CN105184792B - A kind of saw blade wear extent On-line Measuring Method - Google Patents
A kind of saw blade wear extent On-line Measuring Method Download PDFInfo
- Publication number
- CN105184792B CN105184792B CN201510559853.3A CN201510559853A CN105184792B CN 105184792 B CN105184792 B CN 105184792B CN 201510559853 A CN201510559853 A CN 201510559853A CN 105184792 B CN105184792 B CN 105184792B
- Authority
- CN
- China
- Prior art keywords
- point
- saw blade
- pixel
- circular saw
- value
- 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.)
- Expired - Fee Related
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention discloses a kind of saw blade wear extent On-line Measuring Method, implementation step is：Industrial computer triggers image pick-up card, and annular saw picture is obtained by industrial camera；Image is pre-processed；Based on adaptive threshold, with 8 neighborhood gray scale similarity screening techniques, the candidate angular of saw blade is found out；Judge whether candidate angular is that unique angle point or its angle point receptance function value are maximum in neighborhood, to reject pseudo- angle point；Judge whether angle point is maximum point, otherwise rejects it, so that it is determined that the whole pixel coordinate of saw blade point of a knife point；Sub-pixel positioning is carried out to point of a knife point using cubic surface fitting process；The radius value of circle where point of a knife point is solved using least square method, the actual wear amount of saw blade is drawn by camera calibration relation.The present invention has that real-time is good, accuracy of detection is high, is a kind of effective saw blade wear extent online test method, and its testing result is that compensation mechanism performs to compensate and provides foundation.
Description
Technical Field
The invention belongs to the technical field of image processing, relates to a visual detection method for a cutter abrasion state, and particularly relates to an online measurement method for an abrasion loss of a circular saw blade. The method is a method for solving the abrasion loss of the circular saw blade according to the positions of angular points by identifying the angular points of the edge of the image.
Background
Machine vision is an emerging detection technology and is widely applied due to the characteristics of rapidness, real time, intelligence and low cost. The measurement based on machine vision belongs to a non-contact measurement mode, the workpiece characteristics can be measured in real time, the measurement efficiency is improved, the parameters such as the focal length of an industrial camera can be adjusted according to the size of a workpiece, the dimension measurement in a wider range is realized, and meanwhile, the measurement error caused by the change of the psychological factors of measuring personnel can be avoided.
At present, there are several methods for detecting the wear amount of the tool. (1) Monitoring the vibration signal and the motor current signal, and constructing the relationship between the vibration signal and the motor current signal and the abrasion loss of the cutter, so as to detect the abrasion state of the cutter; (2) monitoring an acoustic emission signal in the machining process, establishing a relation between the acoustic emission signal and the abrasion loss of the cutter, and detecting the abrasion state of the cutter; (3) with the rapid development of CCD sensors and their application technologies, non-contact detection technologies based on machine vision are widely used in the fields of size, displacement, surface shape detection, etc. There are three methods for detecting tool wear using machine vision: (1) detecting a tool surface image; (2) detecting a texture image of the surface of the workpiece; (3) the chip image is detected.
The above method is also commonly used for circular saw blade wear monitoring. Hangzhou electronic science and technology university Zhao ling et al has constructed circular saw blade geometric parameters measurement system based on machine vision. The method is based on the optimization of the profile of the circular saw blade, an improved quadratic polynomial interpolation sub-pixel positioning method is provided for the circular hole in the circular saw blade, and an improved least square method is adopted for fitting two sections of straight lines at the tooth tip, so that the detection precision is improved. The Swedish Ekevad et al constructs the relation between the abrasion loss of the circular saw blade and the vibration signal of the saw blade in the process of cutting the beech.
Because measured objects are different, the structural characteristics of the measured objects are very different, and a general method is not available for machine vision-based measurement, and different methods are required for different objects. The conventional circular saw blade abrasion loss measuring method based on the classical Harris method is poor in real-time performance, and non-cutter point points are often misjudged as cutter point points.
Disclosure of Invention
The invention aims to overcome the defects of the conventional circular saw blade abrasion loss measuring method, and provides a machine vision-based circular saw blade abrasion loss online measuring method to improve the accuracy of the circular saw blade abrasion loss online measurement.
In order to achieve the purpose, the technical scheme adopted by the invention for achieving the purpose is as follows:
an online measuring method for the abrasion loss of a circular saw blade comprises the following steps:
1) Acquiring a circular saw blade image: an industrial camera arranged on a bracket is manually adjusted to enable the industrial camera to face a measured circular saw blade, and an industrial personal computer triggers an image acquisition card to acquire an image of the circular saw blade;
2) Carrying out noise reduction pretreatment on the image by adopting median filtering;
3) Based on a self-adaptive threshold value, a candidate angular point of the circular saw blade is found out by using an 8-neighborhood gray level similarity screening method;
specifically, the gray scale change E (u, v) caused by the window centered at (x, y) moving along the translation vector (u, v) is:
i (x + u, y + v) is the gray value after translation, I (x, y) is the gray value before translation, omega (x, y) is the Gaussian window function,
in differential form of
Wherein
In matrix form of
Wherein M is the autocorrelation function matrix of the target pixel point (x, y)
Window function of gauss
Corner response function value of target pixel point (x, y):
CRF(x,y)＝det(M)-k(trace(M)) 2
where det (M) represents determinant of matrix M, trace (M) represents trace of matrix, and k is 0.04-0.06;
taking the standard difference of the gray value of the image of each pixel point in the range of the target point (x, y) and the 8 neighborhoods thereof as a similarity judgment threshold t of the 8 neighborhoods, and taking the maximum corner point response function value CRF max One hundredth as the corner response detection threshold T,
and (3) calculating the gray value difference delta I between the target point (x, y) and each pixel point in the 8 neighborhood range, counting the number n of the pixel points of the delta I in the range of [ -T, T ], and taking the target point which satisfies that n is more than or equal to 2 and less than or equal to 6, the corner response function value of which is more than T and the local maximum as a candidate corner.
4) Judging whether the candidate angular point is a unique angular point in a neighborhood or the angular point response function value of the candidate angular point is the maximum, and eliminating a false angular point;
those candidate angles that are the only corner points in their 5 x 5 neighborhood or those candidate angles in their 5 x 5 neighborhood for which the CRF value is maximal are retained.
5) Judging whether the angular point is the maximum point on the curve to eliminate the tooth root point, thereby determining the whole pixel coordinate of the tool point of the circular saw blade
Slope k of the line connecting the corner point and the previous corner point i1
Slope k of connecting line between corner point and subsequent corner point i2
(x i ,y i ) Is the pixel coordinate of the ith corner point, (x) i-1 ,y i-1 ) Is the pixel coordinate of the corner point preceding the ith corner point, (x) i+1 ,y i+1 ) Is the corner pixel coordinate subsequent to the ith corner,
if k is i1 < 0 and k i2 >, 0, judging that the point is not the tool nose point, removing the point,
6) Sub-pixel positioning of tool cusp point by cubic surface fitting method
Binary cubic function form of CRF for integer pixel cusp point (x, y) and points within some neighborhood:
sum of squares of errors of the fit
Obtaining a 00 ，a 01 ，a 02 ，a 03 ，a 10 ，a 20 ，a 30 ，a 11 ，a 21 ，a 12
And solving CRF of the integer pixel tool nose point subdivided into 3 multiplied by 3 sub-pixel points by using the determined cubic surface expression, and taking a sub-pixel coordinate corresponding to the maximum value of the CRF in the 9 sub-pixel points as the coordinate of the tool nose point.
7) Solving the radius value of the circle where the tool point is located by using a least square method, and obtaining the actual abrasion loss of the circular saw blade through the calibration relation of a camera
Definition of
r 2 ＝(A 2 +B 2 -4C)/4
And then, according to the camera calibration relation, the actual radius value of the cutter is solved, and the difference of the two detection results is the abrasion loss of the circular saw blade.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. through the twice screening of the step 3 and the step 4, the false corners are removed, and the corner clustering phenomenon of the existing method is avoided.
2. Through the step 5, the tooth root point is eliminated, so that the whole pixel coordinate of the circular saw blade tip point is determined, and the deviation and even the error of circle fitting caused by misjudging the tooth root point as the tip point by the existing method are avoided.
Drawings
FIG. 1 is a schematic block diagram of a measuring apparatus according to an embodiment of the present invention,
figure 2 is a schematic view of an industrial camera installation according to an embodiment of the present invention,
figure 3 is a flow chart of an implementation of an embodiment of the present invention,
FIG. 4 is a drawing comparing the points of the nose of a circular saw blade with smooth transition between adjacent teeth by using the present invention and the prior art,
FIG. 5 is a drawing comparing the point of the blade tip of a circular saw blade with the present invention and the prior art method for the sharp transition between adjacent teeth.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not delimit the invention.
The invention relates to an online measuring method for the abrasion loss of a circular saw blade, which is characterized in that an industrial camera is calibrated before the abrasion loss of the circular saw blade is measured online. As shown in fig. 3, the specific steps are as follows:
step 1, mounting an industrial camera on a bracket, and enabling the industrial camera to face a measured circular saw blade through manual adjustment;
as shown in FIG. 1, the whole measuring device comprises an industrial camera, an image acquisition card, an industrial personal computer and measuring software. As shown in fig. 2, before measuring the amount of wear of the circular saw blade, the industrial camera 3 is mounted on the holder 4, the industrial camera 3 is directed toward the circular saw blade 2 on the machine tool 1 by manual adjustment, and the industrial camera is connected to an image acquisition card (not shown) in the industrial personal computer 6 via a network cable 5.
Step 2, an industrial personal computer triggers an image acquisition card to acquire the images of the circular saw blade through an industrial camera;
the industrial personal computer is used as a main controller, the image acquisition card is communicated with the industrial personal computer through a PCI-e bus, the industrial camera faces the measured circular saw blade, the measured circular saw blade is imaged on the industrial camera after being irradiated by the transmission light source, and the image acquisition card transmits acquired digital images to the industrial personal computer so as to acquire images of the circular saw blade.
Step 3, preprocessing the image;
in order to inhibit noise influence, the original image acquired by the industrial camera is subjected to noise reduction processing. The median filtering is adopted for noise reduction treatment, so that the object and the background are respectively uniform and single, the contrast is high, and other lines and details which are difficult to distinguish are avoided.
Step 4, based on the self-adaptive threshold value, a candidate angular point of the circular saw blade is found out by using an 8-neighborhood gray level similarity screening method;
in order to improve the overall adaptability of the method and reduce the wrong detection and the missed detection of the angular points caused by unreasonable threshold setting, a self-adaptive threshold selection method is used in the circular saw blade tool point detection method. Taking the standard deviation of the gray value of the image as a similarity judgment threshold t of 8 neighborhood gray values; the maximum corner response function value CRF of the image max One hundredth as the corner response detection threshold T.
The gray-scale change E (u, v) caused by the window centered at (x, y) moving along the translation vector (u, v) is:
i (x + u, y + v) is the gray value after translation, I (x, y) is the gray value before translation, omega (x, y) is the Gaussian window function,
in differential form of
Wherein
In matrix form of
Wherein M is the autocorrelation function matrix of the target pixel point (x, y)
Gaussian window function
Corner response function value of target pixel point (x, y):
CRF(x,y)＝det(M)-k(trace(M)) 2
where det (M) represents the determinant of matrix M, trace (M) represents the trace of matrix, and k is 0.04-0.06.
Taking the standard difference between the gray value of the image of each pixel point in the range of the target point (x, y) and the 8 neighborhoods thereof as a judgment threshold t of the similarity of the gray values of the 8 neighborhoods, and taking the maximum corner point response function value CRF max One hundredth as the corner response detection threshold T,
and (3) calculating the gray value difference delta I between the target point (x, y) and each pixel point in the 8 neighborhood range, counting the number n of the pixel points of the delta I in the range of [ -T, T ], and taking the target point which satisfies that n is more than or equal to 2 and less than or equal to 6, the corner response function value of which is more than T and the local maximum as a candidate corner.
