of small area asks fitted ellipse method, elliptic curve that can be expressed as according to least square method:
If considering central point offset, it is not in another elliptical description form of origin:
It arranges:
It enables:
Then expansion can be expressed as:
Ax2+By2+ Cxy=1
The formula shows that ellipse long and short shaft is no longer parallel with reference axis, but central point is moved on to (x by center still in origin0,
y0) obtain:
A(x-x0)2+By(y-y0)2+C(x-x0)(y-y0)=1
Expansion has:
Corresponding to ellipse general equation is:
x2+gxy+cy2+ dx+ey+f=0
Wherein Parameter g, c, d is determined, e, f can be obtained by elliptical center (x0,y0), rotation angle
θ and major and minor axis a and b, the least square solution of this five yuan of linear function groups;
If certain point (xi,yj) bring error ε intoi, the principle of least square is exactly with the quadratic sum of minimization error in equation come really
Fixed each index parameter;
ThereforeSingle order local derviation is asked to parameters
Above-mentioned equation is solved to acquire least squares sense parameters g, c, d, e, f, to acquire in ellipse
The heart (x0,y0), rotation angle θ and major and minor axis a and b.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement etc., should be included in the claims in the present invention made by within the spirit and principle of invention
Protection domain within.
Claims (4)
1. a kind of detection of log board hole defect and localization method based on ellipse fitting, it is characterised in that:Including following step
Suddenly:
S1. it is taken pictures downwards, is obtained former to log board in log board conveyor belts upper vertical using capture apparatus
The image of wood plank;
S2. aberration mean-square value operation is done to each pixel in the image of log board, then according to aberration mean-square value pair
The image of log board does binary conversion treatment, and the pixel that aberration mean-square value is more than to a certain setting value is set as 1, and by aberration
The pixel that mean-square value is less than a certain setting value is set as 0;Thus hole and background are isolated;
S3. binary image step S2 obtained using Labeling Connected Component method in demarcating hole edge point in universe,
It completes the calibration of each hole edge point and gradually numbers;
S4. ellipse fitting is carried out respectively to each hole edge point that step S3 is obtained, makes the complete of fitted ellipse energy minimization
All standing hole;
S5. the fixed strip for being painted with calibration line that log board both ends in step S1 are used to be compacted with plank carries out pixel measurement, from
And realize the Pixel-level positioning in entire image, elliptical centre point is accurately positioned in conjunction with fitted ellipse information, and sends
Give numerically-controlled machine tool equipment.
2. the detection of log board hole defect and localization method according to claim 1 based on ellipse fitting, feature
It is:The detailed process that the step S2 carries out aberration mean-square value operation is as follows:
1) each pixel P is first takenx,yThe average value of tri- color values of RBG of (R, G, B)
2) point and three color average values are soughtMean-square value θ:
3. the detection of log board hole defect and localization method according to claim 1 based on ellipse fitting, feature
It is:The detailed process that the step S3 numbers hole marginal point is as follows:
It is 0 for background, the bianry image that hole is 1 carries out progressive image scanning from top to bottom, continuous black in every a line
Color pixel, which forms a sequence, becomes one group, records its starting position, final position and line number where it;Scan next line
When, the group of continuous black picture element is equally found, if the group with lastrow has overlapping region, the group mark of lastrow is assigned to
It;If it has overlapping region with more than two groups of lastrow, the minimum label of the group that is connected is assigned to current group, and will
The group echo write-in of lastrow is of equal value right;By in the group of identical label per a line equivalence to being converted to equivalent sequence, each sequence
For row with an identical label is given, label gives one label of each equivalent sequence since 2;Traversal starts the label of group, searches
Equivalent sequence gives equivalent sequence new label, that is, completes hole edge point search and number.
4. the detection of log board hole defect and localization method according to claim 1 based on ellipse fitting, feature
It is:The step S4 realizes that the pinpoint detailed process of oval centre point is as follows:
Utilize n marginal point (x for being marked hole1,y1), (x2,y2) ... (xn,yn) the empty minimal face of one covering of fitting
Long-pending ellipse asks fitted ellipse method, elliptic curve that can be expressed as according to least square method:
If considering central point offset, it is not in another elliptical description form of origin:
It arranges:
It enables:
Then expansion can be expressed as:
Ax2+By2+ Cxy=1
The formula shows that ellipse long and short shaft is no longer parallel with reference axis, but central point is moved on to (x by center still in origin0,y0)
It arrives:
A(x-x0)2+By(y-y0)2+C(x-x0)(y-y0)=1
Expansion has:
Corresponding to ellipse general equation is:
x2+gxy+cy2+ dx+ey+f=0
Wherein Parameter g, c, d is determined, e, f can be obtained by elliptical center (x0,y0), rotation angle
θ and major and minor axis a and b, the least square solution of this five yuan of linear function groups;
If certain point (xi,yj) bring error ε intoi, the principle of least square is exactly to be determined respectively with the quadratic sum of minimization error in equation
Index parameter;
ThereforeSingle order local derviation is asked to parameters
Above-mentioned equation is solved to acquire least squares sense parameters g, c, d, e, f, to acquire elliptical center (x0,
y0), rotation angle θ and major and minor axis a and b.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810260055.4A CN108537153B (en) | 2018-03-27 | 2018-03-27 | Log plate hole defect detection and positioning method based on ellipse fitting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810260055.4A CN108537153B (en) | 2018-03-27 | 2018-03-27 | Log plate hole defect detection and positioning method based on ellipse fitting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108537153A true CN108537153A (en) | 2018-09-14 |
CN108537153B CN108537153B (en) | 2021-08-24 |
Family
ID=63485204
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810260055.4A Active CN108537153B (en) | 2018-03-27 | 2018-03-27 | Log plate hole defect detection and positioning method based on ellipse fitting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537153B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112991307A (en) * | 2021-03-25 | 2021-06-18 | 中南大学 | Defect circle fitting method and device for drilling blasting and medium |
CN113379688A (en) * | 2021-05-28 | 2021-09-10 | 慕贝尔汽车部件(太仓)有限公司 | Stabilizer bar hole deviation detection method and system based on image recognition |
CN113780200A (en) * | 2021-09-15 | 2021-12-10 | 安徽理工大学 | Computer vision-based pavement multi-disease area detection and positioning method |
CN114782450A (en) * | 2022-06-23 | 2022-07-22 | 北京航空航天大学杭州创新研究院 | Hole filling equipment control method, device, equipment and computer readable medium |
CN115239714A (en) * | 2022-09-22 | 2022-10-25 | 山东汇智家具股份有限公司 | Raw wood material grading evaluation method for floor production |
CN116703922A (en) * | 2023-08-08 | 2023-09-05 | 青岛华宝伟数控科技有限公司 | Intelligent positioning method and system for sawn timber defect position |
CN117214183A (en) * | 2023-11-07 | 2023-12-12 | 山东泗水金立得纸业有限公司 | Paper defect detection method based on machine vision |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0467149A2 (en) * | 1990-07-18 | 1992-01-22 | Dainippon Screen Mfg. Co., Ltd. | Method of and device for inspecting pattern of printed circuit board |
JPH1043917A (en) * | 1996-07-31 | 1998-02-17 | Seiko Precision Kk | Boring method for plate-like work and boring device and boring position detecting method and boring position detecting device |
EP1061466A2 (en) * | 1999-06-10 | 2000-12-20 | Konica Corporation | Optical pickup device and optical type surface displacement detecting apparatus |
CN203148381U (en) * | 2013-01-07 | 2013-08-21 | 电子科技大学 | Automatic device for detecting plate holes and groove positions of furniture plates |
CN105976352A (en) * | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
-
2018
- 2018-03-27 CN CN201810260055.4A patent/CN108537153B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0467149A2 (en) * | 1990-07-18 | 1992-01-22 | Dainippon Screen Mfg. Co., Ltd. | Method of and device for inspecting pattern of printed circuit board |
JPH1043917A (en) * | 1996-07-31 | 1998-02-17 | Seiko Precision Kk | Boring method for plate-like work and boring device and boring position detecting method and boring position detecting device |
EP1061466A2 (en) * | 1999-06-10 | 2000-12-20 | Konica Corporation | Optical pickup device and optical type surface displacement detecting apparatus |
CN203148381U (en) * | 2013-01-07 | 2013-08-21 | 电子科技大学 | Automatic device for detecting plate holes and groove positions of furniture plates |
CN105976352A (en) * | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
Non-Patent Citations (1)
Title |
---|
安新源 等: ""椭圆拟合的非线性最小二乘方法"", 《计算机工程与应用》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112991307A (en) * | 2021-03-25 | 2021-06-18 | 中南大学 | Defect circle fitting method and device for drilling blasting and medium |
CN113379688A (en) * | 2021-05-28 | 2021-09-10 | 慕贝尔汽车部件(太仓)有限公司 | Stabilizer bar hole deviation detection method and system based on image recognition |
CN113379688B (en) * | 2021-05-28 | 2023-12-08 | 慕贝尔汽车部件(太仓)有限公司 | Stabilizer bar hole deviation detection method and system based on image recognition |
CN113780200A (en) * | 2021-09-15 | 2021-12-10 | 安徽理工大学 | Computer vision-based pavement multi-disease area detection and positioning method |
CN114782450A (en) * | 2022-06-23 | 2022-07-22 | 北京航空航天大学杭州创新研究院 | Hole filling equipment control method, device, equipment and computer readable medium |
CN114782450B (en) * | 2022-06-23 | 2022-10-25 | 北京航空航天大学杭州创新研究院 | Hole filling equipment control method, device, equipment and computer readable medium |
CN115239714A (en) * | 2022-09-22 | 2022-10-25 | 山东汇智家具股份有限公司 | Raw wood material grading evaluation method for floor production |
CN115239714B (en) * | 2022-09-22 | 2022-12-06 | 山东汇智家具股份有限公司 | Raw wood material grading evaluation method for floor production |
CN116703922A (en) * | 2023-08-08 | 2023-09-05 | 青岛华宝伟数控科技有限公司 | Intelligent positioning method and system for sawn timber defect position |
CN116703922B (en) * | 2023-08-08 | 2023-10-13 | 青岛华宝伟数控科技有限公司 | Intelligent positioning method and system for sawn timber defect position |
CN117214183A (en) * | 2023-11-07 | 2023-12-12 | 山东泗水金立得纸业有限公司 | Paper defect detection method based on machine vision |
CN117214183B (en) * | 2023-11-07 | 2024-01-30 | 山东泗水金立得纸业有限公司 | Paper defect detection method based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN108537153B (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537153A (en) | A kind of detection of log board hole defect and localization method based on ellipse fitting | |
KR101298957B1 (en) | Wood knot detecting method, device, and program | |
CN108827316A (en) | Mobile robot visual orientation method based on improved Apriltag label | |
CN109523505B (en) | Method for detecting pattern defects on surface of ceramic tile based on machine vision | |
CN106981081A (en) | A kind of degree of plainness for wall surface detection method based on extraction of depth information | |
CN107358627B (en) | Fruit size detection method based on Kinect camera | |
CN103190224B (en) | Computer vision technique-based corn ear species test method, system and device | |
CN108364675A (en) | A kind of identification method of food weight and nutrient content based on image recognition | |
CN108921804A (en) | Distort the bearing calibration of file and picture | |
CN108985363A (en) | A kind of cracks in reinforced concrete bridge classifying identification method based on RBPNN | |
CN108550138A (en) | Refractory brick surface scratch recognition methods based on frequency filtering enhancing | |
US6947591B2 (en) | Process of identifying the sky in an image and an image obtained using this process | |
CN114241024B (en) | Artificial neural network building texture mapping method and system based on sliding edge detection | |
CN110136196A (en) | A kind of Bridge Crack width method for automatic measurement | |
CN107464233A (en) | The image detecting method and system of composite insulator based on Lab color modes | |
CN106780504A (en) | Flesh automatic division method long is carried on the back in a kind of beef image based on distance holding level set | |
CN110246123A (en) | A kind of tile laying regularity detection method based on machine vision | |
CN111476153A (en) | Method for calculating fruit maturity | |
CN113605188A (en) | Pavement structure testing method | |
CN113506276A (en) | Marker and method for measuring structure displacement | |
CN111860125A (en) | Method for identifying fruit maturity based on machine vision | |
CN1492379A (en) | Method for covering face of news interviewee using quick face detection | |
CN107367513B (en) | Workpiece, defect on-line analysis device | |
CN110530287B (en) | Unwrapping phase error detection and correction method based on fringe series inaccuracy | |
JP2004077290A (en) | Apparatus and method for measuring three-dimensional shape |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |