CN105389793B - A kind of method of automatic identification body surface fracture strike and width - Google Patents
A kind of method of automatic identification body surface fracture strike and width Download PDFInfo
- Publication number
- CN105389793B CN105389793B CN201510661260.8A CN201510661260A CN105389793B CN 105389793 B CN105389793 B CN 105389793B CN 201510661260 A CN201510661260 A CN 201510661260A CN 105389793 B CN105389793 B CN 105389793B
- Authority
- CN
- China
- Prior art keywords
- pixel
- point
- crack
- value
- histogram
- 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.)
- Active
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
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of automatic identification body surface fracture strike and the methods of width.The method includes：Gray processing, binaryzation are carried out to image and are filtered, Canny edge detections is then carried out, obtains the image of edge of crack pixel；Two curves of edge of crack are extracted, and determine the trend in crack；Two curves are filtered, and calculate fracture width.The present invention carries out the extraction of body surface edge of crack curve using image processing techniques, and need not manually adjust the trend of crack in the picture can calculate the maximum width in crack, and can automatically identify the trend in crack.Image procossing is carried out using the image overall binarization method based on histogram, the pixel of edge of crack can be retained to the maximum extent, improve measurement accuracy.Two curves at first fracture edge are filtered before calculating fracture width, are reduced the quantity put on curve, are improved the calculating speed of fracture width.
Description
Technical field
The invention belongs to image processing fields, and in particular to a kind of to utilize image processing techniques automatic identification object table facial cleft
The trend of seam and the method for fracture width.
Background technology
Include mainly following several currently with the method that image processing techniques identifies body surface fracture width：
Artificial ocular estimate：Crack image is obtained using high-precision camera, using the graduated scale on screen, with the side of range estimation
Formula differentiates the width in crack.Artificial ocular estimate differentiates the width in crack, differentiate a crack usually require tens seconds it is even several
Minute, and the subjectivity of personnel is big, and the result that different people differentiates is all different.Measurement accuracy is low, can not accomplish Pixel-level
Not.
Semi-automatic method of identification：Utilize the width in computer image processing technology automatic discrimination crack.This method relative to
Artificial ocular estimate improves a lot in terms of measurement accuracy, but semi-automatic method of identification needs to have manually adjusted crack in the picture
It walks backward, ability automatic identification comes out.Accuracy of measurement also has relationship with the trend of crack in the picture.Fracture strike with it is vertical
The inclination angle in direction is smaller, and the accuracy of crack identification is higher.In order to ensure that accuracy of measurement usually requires adjustment crack repeatedly
Trend in the picture, this is a time-consuming process.Therefore semi-automatic method of identification is being measured relative to artificial ocular estimate
It is not significantly improved in terms of efficiency.
Invention content
In order to solve the above-mentioned problems in the prior art, the present invention proposes that a kind of automatic identification body surface crack is walked
To and width method, this method need not manually adjust the trend in crack, as long as in the picture, capable of automatically knowing occurs in crack
The trend and fracture width in other crack.
In order to achieve the above objectives, the present invention adopts the following technical scheme that：
A kind of method of automatic identification body surface fracture strike and width, includes the following steps：
Step 1, gray processing, binaryzation are carried out to image and are filtered, then carried out Canny edge detections, split
The image of tape edge edge pixel.
Step 2, two curves of edge of crack are extracted based on the path finding algorithm in the anti-game of tower, and determine crack
Trend.
Step 3, two curves of the edge of crack obtained to step 2 are filtered, and calculate fracture width.
Further, the image binaryzation processing described in step 1 uses a kind of image overall binaryzation based on histogram
Method includes the following steps：
(1) gray value obtained after being handled according to image gray processing calculates histogram.
(2) if the histogram is a bimodal histogram, take the lowest point value between two peaks as threshold value；If institute
It is a bimodal histogram to state histogram not, then is smoothed to histogram data.
(3) step (2) is repeated, until the histogram becomes a bimodal histogram.If do not obtained yet after n times are repeated
A bimodal histogram is obtained, takes the weighted average of all gray values on histogram as threshold value, the value of N is determined by experiment.
Preferably, described to be to the method that histogram data is smoothed：To removing first point and most in histogram X-axis
The value of the histogram for left and right 3 points put each of outside latter point is averaged the value of the histogram as the point after smooth.The
The value that the value of the histogram of any and second point is averaged as first point of histogram after smooth.Point second from the bottom and last
The value of the histogram of any is averaged the value of the histogram as last point after smooth.
Further, the gray value through step 1 treated pixel only has 0 and 255 two kind, the pixel that gray value is 0
Point belongs to edge of crack point, and gray value is 255 to belong to non-edge of crack point.
Further, two curves of edge of crack are extracted described in step 2 and the method for determining fracture strike includes following
Step：
(1) it is progressively scanned by the sequence of ordinate from small to large, until scanning to there is 2 gray values on a same row
For 0 pixel until.
(2) it with the starting point that 2 pixels in step (1) are two curves, is calculated using the path finding in the anti-game of tower
Method calculates 2 curves of edge of crack.
(3) point for whether having repetition on 2 curves that judgment step (2) obtains, if there is the point repeated, then 2 curves
It is same curve, scanning ordinate value is added 1, step (1), (2), (3) are repeated, until finding 2 different curves.
If it fails, thening follow the steps (4).
(4) it is scanned by column by the sequence of abscissa from small to large, until scanning in same row to there is 2 gray values
For 0 pixel.
(5) it with the starting point that 2 pixels in step (4) are two curves, is calculated using the path finding in the anti-game of tower
Method calculates 2 curves of edge of crack.
(6) point for whether having repetition on 2 curves that judgment step (5) obtains, if there is the point repeated, then 2 curves
It is same curve, scanning abscissa value is added 1, step (4), (5), (6) are repeated, until finding 2 different curves.
The computational methods of 2 boundary curves are identical, and the method for calculating a curve is as follows：
The pixel come will be scanned first to be added in a search queue, is then iterated, every time from scouting team
A pixel is taken out in row, checks the gray value of 8 adjacent pixels around it, and the pixel that gray value is 0 is added
Into described search queue, until having searched for the last one pixel in queue.Preserve the gray value searched out in iterative process
For 0 pixel, and record a upper pixel and the distance between current pixel point and starting point for current pixel point.
After the completion of search, finds with starting point apart from maximum pixel, i.e. terminal, distance is calculated most by recursive algorithm
Path between big pixel and starting point, to obtain the one edge curve in crack.
The curve is from the trend that the direction of origin-to-destination is exactly crack.
Further, the distance between the current pixel point and starting point are equal on the path from starting point to current pixel point
Including pixel number, computational methods are that the distance between a upper pixel and starting point add 1.
Further, as follows to the method for every curve filtering described in step 3：
(1) two pixel of first and last of junction curve obtains a straight line, find out remaining each pixel to the straight line distance.
(2) if the maximum value of the distance acquired in step (1) is poor less than or equal to limiting, the first and last on the straight line is deleted
All pixels point between two pixels；If it is poor that the maximum value of the distance is more than limit, it is corresponding to retain the maximum distance
Pixel, and curve is divided into two parts using this pixel as boundary, step (1), (2) are repeated to this two parts curve, until not
The maximum value for occurring the distance again is less than or equal to the pixel of limit difference.The value of the limit difference is determined by experiment.
It is filtered the rear curve and splits into a plurality of line segment, find out every line segment on the 1st article of curve and the 2nd article respectively
The normal distance between every line segment on curve, the maximum value of the normal distance is fracture width.
Compared with prior art, the invention has the advantages that：
(1) present invention carries out the extraction of body surface edge of crack curve using image processing techniques, need not manually adjust
The trend in crack can the trend in automatic identification crack and the maximum width in crack as long as crack occurs in the picture.
(2) present invention carries out image procossing using the image overall binarization method based on histogram, can be to the maximum extent
The pixel for retaining edge of crack, improves measurement accuracy.
(3) the method for the invention two curves at first fracture edge before calculating fracture width are filtered,
Not only the boundary curve in crack can be made more smooth, but also reduce the quantity put on curve, improve the meter of fracture width
Calculate speed.The interpretation time of the method for the invention fracture width is less than the 1/10 of semi-automatic method of identification, is less than artificial range estimation
The 1/30 of method.
Description of the drawings
Fig. 1 be the present embodiments relate to the fracture strike of automatic identification body surface and width method flow diagram；
Fig. 2 is the flow chart of image processing method in Fig. 1；
Fig. 3 is the flow chart for calculating global binary-state threshold；
Fig. 4 is the flow chart for calculating a crack boundary curve.
Specific implementation mode
The present invention will be further described with reference to the accompanying drawings and examples.
A kind of method that the present invention proposes automatic identification body surface fracture strike and width, flow chart such as Fig. 1~4 institutes
Show, the described method comprises the following steps：
Step 1, gray processing, binaryzation are carried out to image and are filtered, then carried out Canny edge detections, split
The image of tape edge edge pixel.
Binary conversion treatment uses a kind of image overall binarization method based on histogram, includes the following steps：
Step 1.1, the gray value obtained after being handled according to image gray processing calculates histogram.
Step 1.2, if the histogram is a bimodal histogram, take the lowest point value between two peaks as threshold value；
If the histogram is not a bimodal histogram, histogram data is smoothed, method is as follows：
Flat is asked to the value of the histogram for left and right 3 points put each of in addition to first point and last point in histogram X-axis
The value of histogram of the mean value as the point after smooth.The value of the histogram of first point and second point is averaged flat as first point
The value of histogram after cunning.The value of the histogram of point and last point second from the bottom average as last point it is smooth after
The value of histogram.
Step 1.3, step 1.2 is repeated, until the histogram becomes a bimodal histogram.
If not obtaining a bimodal histogram after n times are repeated yet, the weighted average of all gray values on histogram is taken
Value is used as threshold value.The value of N is determined that the present embodiment N takes 1000 by experiment.
Gray value through treated pixel only has 0 and 255 two kind, the pixel that gray value is 0 to belong to crack
Marginal point, gray value are 255 to belong to non-edge of crack point.
Step 2, two curves of edge of crack are extracted based on the path finding algorithm in the anti-game of tower, and determine crack
Trend.
Step 2.1, it is progressively scanned by the sequence of ordinate from small to large, until scanning to there is 2 on a same row
Until the pixel that gray value is 0.
Step 2.2, it with the starting point that 2 pixels in step 2.1 are 2 curves, is sought using the path in the anti-game of tower
Algorithm is looked for, 2 curves of edge of crack are calculated.
The computational methods of 2 boundary curves are identical, and the method for calculating a curve is as follows：
The pixel come will be scanned first to be added in a search queue, is then iterated, every time from scouting team
A pixel is taken out in row, checks the gray value of 8 adjacent pixels around it, and the pixel that gray value is 0 is added
Into described search queue, until having searched for the last one pixel in queue.Preserve the gray value searched out in iterative process
For 0 pixel, and record current pixel point a upper pixel and the distance between current pixel point and starting point it is (current
The distance between pixel and starting point refer to the number for the pixel for including, computational methods in starting point to the path of current pixel point
It is 1) the distance between a upper pixel and starting point add.
After the completion of search, find with starting point apart from maximum pixel, before saved upper the one of each pixel
A pixel calculates the path between maximum pixel and starting point by recursive algorithm, then this paths is exactly
The one edge curve in crack.This curve from the direction of origin-to-destination (apart from maximum pixel) be exactly walking for crack
To.
Step 2.3, the point for whether having repetition on 2 curves that judgment step 2.2 obtains just is recognized if there is the point repeated
To be same curve, scanning ordinate value is added 1, step 2.1, step 2.2, step 2.3 are repeated, until finding different 2
Until curve.If it fails, thening follow the steps 2.4.
Step 2.4, it is scanned by column by the sequence of abscissa from small to large, until scanning in same row to there is 2
The pixel that gray value is 0.
Step 2.5, it with the starting point that 2 pixels in step 2.4 are two curves, is sought using the path in the anti-game of tower
Algorithm is looked for, calculates 2 curves of edge of crack, computational methods are the same as step 2.2.
Step 2.6, the point for whether having repetition on 2 curves that judgment step 2.5 obtains, if there is repeat point, then 2
Curve is same curve, and scanning abscissa value is added 1, repeats step 2.4, step 2.5, step 2.6, different until finding
Until 2 curves.If it fails, then function returns to failure.
Step 3, two curves of the edge of crack obtained to step 2 are filtered, and calculate fracture width.
Processing speed is improved in order to reduce calculation amount, 2 curves at first fracture edge carry out before calculating fracture width
The disposal of gentle filter is as follows to the method for every curve filtering：
Step 3.1, two pixel of first and last of junction curve obtains a straight line, find out remaining each pixel to the straight line away from
From.
Step 3.2, if the maximum value of the distance acquired in step 3.1 is poor less than or equal to limiting, the straight line is deleted
On two pixel of first and last between all pixels point；If the maximum value of the distance be more than limit it is poor, retain it is described maximum away from
Curve is divided into two parts from corresponding pixel, and using this pixel as boundary, to this two parts curve repeat step 3.1,
3.2, until the maximum value for the distance no longer occur is less than or equal to the pixel of limit difference.
The value of the limit difference is determined by experiment.In order to ensure it is smooth after curve shape and smooth previous cause, reduce and survey
Error is measured, limit difference takes 1 described in the present embodiment.After the completion of curve filtering, curve becomes to be made of a plurality of line segment, the width in crack
It is exactly the maximum value of normal direction distance between all line segments on the boundary curve of 2, crack.
Table 1 gives using the method for the invention and semi-automatic method of identification in the prior art and artificial ocular estimate, into
The Contrast on effect of row fracture strike and width identification.As shown in Table 1, the method for the invention is not only better than in terms of measurement accuracy
Semi-automatic method of identification and artificial ocular estimate, and other two methods are substantially better than in terms of processing speed, fracture width is sentenced
Read time is less than 1/10, the 1/30 of artificial ocular estimate of semi-automatic method of identification.In addition, the method for the invention being capable of automatic identification
Fracture strike, fracture trend do not require.
The comparison of table 1 the method for the invention and the prior art
| The method of the present invention | Semi-automatic method of identification | Artificial ocular estimate | |
| Measurement accuracy | ≤0.005mm | ≥0.005mm | ≥0.05mm |
| The fracture width interpretation time | ≤ 1 second | >=10 seconds | >=30 seconds |
| Whether automatic discrimination is supported | It supports | It supports | It does not support |
| Whether real-time interpretation | It supports | It supports part | It does not support |
| Whether fracture strike requires | No | Horizontal or vertical direction | Vertical direction |
| It can identify fracture strike | Energy | It cannot | It cannot |
The present invention is not limited to the above embodiment, made any to the above embodiment aobvious of those skilled in the art and
The improvement or change being clear to, all protection domain without departing from the design and appended claims of the present invention.
Claims (4)
1. a kind of method of automatic identification body surface fracture strike and width, it is characterised in that include the following steps：
Step 1, gray processing, binaryzation are carried out to image and are filtered, then carried out Canny edge detections, obtain crack side
The image of edge pixel；The image binaryzation processing uses a kind of image overall binarization method based on histogram, packet
Include following steps：
(1.1) gray value obtained after being handled according to image gray processing calculates histogram；
(1.2) if the histogram is a bimodal histogram, take the lowest point value between two peaks as threshold value；If described
Histogram is not a bimodal histogram, then is smoothed to histogram data；It is described that histogram data is carried out smoothly
The method of processing is：To in histogram X-axis each of in addition to first point and last point point and 2 points of its left and right composition 3 points
The value of histogram average the value of the histogram as the point after smooth；The value of the histogram of first point and second point asks flat
Value of the mean value as first point of histogram after smooth；The value of the histogram of point and last point second from the bottom is averaged conduct
The value of histogram after last point is smooth；
(1.3) step (1.2) is repeated, until the histogram becomes a bimodal histogram；If do not obtained yet after n times are repeated
A bimodal histogram is obtained, takes the weighted average of all gray values on histogram as threshold value；The value of N is determined by experiment；
Step 2, two curves of edge of crack are extracted, and determine the trend in crack；
Step 3, two curves of the edge of crack obtained to step 2 are filtered, and calculate fracture width；To every song
The method of line filtering is as follows：
(3.1) two pixel of first and last of junction curve obtains a straight line, find out remaining each pixel to the straight line distance；
(3.2) if the maximum value of the distance acquired in step (3.1) is poor less than or equal to limiting, the head on the straight line is deleted
All pixels point between last two pixels；If it is poor that the maximum value of the distance is more than limit, retains the maximum distance and correspond to
Pixel, and curve is divided into two parts using this pixel as boundary, step (3.1), (3.2) is repeated to this two parts curve,
Until the maximum value for the distance no longer occur is less than or equal to the pixel of limit difference；The value of the limit difference is determined by experiment；
It is filtered the rear curve and splits into a plurality of line segment, find out the every line segment and the 2nd article of curve on the 1st article of curve respectively
On every line segment between normal distance, the maximum value of the normal distance is fracture width.
2. the method for automatic identification body surface fracture strike according to claim 1 and width, which is characterized in that through step
The gray value of rapid 1 treated pixel only has 0 and 255 two kind, the pixel that gray value is 0 to belong to edge of crack point, gray scale
Value is 255 to belong to non-edge of crack point.
3. the method for automatic identification body surface fracture strike according to claim 1 and width, which is characterized in that step
2 it is described extraction edge of crack two curves and determine fracture strike method include the following steps：
(1) it is progressively scanned by the sequence of ordinate from small to large, until scanning is 0 to there is 2 gray values on a same row
Pixel until；
(2) with the starting point that 2 pixels in step (1) are two curves, the path finding algorithm in the anti-game of tower, meter are utilized
Calculate 2 curves of edge of crack；
(3) point for whether having repetition on 2 curves that judgment step (2) obtains, if there is the point repeated, then 2 curves are same
Scanning ordinate value is added 1, step (1), (2), (3) is repeated, until finding 2 different curves by one curve；If
Failure, thens follow the steps (4)；
(4) it is scanned by column by the sequence of abscissa from small to large, until scanning is 0 to there is 2 gray values in same row
Pixel；
(5) with the starting point that 2 pixels in step (4) are two curves, the path finding algorithm in the anti-game of tower, meter are utilized
Calculate 2 curves of edge of crack；
(6) point for whether having repetition on 2 curves that judgment step (5) obtains, if there is the point repeated, then 2 curves are same
Scanning abscissa value is added 1, step (4), (5), (6) is repeated, until finding 2 different curves by one curve；
The computational methods of 2 curves are identical, and the method for calculating a curve is as follows：
The pixel come will be scanned first to be added in a search queue, is then iterated, every time from search queue
A pixel is taken out, the gray value of 8 adjacent pixels around it is checked, gray value is added to institute for 0 pixel
It states in search queue, until having searched for the last one pixel in queue；It is 0 to preserve the gray value searched out in iterative process
Pixel, and record the upper pixel and the distance between current pixel point and starting point of current pixel point；
After the completion of search, finds with starting point apart from maximum pixel, i.e. terminal, calculated apart from maximum by recursive algorithm
Path between pixel and starting point, to obtain the one edge curve in crack；
The curve is from the trend that the direction of origin-to-destination is exactly crack.
4. the method for automatic identification body surface fracture strike according to claim 3 and width, which is characterized in that described
The distance between current pixel point and starting point are equal to the number of the pixel on the path from starting point to current pixel point included, meter
Calculation method is that the distance between a upper pixel and starting point add 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510661260.8A CN105389793B (en) | 2015-10-14 | 2015-10-14 | A kind of method of automatic identification body surface fracture strike and width |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510661260.8A CN105389793B (en) | 2015-10-14 | 2015-10-14 | A kind of method of automatic identification body surface fracture strike and width |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105389793A CN105389793A (en) | 2016-03-09 |
| CN105389793B true CN105389793B (en) | 2018-10-19 |
Family
ID=55422043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510661260.8A Active CN105389793B (en) | 2015-10-14 | 2015-10-14 | A kind of method of automatic identification body surface fracture strike and width |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389793B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919377B (en) * | 2018-07-28 | 2020-07-17 | 嘉兴麦瑞网络科技有限公司 | Geotechnical engineering surrounding rock crack detection system |
| CN109448012A (en) * | 2018-10-29 | 2019-03-08 | 山东浪潮云信息技术有限公司 | A kind of method for detecting image edge and device |
| CN110207592B (en) * | 2019-04-15 | 2021-11-09 | 深圳高速工程检测有限公司 | Building crack measuring method and device, computer equipment and storage medium |
| CN113689453A (en) * | 2021-08-24 | 2021-11-23 | 中石化石油工程技术服务有限公司 | Method, device and equipment for automatically identifying well logging image cracks and storage medium |
| CN114111602B (en) * | 2021-11-22 | 2023-07-25 | 招商局重庆交通科研设计院有限公司 | Bridge surface crack width calculation method based on image technology |
| CN117132602B (en) * | 2023-10-27 | 2024-01-02 | 湖南三昌泵业有限公司 | Visual inspection method for defects of centrifugal pump impeller |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| CN101413901A (en) * | 2008-12-01 | 2009-04-22 | 南京航空航天大学 | Surface fatigue crack detecting method based on CCD image characteristic |
-
2015
- 2015-10-14 CN CN201510661260.8A patent/CN105389793B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| CN101413901A (en) * | 2008-12-01 | 2009-04-22 | 南京航空航天大学 | Surface fatigue crack detecting method based on CCD image characteristic |
Non-Patent Citations (3)
| Title |
|---|
| 基于数字图像处理的表面裂缝宽度测量;叶贵如等;《公路交通科技》;20100228;第27卷(第2期);第75-78,84页 * |
| 基于直方图估计和形状分析的沥青路面裂缝识别算法;徐志刚等;《仪器仪表学报》;20101031;第31卷(第10期);第2260-2266页 * |
| 基于直方图分析和OTSU算法的文字图像二值化;吴丹等;《计算机与现代化》;20130731(第7期);第117-119,234页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105389793A (en) | 2016-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105389793B (en) | A kind of method of automatic identification body surface fracture strike and width | |
| CN107315012B (en) | Composite polycrystal-diamond end face collapses the intelligent detecting method at angle | |
| JP2009146407A (en) | Method and apparatus for segmenting object region | |
| CN104268853A (en) | Infrared image and visible image registering method | |
| CN108470343A (en) | A kind of improved method for detecting image edge | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN110263662B (en) | Human body contour key point and key part identification method based on grading | |
| CN111598897A (en) | Infrared image segmentation method based on Otsu and improved Bernsen | |
| CN109785348A (en) | Novel angular-point detection method and system based on the variation of image boundary approximate curvature | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| JP6338429B2 (en) | Subject detection apparatus, subject detection method, and program | |
| CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
| CN110717900A (en) | Pantograph abrasion detection method based on improved Canny edge detection algorithm | |
| CN110245600A (en) | Adaptively originate quick stroke width unmanned plane Approach for road detection | |
| CN111652844B (en) | X-ray defect detection method and system based on digital image region growing | |
| CN104036514A (en) | Circle detection method based on histogram peak value search | |
| CN109636822B (en) | Improved Canny self-adaptive edge extraction method based on newly-constructed membership function | |
| TWI383690B (en) | Method for image processing | |
| WO2019242388A1 (en) | Obstacle recognition method for library robot based on depth image | |
| CN113409334B (en) | Centroid-based structured light angle point detection method | |
| CN117853510A (en) | Canny edge detection method based on bilateral filtering and self-adaptive threshold | |
| CN107590501A (en) | A kind of improved Canny adaptive edge extracting methods based on Otsu | |
| CN114627147B (en) | Craniofacial landmark point automatic identification method based on multi-threshold image segmentation | |
| CN113658153B (en) | Contour data feature point detection method and device | |
| CN112651936B (en) | Steel plate surface defect image segmentation method and system based on image local entropy |
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 |