Step 5, aiming at the candidate angular points, judging whether the candidate angular points are the only angular points in the neighborhood or the angular point response function values of the candidate angular points are the maximum, and eliminating false angular points;
and judging the true and false angular points of the candidate angular points. Taking a 5 multiplied by 5 neighborhood of each target point as an interested area, judging whether the target point is a unique corner point, and if so, taking the target point as a real corner point for storage; if not, the judgment is carried out again. And searching other corner points in the 5 multiplied by 5 neighborhood, and storing the pixel point with the maximum CRF in the corner points as a real corner point.
Step 6, judging whether the angular point is a maximum point on the curve to eliminate the tooth root point, thereby determining the integral pixel coordinate of the tool point of the circular saw blade;
all the corner points on the circular saw blade are extracted, but these corner points include not only the nose points of the circular saw blade but also the root points between adjacent saw teeth, and these non-nose points cause deviation or even error in the circle fitting, so that re-screening is performed to eliminate the non-nose points. When the edge profile of the circular saw blade is regarded as a continuous curve, the tool tip point is the maximum value point on the curve, and the tooth root point between adjacent saw teeth is the minimum value point of the curve.
Slope k of the line connecting a corner point and a preceding corner point i1
Slope k of connecting line between corner point and subsequent corner point i2
(x i ,y i ) Is the pixel coordinate of the ith corner point, (x) i-1 ,y i-1 ) Is the pixel coordinate of the corner point preceding the ith corner point, (x) i+1 ,y i+1 ) Is the corner pixel coordinate subsequent to the ith corner,
if k is i1 < 0 and k i2 >, 0, judging that the point is not the tool nose point, removing the point,
step 7, performing sub-pixel positioning on the tool cusp point by utilizing a cubic surface fitting method;
in order to improve the detection precision on the premise of not changing hardware equipment, the sub-pixel positioning is carried out on the tool cusp. The sub-pixel is to perform k subdivision on the physical pixel, and if the original image is n rows and m columns, the k subdivision becomes kn rows and km columns, which means that each pixel is divided into smaller units, so that the interpolation operation is performed on the smaller units to improve the accuracy of the method.
A binary cubic representation of CRF for the integer pixel cusp point (x, y) and for points in some neighborhood:
sum of squares of errors of the fit
Find a 00 ，a 01 ，a 02 ，a 03 ，a 10 ，a 20 ，a 30 ，a 11 ，a 21 ，a 12
And solving CRF of subdividing the whole-pixel tool nose point into 3 multiplied by 3 sub-pixel points by utilizing the determined cubic surface expression, and taking a sub-pixel coordinate corresponding to the maximum value of the CRF in 9 sub-pixel points as the coordinate of the tool nose point.
Step 8, solving the radius value of the circle where the tool point is located by using a least square method, and obtaining the actual abrasion loss of the circular saw blade through the camera calibration relation
Definition of
According to
r 2 ＝(A 2 +B 2 -4C)/4
And (3) calculating the actual radius value of the cutter, wherein the difference of the two detection results is the pixel value of the abrasion loss of the circular saw blade.
The beneficial effects of the present invention can be further illustrated by the following experiments
1. Content of the experiment
The test was carried out with 2 circular saw blades, in fig. 4a the transition between adjacent teeth of the circular saw blade was gentle, in fig. 5a the transition between adjacent teeth of the circular saw blade was jerky, and the point of the blade of the circular saw blade was extracted by the classical Harris method, the modified Harris method and the method according to the invention.
2. Experimental device
The industrial personal computer adopts an industrial personal computer IPC-610H of Taiwan Shanhua, the CPU is E5300, and the internal memory is 2G; the image acquisition card adopts PCIe-GIE64+ image acquisition card of Taiwan Linghua company; the industrial camera adopts 500 ten thousand pixels acA2500-14gm industrial camera of BASLER company in Germany, and the lens adopts M5018-MP2 fixed focus lens of Japan computer company.
3. Results of the experiment
In order to verify the effectiveness of the invention, a circular saw blade tool point detection effect comparison experiment is designed. Two circular saw blades with different appearance characteristics are adopted in the experiment, the blade tip points of the circular saw blades are extracted by adopting the classical Harris method, the improved Harris method and the method of the invention respectively, the detection results are listed in tables 1 and 2, and the detection effect graph is shown in figures 4 and 5.
TABLE 1 circular saw blade detection parameters with smooth transition between adjacent teeth
| Run time(s) | Number of points of the nose | Number of detected corner points | |
| Classical Harris method | 5.25 | 10 | 10 |
| Improved Harris process | 1.078 | 10 | 14 |
| The method of the invention | 1.571 | 10 | 10 |
TABLE 2 detection parameters for circular saw blades with sharp transitions between adjacent teeth
| Run time(s) | Number of points of the nose | Number of detected corner points | |
| Classical Harris method | 4.39 | 12 | 24 |
| Improved Harris process | 1.031 | 12 | 32 |
| The method of the invention | 1.304 | 12 | 12 |
The running time of the improved Harris method is shortest and is less than 20% of that of the classical Harris method; the process run time of the present invention is also less than 35% of the classical Harris process. The method has the best effect of extracting the tool point; the classical Harris method has good effect of extracting the tool point of the circular saw blade with smooth transition between adjacent sawteeth, but the angular point extracted by the classical Harris method for the circular saw blade with rapid transition between the adjacent sawteeth not only comprises the tool point, but also comprises the tooth root point between the adjacent sawteeth; the corner points extracted by the improved Harris method have serious clustering phenomenon, and the detection effect is the worst. It can be seen that the method of the present invention is more effective in circular saw blade wear detection applications.
Claims (5)
1. An online measuring method for the abrasion loss of a circular saw blade comprises the following steps:
(1) Acquiring a circular saw blade image;
(2) Carrying out noise reduction pretreatment on the acquired image;
(3) Based on the self-adaptive threshold value, a candidate angular point of the circular saw blade is found out by using an 8-neighborhood gray level similarity screening method;
(4) Judging whether the candidate angular point is a unique angular point in a neighborhood or the angular point response function value of the candidate angular point is the maximum, and eliminating a false angular point; reserving candidate corners which are unique corners in the 5 x 5 neighborhood or candidate corners in the 5 x 5 neighborhood with the largest corner response function value;
(5) Judging whether the angular point is a maximum point on the curve to eliminate a tooth root point, thereby determining the whole pixel coordinate of the tool point of the circular saw blade;
(6) Performing sub-pixel positioning on the sharp point by utilizing a cubic surface fitting method;
(7) Solving the radius value of the circle where the tool point is located by using a least square method, and obtaining the actual abrasion loss of the circular saw blade through an industrial camera calibration relation;
the method for sub-pixel positioning of the tool cusp point in the step 6 is characterized by comprising the following steps:
the two-element cubic function representation form of the CRF of the whole pixel knife point (x, y) and each point in a certain neighborhood thereof is as follows:
sum of squares of errors of the fit
Obtaining a 00 ，a 01 ，a 02 ，a 03 ，a 10 ，a 20 ，a 30 ，a 11 ，a 21 ，a 12
Solving CRF of the integer pixel tool nose point subdivided into 3 multiplied by 3 sub-pixel points by using the determined cubic surface expression, and taking a sub-pixel coordinate corresponding to the maximum value of CRF in 9 sub-pixel points as the coordinate of the tool nose point;
the method for determining the candidate corner point in step 3 is as follows:
the change in gray level E (u, v) caused by the movement of the window centered at (x, y) along the translation vector (u, v) is:
in the formula: i (x + u, y + v) is the gray value after translation, I (x, y) is the gray value before translation, and omega (x, y) is a Gaussian window function with the differential form
Wherein
In the form of a matrix of
Wherein M is the autocorrelation function matrix of the target pixel point (x, y)
Gaussian window function
Corner response function value CRF (x, y) of target pixel point (x, y):
CRF(x,y)＝det(M)-k(trace(M)) 2
where det (M) represents the determinant of matrix M, trace (M) represents the trace of matrix, k is 0.04-0.06,
taking the standard difference between the gray value of the image of each pixel point in the range of the target point (x, y) and the 8 neighborhoods thereof as a judgment threshold t of the similarity of the gray values of the 8 neighborhoods, and taking the maximum corner point response function value CRF max One hundredth as the corner response detection threshold T,
calculating the gray value difference delta I between the target point (x, y) and each pixel point in the 8 neighborhood range, counting the number n of the pixel points of the delta I in the range of [ -T, T ], and taking the target point which satisfies that n is more than or equal to 2 and less than or equal to 6, the corner response function value of which is more than T and the local maximum as a candidate corner;
the method for eliminating the root points of the circular saw blade in the step 5 comprises the following steps:
slope k of the line connecting a corner point and a preceding corner point i1
Slope k of connecting line between corner point and subsequent corner point i2
(x i ,y i ) Is the pixel coordinate of the ith corner point, (x) i-1 ,y i-1 ) Is the pixel coordinate of the corner point preceding the ith corner point, (x) i+1 ,y i+1 ) Is the corner pixel coordinate subsequent to the ith corner,
reject those k i1 <, 0 and k i2 >, 0.
2. The method for measuring the amount of wear of a circular saw blade in-line according to claim 1, wherein the method for obtaining the image of the circular saw blade in the step 1 is: the industrial camera arranged on the bracket is manually adjusted to be right opposite to the circular saw blade to be detected, and the industrial personal computer triggers the image acquisition card to acquire the image of the circular saw blade.
3. The method for measuring the abrasion loss of the circular saw blade in the on-line manner as claimed in claim 1, wherein the step 2 is a method for performing noise reduction preprocessing on the acquired image, and comprises the following steps: mean filtering, median filtering or wavelet denoising is adopted.
4. The method for measuring the abrasion loss of the circular saw blade in the claim 1, wherein the method for calculating the radius value of the circle where the nose point is located in the step 7 is as follows:
definition of
According to the formula r 2 ＝(A 2 +B 2 4C)/4, calculating the sub-pixel value of the circle radius where the knife point is located.
5. The method for measuring a circular saw blade wear amount on line as claimed in claim 1, wherein the method for calculating the actual wear amount of the circular saw blade in the step 7 is as follows:
(1) Calibrating a camera, namely installing a calibration object with a known size at the position where the circular saw blade is installed, triggering an image acquisition card by an industrial personal computer to acquire an image of the calibration object, calculating a pixel value with the known size according to the acquired image, and dividing the known size by the pixel value to acquire an actual size value represented by each pixel;
(2) And according to the actual radius value of the cutter, the difference of the two detection results is the pixel value of the abrasion loss of the circular saw blade, and the pixel value is multiplied by the actual size value represented by each pixel to obtain the abrasion loss value of the circular saw blade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510559853.3A CN105184792B (en) | 2015-09-06 | 2015-09-06 | A kind of saw blade wear extent On-line Measuring Method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510559853.3A CN105184792B (en) | 2015-09-06 | 2015-09-06 | A kind of saw blade wear extent On-line Measuring Method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105184792A CN105184792A (en) | 2015-12-23 |
| CN105184792B true CN105184792B (en) | 2018-01-30 |
Family
ID=54906845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510559853.3A Expired - Fee Related CN105184792B (en) | 2015-09-06 | 2015-09-06 | A kind of saw blade wear extent On-line Measuring Method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184792B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815831B (en) * | 2016-12-21 | 2020-04-10 | 南昌青橙视界科技有限公司 | Method and device for detecting abrasion of steel wire rope |
| CN111445438B (en) * | 2020-02-26 | 2022-03-15 | 长安大学 | Double-neighborhood grinding crack angle automatic detection method |
| CN111754461B (en) * | 2020-05-28 | 2024-03-01 | 江苏理工学院 | Method and device for positioning image character area of semiconductor chip |
| CN113269766A (en) * | 2021-06-07 | 2021-08-17 | 中铁工程装备集团有限公司 | Hob abrasion detection method, hob abrasion detection device, hob abrasion detection equipment and readable storage medium |
| CN117124139B (en) * | 2023-10-26 | 2024-01-09 | 合肥亚明汽车部件有限公司 | Visual detection method for intelligent machine tool cutter abrasion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071455A (en) * | 2006-05-10 | 2007-11-14 | 航伟科技股份有限公司 | Body image automatic standardizing method |
| CN103530851A (en) * | 2013-10-11 | 2014-01-22 | 深圳市掌网立体时代视讯技术有限公司 | Method and device for eliminating edge sawtooth of digital painting and calligraphy chirography |
| CN103942552A (en) * | 2014-02-11 | 2014-07-23 | 北京大学 | Character image vectorization method and system based on framework instruction |
| CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电（苏州）有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
-
2015
- 2015-09-06 CN CN201510559853.3A patent/CN105184792B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071455A (en) * | 2006-05-10 | 2007-11-14 | 航伟科技股份有限公司 | Body image automatic standardizing method |
| CN103530851A (en) * | 2013-10-11 | 2014-01-22 | 深圳市掌网立体时代视讯技术有限公司 | Method and device for eliminating edge sawtooth of digital painting and calligraphy chirography |
| CN103942552A (en) * | 2014-02-11 | 2014-07-23 | 北京大学 | Character image vectorization method and system based on framework instruction |
| CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电（苏州）有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
Non-Patent Citations (5)
| Title |
|---|
| Machine Learning for High-Speed Corner Detection;Edward Ｒosten 等;《Computer Vision》;20060513;第430-443页 * |
| 一种改进的Harris角点提取算法;王崴 等;《光学精密工程》;20081031;第16卷(第10期);第1995-2001页 * |
| 一种改进的Harris角点检测算法;齐俊 等;《北京印刷学院学报》;20150430;第23卷(第2期);第28-32页 * |
| 改进的Harris亚像素角点快速定位;何海清、黄声享;《中国图象图形学报》;20120731;第17卷(第7期);第855页左栏第2-3段、右栏第3段 * |
| 玻镁板材高速切割机关键技术的研究;吴倩;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150315(第03期);正文第21页3.2节第2段、第31页3.5.3节第1段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105184792A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109060836B (en) | Machine vision-based high-pressure oil pipe joint external thread detection method | |
| CN105184792B (en) | A kind of saw blade wear extent On-line Measuring Method | |
| CN110223296B (en) | Deformed steel bar surface defect detection method and system based on machine vision | |
| CN107341802B (en) | Corner sub-pixel positioning method based on curvature and gray scale compounding | |
| CN107678192B (en) | Mura defect detection method based on machine vision | |
| CN109115800B (en) | Method for rapidly detecting burrs of product and accurately measuring length | |
| Peng et al. | Study of tool wear monitoring using machine vision | |
| CN107796826B (en) | Micro duplicate gear broken tooth defect detection method based on tooth center distance curve analysis | |
| CN110751604A (en) | Machine vision-based steel pipe weld defect online detection method | |
| CN115311629B (en) | Abnormal bending precision monitoring system of bending machine | |
| Zhang et al. | Research on tool wear detection based on machine vision in end milling process | |
| CN111047588A (en) | Imaging measurement method for size of shaft type small part | |
| CN107388991B (en) | A kind of more fillet axial workpiece radius of corner measurement methods in end face | |
| CN114279357A (en) | Die casting burr size measurement method and system based on machine vision | |
| CN113237889A (en) | Multi-scale ceramic detection method and system | |
| CN113607058B (en) | Straight blade size detection method and system based on machine vision | |
| Sa et al. | Improved Otsu segmentation based on sobel operator | |
| CN111815575B (en) | Bearing steel ball part detection method based on machine vision | |
| CN107748897B (en) | Large-size curved part profile quality detection method based on pattern recognition | |
| CN104748684B (en) | Visual detection method and device for crankshaft shoulder back chipping | |
| CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| Cai et al. | PCB defect detection system based on image processing | |
| Chen et al. | Tool wear monitoring based on the combination of machine vision and acoustic emission | |
| CN108416790A (en) | A kind of detection method for workpiece breakage rate | |
| CN111192261A (en) | Method for identifying lens defect types |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191203 Address after: 315040 Zhejiang city of Ningbo province high tech Zone Juxian 587 Lane Road No. 15 Building 2 building 033 17-1 Patentee after: CHINA E-TECH (NINGBO) MARITIME ELECTRONICS RESEARCH INSTITUTE Co.,Ltd. Address before: Meng Xi Road 212003 Zhenjiang city of Jiangsu province Jingkou District No. 2 Patentee before: Jiangsu University of Science and Technology |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180130 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |