CN110211113A - A kind of detection algorithm and calculating equipment of groove exception - Google Patents
A kind of detection algorithm and calculating equipment of groove exception Download PDFInfo
- Publication number
- CN110211113A CN110211113A CN201910477151.9A CN201910477151A CN110211113A CN 110211113 A CN110211113 A CN 110211113A CN 201910477151 A CN201910477151 A CN 201910477151A CN 110211113 A CN110211113 A CN 110211113A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- exception
- groove
- template
- 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
- 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
- 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
- G06T2207/30152—Solder
Abstract
The invention discloses a kind of detection methods of groove exception, comprising steps of the image of the zirconium end surfaces groove under the irradiation of different light sources is acquired, as the first image and the second image;Based on the second image, the ring-data of zirconium end surfaces is determined;Based on ring-data, third image corresponding with the first image and the second image and the 4th image are generated;Using third image and the 4th image, construct for detecting at least one abnormal template image;Based at least one template image, detects the exception of groove and determine Exception Type.The present invention discloses corresponding calculating equipment together.
Description
Technical field
The present invention relates to the detection algorithms and calculating of measurement and detection technique field more particularly to a kind of groove exception to set
It is standby.
Background technique
Nuclear energy has been widely used in military, production and economic as a kind of cleaning, efficient, free of contamination clean energy resource
Equal fields.Since heavy water reactor has the features such as residual waste is few, capacity usage ratio is high and industrial application technical maturity is high,
It all has in worldwide nuclear power system and is widely applied.Therefore, primitive of the nuclear fuel rod as heavy water reactor, adds
The quality of work production is directly related to the normal operation of nuclear power station.In existing processing scheme, since zirconia material is in high temperature, height
It is still able to maintain good metallic character under radiation regimes, therefore generally nuclear fuel is wrapped using zirconium alloy pipe and is sold of one's property to prevent crack arrest
Object overflows.Filling nuclear fuel is needed inside zirconium pipe, and is filled the zirconium pipe completed and be also required to weld end plug at both ends to prevent internal combustion
Material is contacted with external environment.Before welding, at zirconium pipe both ends, vehicle goes out groove for welding, and the quality of groove quality, which affects, to be welded into
Power, the nuclear fuel rod of end plug failure welding will cause fission product leakage when participating in nuclear reaction, and then safety accident occurs,
So the detection for carrying out groove abnormal (or referred to as defect) with zirconium pipe to nuclear power is particularly important.
It, need to be using intelligent, high degree of automation equipment since nuclear fuel has certain radiativity, and enormous amount
The groove row of nuclear power zirconium pipe is detected with method, avoids excessive human intervention in detection process, to avoid to artificial at mistake
More radiation.Detection mode is artificial periodically sampling observation at present, and man-machine cooperation is needed to complete detection work in whole process, automation and
Intelligence degree is low.And the detection device and system for detecting groove exception published at present cannot perfect suitable zirconium pipe end
This special circumstances of face groove, and the demand of measurement accuracy and measurement efficiency cannot be combined, system designs often function
Single, measuring system is incomplete, and equipment price is expensive.
It is core in conclusion how effectively to solve efficient, accurate, the inexpensive abnormality detection of nuclear power zirconium pipe bevel
Electrical domain and measurement detection field urgent problem to be solved.
Summary of the invention
For this purpose, the present invention provides a kind of detection algorithm of groove exception and equipment is calculated, to try hard to solve or at least delay
Solution at least one existing problem above.
According to an aspect of the invention, there is provided a kind of detection method of groove exception, comprising steps of acquisition is in difference
The image of zirconium end surfaces groove under light source irradiation, as the first image and the second image;Based on the second image, zirconium pipe end is determined
The ring-data in face;Based on ring-data, third image corresponding with the first image and the second image and the 4th figure are generated
Picture;Using third image and the 4th image, construct for detecting at least one abnormal template image;Based at least one template
Image detects the exception of groove and determines Exception Type.
Optionally, it further comprises the steps of: according to the method for the present invention according to detected exception in third image or the 4th
The abnormal position in the first image or the second image is determined in position in image.
Optionally, in the method according to the invention, the first image is the zirconium end surfaces groove under single axis light irradiation
Image, the second image are the image of the zirconium end surfaces groove under the irradiation simultaneously of axis light and ring light.
Optionally, in the method according to the invention, ring-data include the central coordinate of circle of zirconium end surfaces, outer diameter length and
Interior electrical path length.
Optionally, in the method according to the invention, the step of being based on the second image, determining the ring-data of zirconium end surfaces
It include: that the bianry image about zirconium end surfaces is generated based on second image;Calculate the center of circle of annulus in bianry image
Coordinate and outer diameter length;According to outer diameter length, the interior electrical path length of the annulus in bianry image is determined.
Optionally, in the method according to the invention, it is based on ring-data, generates and distinguishes with the first image and the second image
The step of corresponding third image and four images includes: to determine the size of third image and the 4th image based on ring-data;
Using the pixel value of adjacent pixel of the respective pixel in the first image or the second image, determine the pixel in third figure respectively
Pixel value in picture or the 4th image.
Optionally, in the method according to the invention, it using third image and the 4th image, constructs abnormal for detecting
The step of at least one template image includes: based on the 4th the first template image of picture construction and the second template image;Based on
Three picture construction third template images.
Optionally, in the method according to the invention, be based at least one template image, detect the exception of groove and really
The step of determining Exception Type includes: the error image for calculating the first template image and the 4th image;It determines in error image extremely
A few connected region;When detecting that at least one connected region meets the first preset condition, detected connection is determined
It is tube wall curvature abnormalities that region corresponding position, which has abnormal and Exception Type,.
Optionally, in the method according to the invention, be based at least one template image, detect the exception of groove and really
The step of determining Exception Type includes: the error image for calculating the second template image and the 4th image;It determines in error image extremely
A few connected region;When detecting that at least one connected region meets the second preset condition, the connected region detected is determined
It is abnormal at groove chamfering that domain corresponding position, which has abnormal and Exception Type,.
Optionally, in the method according to the invention, it is based at least one template, detects the exception and exception class of groove
The step of type includes: to construct the first array and the second array based on third template image;Pass through in the first array of statistics at least two
A adjacent element is 0 element, generates at least one First ray, and big in the length for detecting at least one First ray
When breaking length threshold value, determining that First ray corresponding position has abnormal and Exception Type is that groove tip fracture is abnormal;Meter
The difference for calculating corresponding element in the first array and the second array, obtains difference array;Pass through in statistics difference array at least two
Adjacent element is all larger than 0 element, generates at least one second sequence, and big in the length for detecting at least one the second sequence
When protruding limitation of length value and the maximum value of the corresponding element of the second sequence in difference array is greater than prominent threshold value, really
It is that groove top width is abnormal that fixed second sequence corresponding position, which has abnormal and Exception Type,.
Optionally, in the method according to the invention, it is based on third template image, constructs the first array and the second array
Step includes: to carry out binary conversion treatment to third template image, obtains the third template image of binaryzation;By traversing binaryzation
Third template image in each column pixel, count each column pixel in characterize bright band pixel number, come generate characterization bright band it is wide
First array of degree;By calculating the average value of each element and its at least one adjacent element in the first array, it is bright to generate characterization
Second array of bandwidth.
Optionally, it further comprises the steps of: according to the method for the present invention and determines detected exception in third image or the 4th
Enclosure rectangle in image;Based on position mapping relations, the exception is calculated according to the position coordinates of enclosure rectangle in the first figure
Position in picture or the second image.
According to another aspect of the present invention, a kind of calculating equipment is provided, comprising: at least one processor;And storage
There is the memory of program instruction, wherein program instruction is configured as being suitable for being executed by least one processor, and program instruction includes
For executing the instruction of method as described above.
According to another aspect of the present invention, a kind of readable storage medium storing program for executing for being stored with program instruction is provided, program is worked as
When instruction is read and executed by calculating equipment, so that the calculating equipment executes method as described above.
According to the solution of the present invention, acquire the lower zirconium end surfaces groove image of different light sources irradiation, and to the first image with
Second image is detected respectively, overcome single light source single imaging can only detection part groove exception defect.Meanwhile it will
First image and the second image spread detect slope at third image and the 4th image, then based on third image and the 4th image
Mouth is abnormal, effectively improves area-of-interest accounting, reduces operand.
Furthermore, it is contemplated that error influences when due to retaining wall on slope, each groove face pattern is not quite similar, in this programme
In, constructed template image is not fixed, based on current unfolded image (that is, third image and the 4th image),
At least one template image is constructed in the way of being averaged, and as the standard picture of groove, can adaptively be restored every
The state without exception of a groove face.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
To the accomplishment of the foregoing and related purposes, certain illustrative sides are described herein in conjunction with following description and drawings
Face, these aspects indicate the various modes that can practice principles disclosed herein, and all aspects and its equivalent aspect
It is intended to fall in the range of theme claimed.Read following detailed description in conjunction with the accompanying drawings, the disclosure it is above-mentioned
And other purposes, feature and advantage will be apparent.Throughout the disclosure, identical appended drawing reference generally refers to identical
Component or element.
Fig. 1 shows the schematic diagram according to an embodiment of the invention for calculating equipment 100;
Fig. 2 shows the flow diagrams of the detection method 200 of groove exception according to some embodiments of the invention;
Fig. 3 shows the schematic diagram of zirconium pipe and its end face groove according to an embodiment of the present invention;
Fig. 4 A and Fig. 4 B respectively illustrate the schematic diagram of the first image and the second image according to an embodiment of the present invention;
Fig. 5 A and Fig. 5 B respectively illustrate the schematic diagram of third image and the 4th image according to an embodiment of the present invention;
Fig. 6 A shows the schematic diagram of the first template image according to an embodiment of the invention;
Fig. 6 B shows the schematic diagram of the second template image according to an embodiment of the invention;
Fig. 6 C shows the schematic diagram of third template image according to an embodiment of the invention;
Fig. 7 A shows the schematic diagram of the 4th image of another embodiment according to the present invention;
Fig. 7 B shows the schematic diagram of the 4th image of another embodiment according to the present invention;
Fig. 7 C shows the schematic diagram of the third image of another embodiment according to the present invention;And
Fig. 8 A and Fig. 8 B are respectively illustrated according to an embodiment of the invention to be shown in the first image and the second image
The abnormal schematic diagram detected.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
The detection scheme of groove exception according to the present invention, it is contemplated that the radiativity of nuclear fuel and the particularity of zirconium pipe bevel
Etc. factors, image about zirconium end surfaces groove is acquired, in this manner it is possible to detect acquired image by image processing method
Abnormal conditions, and then judge zirconium pipe bevel that the image is characterized with the presence or absence of abnormal.
In realization according to the present invention, using the image of image capture device acquisition zirconium pipe bevel, calculating equipment is utilized
To realize the detection method 200 of groove exception.An example for calculating equipment is shown first below.
Fig. 1 is the schematic block diagram of Example Computing Device 100.
As shown in Figure 1, calculating equipment 100 in basic configuration 102 and typically comprising system storage 106 and one
Or multiple processors 104.Memory bus 108 can be used for the communication between processor 104 and system storage 106.
Depending on desired configuration, processor 104 can be any kind of processing, including but not limited to: microprocessor
(μ P), microcontroller (μ C), digital information processor (DSP) or any combination of them.Processor 104 may include such as
The cache of one or more rank of on-chip cache 110 and second level cache 112 etc, processor core
114 and register 116.Exemplary processor core 114 may include arithmetic and logical unit (ALU), floating-point unit (FPU),
Digital signal processing core (DSP core) or any combination of them.Exemplary Memory Controller 118 can be with processor
104 are used together, or in some implementations, and Memory Controller 118 can be an interior section of processor 104.
Depending on desired configuration, system storage 106 can be any type of memory, including but not limited to: easily
The property lost memory (RAM), nonvolatile memory (ROM, flash memory etc.) or any combination of them.System storage
Device 106 may include operating system 120, one or more is using 122 and program data 124.In some embodiments,
It may be arranged to be executed instruction by one or more processors 104 using program data 124 on an operating system using 122.
Calculating equipment 100 can also include facilitating from various interface equipments (for example, output equipment 142, Peripheral Interface
144 and communication equipment 146) to basic configuration 102 via the communication of bus/interface controller 130 interface bus 140.Example
Output equipment 142 include graphics processing unit 148 and audio treatment unit 150.They can be configured as facilitate via
One or more port A/V 152 is communicated with the various external equipments of such as display or loudspeaker etc.Outside example
If interface 144 may include serial interface controller 154 and parallel interface controller 156, they, which can be configured as, facilitates
Via one or more port I/O 158 and such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment) or the external equipment of other peripheral hardwares (such as printer, scanner etc.) etc communicated.Exemplary communication is set
Standby 146 may include network controller 160, can be arranged to convenient for via one or more communication port 164 and one
A or multiple other calculate communication of the equipment 162 by network communication link.
Network communication link can be an example of communication media.Communication media can be usually presented as in such as carrier wave
Or computer readable instructions, data structure, program module in the modulated data signal of other transmission mechanisms etc, and can
To include any information delivery media." modulated data signal " can be such signal, one in its data set or
It is multiple or it change can the mode of encoded information in the signal carry out.As unrestricted example, communication media can
To include the wired medium of such as cable network or private line network etc, and it is such as sound, radio frequency (RF), microwave, infrared
(IR) the various wireless mediums or including other wireless mediums.Term computer-readable medium used herein may include depositing
Both storage media and communication media.
Calculate equipment 100 can be implemented as include desktop computer and notebook computer configuration personal computer.When
So, calculating equipment 100 also can be implemented as a part of portable (or mobile) electronic equipment of small size, these electronic equipments can
To be such as cellular phone, digital camera, personal digital assistant (PDA), personal media player device, wireless network browsing
Equipment, personal helmet, application specific equipment or may include any of the above function mixing apparatus.It even can be by
It is embodied as server, such as file server, database server, apps server and WEB server.Reality of the invention
Example is applied to this with no restrictions.
In an embodiment according to the present invention, equipment 100 is calculated to be configured as executing groove exception according to the present invention
Detection method 200.Wherein, the detection method in the application 122 of equipment 100 comprising executing groove exception according to the present invention is calculated
200 a plurality of program instruction.
Fig. 2 shows the flow diagrams of the detection method 200 of groove exception according to some embodiments of the invention.Such as figure
Shown in 2, method 200 starts from step S210.
In step S210, acquire the image of the zirconium end surfaces groove under the irradiation of different light sources, as the first image and
Second image.
The schematic diagram that Fig. 3 shows zirconium pipe and its end face groove according to an embodiment of the present invention (will use rectangle frame in left figure
Amplification display such as right figure at the zirconium end surfaces groove irised out).Zirconium end surfaces are in circular ring shape, annulus central filler nuclear fuel.It is logical
The analysis and research to zirconium end surfaces groove pattern are crossed, it has been found that illuminating groove difference table respectively by using different light sources
Face can be used to find the exception on different location (such as groove top 301, outer chamfer 302, inner chamfer 303).Therefore in method
In 200, the image of the zirconium end surfaces groove under different light source irradiations is acquired, the zirconium pipe is judged by the exception in detection image
End face groove is with the presence or absence of abnormal.
According to a kind of embodiment, the image for acquiring the zirconium end surfaces groove under single axis light vertical irradiation, as first
Image.Since in the actual production process, the polishing mode of artificial detection exception is single axis light, to illuminate groove top zone
Domain, thus according to the first image acquired in this kind of polishing mode, more meet the habit and cognition of reviewer, it is abnormal convenient for definition
Shape characteristic.According to another embodiment, axis light (for example, vertical irradiation) and ring light are acquired (for example, with zirconium pipe end
Face is incident at an angle) irradiate simultaneously under zirconium end surfaces groove image, as the second image.Applicant is excessive in test
After kind light source, determine that the light got using the polishing mode of axis light and ring light is relatively uniform and can clearly be irradiated to slope
Mouthful, therefore the second acquired image is more suitable for detecting the edge defect of groove;In addition, integrating light source compared to other balls, coaxially
Light and ring light are easy to operate convenient for setting.
Fig. 4 A and Fig. 4 B respectively illustrate the schematic diagram of the first image and the second image according to an embodiment of the present invention.It needs
Illustrate, here in shown method 200, the first image and the second image are grayscale image, below to the first image
With the processing of the second image, it is also based on the processing (following pixel value, can be understood as gray value) of gray level image.When
So, it is noted that the embodiment of the present invention is not limited to this, also the color image of available zirconium end surfaces groove and to its coloured silk
Color pixel value is handled, and the embodiment of the present invention does not do excessive limitation to this.
It can be seen that, in collected first image and the second image, zirconium end surfaces are formed from Fig. 4 A and Fig. 4 B
One annulus.Wherein, the annular shape of the second image is more obvious.In embodiment according to the present invention, the first image is used
To detect groove top end, (exception of 301) as shown in Figure 3, the second image are used to detect at groove chamfering (as shown in Figure 3
302 and exception 303).
Then in step S220, it is based on the second image, determines the ring-data of zirconium end surfaces.
In some embodiments of the invention, ring-data includes the central coordinate of circle, outer diameter length and internal diameter of zirconium end surfaces
Length.
According to a kind of embodiment, step S220 can be carried out according to following three step.
The first step is based on the second image, generates the bianry image about zirconium end surfaces.In one embodiment, first to
Two images carry out noise reduction process, then from being extracted in the image after noise reduction process about zirconium end surfaces (that is, outside characterization annulus
Profile) bianry image.
Second step calculates the central coordinate of circle and outer diameter length of annulus in bianry image.
In the bianry image, the outer profile of annulus can be regarded as a standard round, calculate the center of gravity of the bianry image
As the center of circle of annulus, central coordinate of circle is denoted as (Xc,Yc), central coordinate of circle (X is calculated by following formulac,Yc):
In formula, piIndicate the pixel value of ith pixel, xiIndicate the x coordinate of ith pixel, yiIndicate the y of ith pixel
Coordinate.
In addition, calculating the outer diameter length of annulus, it is denoted as Router, the outer path length of annulus in bianry image is calculated by following formula
Spend Router:
In formula, p(i,j)Indicates coordinate is the pixel value of the pixel of (i, j), which shares m row n column.
Third step, according to outer diameter length Router, determine the interior electrical path length of the annulus in bianry image.According to the present invention
In one embodiment, the interior electrical path length and outer diameter length (that is, length in kind) of the zirconium end surfaces can be obtained in advance, in this way,
After calculating the outer diameter length in bianry image, so that it may estimated in bianry image according to length in kind, annulus it is interior
Electrical path length is shown below:
In formula, riAnd roRespectively indicate the actual internal diameter of zirconium end surfaces and outer diameter length, RinnerAnd RouterIt respectively indicates
The internal diameter and outer diameter length of annulus in bianry image.
In conjunction with Fig. 4 A and Fig. 4 B it can be concluded that, in the first image and the second image, circle ring area (i.e. area-of-interest)
Sub-fraction is accounted for, only to improve area-of-interest accounting, embodiment according to the present invention, in a subsequent step, by first
Annulus in image and the second image is launched into shape of rectangular ribbon, forms new unfolded image.It can not only increase so interested
Region accounting can also remove influence of the annulus center nuclear fuel to detection, while reducing operand, improve detection effect
Rate.
In step S230, it is based on ring-data, generates third image corresponding with the first image and the second image
With the 4th image, third image and the 4th image are exactly the first image and the corresponding unfolded image of the second image.
According to an embodiment of the invention, firstly, determining the size of third image and the 4th image based on ring-data.One
As, the size of unfolded image (i.e. third image and the 4th image) determines as follows: with the first image (or the second figure
As in) width wide, with the first image (or in second image) annulus of the Zhou Changwei third image (or the 4th image) of annulus
(i.e. outer diameter length subtracts interior electrical path length) is the height of third image (or the 4th image).Then, by the first image or the second image
Circle ring area in each pixel pixel value, the corresponding pixel being assigned in third image or the 4th image.In one embodiment,
Using the pixel value of adjacent pixel of the respective pixel in the first image or the second image, determine the pixel in third figure respectively
Pixel value in picture or the 4th image.
Fig. 5 A and Fig. 5 B respectively illustrate the schematic diagram of third image and the 4th image according to an embodiment of the present invention.It needs
Illustrate, length is limited, and Fig. 5 A and Fig. 5 B shown herein have only intercepted the part of third image and the 4th image.Wherein,
It is the image in Fig. 4 A after annulus expansion that Fig. 5 A and Fig. 5 B, which respectively correspond Fig. 4 A and Fig. 4 B, Fig. 5 A, and Fig. 5 B is the annulus in Fig. 4 B
Image after expansion.
Further, in conjunction with foregoing description, first image of generation according to an embodiment of the invention described below is corresponding
Unfolded image, i.e. the calculating process of third image.It should be noted that generating the corresponding unfolded image of the second image --- the
The calculating process of four images is identical as the calculating process of third image is generated, and reference is described below, and those skilled in the art can give birth to
At corresponding 4th image, length is limited, and details are not described herein again.
(1) according to the ring-data of zirconium end surfaces, the pixel columns n of third image is calculatedl=2 π Router, and, it is right
Answer the angle parameter theta of each column pixelk=2k π/(nl- 1), k ∈ [0, nl), wherein RouterIndicate outer diameter length.
(2) according to central coordinate of circle (Xc,Yc) and zirconium end surfaces annulus internal-and external diameter (Rinner,Router), calculate third
The corresponding position in the first image of kth column the i-th row pixel in image, that is, xki=Xc+i*cosθk, yki=Yc+i*sinθk,
In, k ∈ [0, nl), i ∈ [Rinner,Router]。
(3) pixel value of each pixel in third image is calculated using the method for bilinear interpolation, such as by identified
Pixel (xki,yki) and its 4 adjacent up and down pixels pixel value, it is corresponding in third image that interpolation goes out the pixel
Pixel value.
According to one embodiment of present invention, the processing through step S230, by picture size be 2736*2736, sense
The original image (that is, the first image/second image) of interest region only accounting 6.5%, being converted into picture size is about 100*
7000, area-of-interest accounting reaches 70% unfolded image (that is, third image/the 4th image), it can be seen that, through step
The processing of S230, so that method 200 focuses more on area-of-interest and reduces computational complexity.
Then in step S240, using third image and the 4th image, construct for detecting at least one abnormal mould
Plate image.
For the exception at zirconium end surfaces groove, three classes can be classified as according to position difference, the first kind is that nozzle is non-round,
Groove is in production or transportational process extrusion;Second class is groove top exception, is divided into bright band fracture and bright band prominent two
Kind;Third class is that groove chamfering is abnormal.Embodiment according to the present invention constructs template according to the exception of different location respectively
Image is detected.
In an embodiment according to the present invention, the 4th the first template image of picture construction and the second template image, base are based on
In third picture construction third template image.Wherein, the first template image is used to detect the tube wall curvature abnormalities of zirconium pipe, the second mould
Plate image is used to detect the exception at the groove chamfering of zirconium pipe, and third template image is used to detect the different of the groove top of zirconium pipe
Often.
The process of building above three template image described separately below.
1) it is based on the 4th the first template image of picture construction
Under normal circumstances, the form after annulus expansion is to highlight straight band, the item when tube wall is bent, after expansion
Band has significantly large area bending, that is to say, that and it is brighter than its two side areas (that is, gray value is big) that there are abnormal positions, therefore,
In an embodiment according to the present invention, the first template image is constructed based on the characteristic, to restore no curved band.
Such as Fig. 6 A, the schematic diagram of the first template image according to an embodiment of the invention is shown.It is detailed below
Generate the calculating process of the first template image.
Firstly, the first template image of building and the 4th image same size.Then, for each column picture in the 4th image
Each pixel in element, the mean value for calculating this pixel and the pixel value of at least one adjacent pixel (in one embodiment, take this
The pixel value of m pixel before and after pixel, to calculate mean value, the value range of m for example can be 300-1000, without being limited thereto), then
Determine the pixel value of this pixel with counted mean value difference.Next, according to the size of difference, to determine third template
The pixel value of each pixel in image: when difference be more than the first preset value (optionally, the first preset value is set as 50, but not limited to this)
When, which is assigned to the pixel of corresponding position in the first template image;When difference is no more than the first preset value, by the 4th figure
The pixel value of corresponding position is assigned to the pixel of corresponding position in the first template image as in.
In other words, the process of the pixel value of each pixel can be with following formula come table in above-mentioned the first template image of calculating
Show:
In above formula, h21(k, y) indicates the pixel value of a pixel in the first template image, g2(k, y) is indicated in the 4th image
The pixel value of one pixel,Indicate the pixel mean value of a pixel and its at least one adjacent pixel in the 4th image, T1 table
Show the first preset value.
2) it is based on the 4th the second template image of picture construction
Under normal circumstances, the groove under axis light and ring light irradiation should show uniform highlighted state, work as appearance
When abnormal, since exception light-inletting quantity is few, it may appear that obvious blackspot, therefore, in an embodiment according to the present invention, it is based on the characteristic
The second template image is constructed, to restore the band of not blackspot.
Such as Fig. 6 B, the schematic diagram of the second template image according to an embodiment of the invention is shown.It is detailed below
Generate the calculating process of the second template image.
Firstly, the second template image of building and the 4th image same size.Then, for each column picture in the 4th image
Each pixel in element, the mean value for first calculating the pixel and the pixel value of at least one adjacent pixel (in one embodiment, take this
The pixel value of m pixel before and after pixel, to calculate mean value, the value range of m for example can be 300-1000, without being limited thereto), then
Determine institute counted mean value and this pixel pixel value difference.Next, according to the size of difference, to determine the second template
The pixel value of each pixel in image: when difference be more than the second preset value (optionally, the second preset value is set as 20, but not limited to this)
When, which is assigned to the pixel of corresponding position in the second template image;When difference is no more than the second preset value, by the 4th figure
The pixel value of corresponding position is assigned to the pixel of corresponding position in the second template image as in.
In other words, the process of the pixel value of each pixel can be with following formula come table in above-mentioned the second template image of calculating
Show:
In above formula, h22(k, y) indicates the pixel value of a pixel in the second template image, g2(k, y) is indicated in the 4th image
The pixel value of one pixel,Indicate the pixel mean value of a pixel and its at least one adjacent pixel in the 4th image, T2 table
Show the second preset value.
3) it is based on third picture construction third template image
Under normal circumstances, under the irradiation of single axis light, groove top shows as one perpendicular to light source in third image
Thin and tall bright wisp band (hereinafter referred to as bright band) is not illuminated at groove chamfering, but lathe tool line at individual chamferings and defect also can be by
Single axis light illuminates, that is to say, that and it is brighter than its two side areas (that is, gray value is big) that there are abnormal positions, therefore, according to this hair
In bright embodiment, third template image is constructed based on the characteristic.
In addition, Lai Shengcheng third template image can be interfered to groove top if directly carrying out binary conversion treatment to third image
Hold abnormal judgement.Therefore in other embodiments according to the present invention, based on third picture construction third template image it
Before, first third image can be pre-processed, to remove image interference.Then, the third image after recycling removal interference, structure
Build out third template image.
Such as Fig. 6 C, the schematic diagram of third template image according to an embodiment of the invention is shown.It is detailed below
Generate the calculating process of third template image.
Firstly, the third template image of building and third image same size.Then, for column picture each in third image
Each pixel in element, the mean value for first calculating this pixel and the pixel value of at least one adjacent pixel (in one embodiment, take
The pixel value of m pixel before and after the pixel, to calculate mean value, the value range of m for example can be 300-1000, without being limited thereto),
Determine again the pixel value with counted mean value difference.Next, according to the size of difference, to determine in third template image
The pixel value of each pixel: when difference is more than third preset value (in one embodiment, third preset value takes 20, without being limited thereto)
When, by counted mean value be assigned to the pixel of corresponding position in third template image;It, will when difference is no more than third preset value
The pixel value of corresponding position is assigned to the pixel of corresponding position in third template image in third image.
In other words, the process of the pixel value of each pixel can be with following formula come table in above-mentioned calculating third template image
Show:
In above formula, h11(k, y) indicates the pixel value of a pixel in third template image, g1(k, y) is indicated in third image
The pixel value of one pixel,Indicate the pixel mean value of a pixel and its at least one adjacent pixel in third image, T3 table
Show third preset value.
Then in step s 250, it is based at least one template image, detect the exception of groove and determines Exception Type.
As it was noted above, different template images is used to detect the exception at different location.Therefore in reality according to the present invention
It applies in example, to different template images, exception is detected using different methods.It is described separately below from three kinds of template images
Detect abnormal process.
1) it is based on the first template image, detection groove is abnormal
Fig. 7 A shows the schematic diagram of the 4th image (there are exceptions) of another embodiment according to the present invention.By Fig. 7 A with
Fig. 6 A is corresponding, and paired observation is arrived: there is exception in the a1-a2 section of Fig. 7 A, be rendered as the abnormal bending of tube wall.
The process of following further clarification measurement groove exception.
Firstly, calculating the error image of the first template image and the 4th image.In one embodiment, the first template is calculated
The difference of the pixel value of respective pixel in image and the 4th image, utilizes difference setting value image.Secondly, determining the differential chart
At least one connected region as in.In image procossing, connected region generally refers to have same pixel value and position in image
Image-region composed by adjacent pixel is set, content known to those skilled in the art is belonged to, no longer does excessive explanation herein.
Then, identified connected region is detected, when detecting that at least one connected region meets the first preset condition, really
It is tube wall curvature abnormalities that fixed detected connected region corresponding position, which has abnormal and Exception Type,.
In some embodiments in accordance with the present invention, when the gray scale of pixel in the size of connected region and connected region
When value is met certain condition, it is abnormal to determine that the corresponding position of the connected region exists.Optionally, the first preset condition defines
Are as follows: connected region length (optionally, when connected region it is in irregular shape when, water intaking square upwards a longest a line come
Count connected region length) be greater than the first length threshold, connected region width (optionally, when the shape of connected region not
When regular, longest a line in vertical direction is taken to count the width of connected region) it is greater than the first width threshold value, connected region
Maximum gradation value be greater than the first gray threshold, the average gray of connected region is greater than the second gray threshold and (is connected to about determining
The method of maximum gradation value and average gray value in region, belongs to content known to those skilled in the art, details are not described herein again).
Wherein, the first length threshold and the first width threshold value represent the abnormal length and width threshold value detected, can be according to reality
The border condition of production and testing conditions determine, for example, can increase corresponding threshold value when testing conditions are loose, work as detector bar
When part is harsh, corresponding threshold value can reduce.Similarly, the first gray threshold and the second gray threshold can also be according to actual lifes
Situation and testing conditions are produced to determine, for example, can reduce corresponding threshold value when testing conditions are loose, when testing conditions are tight
When severe, corresponding threshold value can be increased.
2) it is based on the second template image, detection groove is abnormal
Fig. 7 B shows the schematic diagram of the 4th image (there are exceptions) of another embodiment according to the present invention.By Fig. 7 B with
Fig. 6 B is corresponding, and there is obvious blackspot in the part b1 of paired observation to: Fig. 7 B, illustrate at the groove chamfering of corresponding position there may be
It is abnormal.
The process of following further clarification measurement groove chamfering exception.
Firstly, calculating the error image of the second template image and the 4th image.With reference to the foregoing, the second Prototype drawing is calculated
As the difference with the pixel value of respective pixel in the 4th image, difference setting value image is utilized.Secondly, determining the error image
In at least one connected region.Determination about connected region can refer to the description of the 1) part above, be not repeated herein.
Then, identified connected region is detected, when detecting that at least one connected region meets the second preset condition, really
It is abnormal at groove chamfering that the connected region corresponding position that regular inspection is measured, which has abnormal and Exception Type,.
In some embodiments in accordance with the present invention, when the gray scale of pixel in the size of connected region and connected region
When value is met certain condition, it is abnormal to determine that the corresponding position of the connected region exists.Optionally, the second preset condition defines
Are as follows: the length of connected region is greater than the second length threshold, and the width of connected region is greater than the second width threshold value, the length of connected region
Width is less than default Aspect Ratio than (that is, ratio of length and width), and the maximum gradation value of connected region is greater than third gray scale threshold
The average gray of value, connected region is greater than the 4th gray threshold.About the mode for the relevant parameter for determining connected region, above
Through being explained, details are not described herein again.
Wherein, the second length threshold and the second width threshold value just represent the abnormal length and width threshold value detected, can basis
Practical condition and testing conditions determine, for example, can increase corresponding threshold value when testing conditions are loose, work as detection
When condition is harsh, corresponding threshold value can reduce.Similarly, third gray threshold and the 4th gray threshold can also be according to actual
The condition of production and testing conditions determine, for example, can reduce corresponding threshold value when testing conditions are loose, working as testing conditions
When harsh, corresponding threshold value can be increased.Furthermore, it is contemplated that generally there is no the exceptions of elongated strip, therefore default length is set
Wide ratio deletes too long error detection region, according to one embodiment of present invention, presets the value of Aspect Ratio about
It is 10.
3) it is based on third template image, detection groove is abnormal
Fig. 7 C shows the schematic diagram of the third image (there are exceptions) of another embodiment according to the present invention.By Fig. 7 C with
Fig. 6 C is corresponding, paired observation to bright band width and gray value shown in Fig. 7 C, and different shown in Fig. 6 C.
Below in four steps, it further illustrates and is based on third template image, to measure the process of groove top exception.
The first step is based on third template image, constructs the first array and the second array.
Embodiment according to the present invention first carries out binary conversion treatment to third template image, obtains the third of binaryzation
Template image.Optionally, the pixel value in third template image is classified as 0 and 1, in this way, the pixel that pixel value is 0 represents third
Bright band region in template image, the pixel that pixel value is 1 represent the region that two sides are darker in third template image.
Then, each column pixel in the third template image by traversing the binaryzation, counts table in each column pixel
The pixel number of bright band is levied, to generate the first array of characterization bright band width.Optionally, each column pixel is traversed, is therefrom found out bright
The starting point coordinate (being denoted as start) and terminating point coordinate (being denoted as end) of band are (for example, define in each column pixel, first picture
The pixel that plain value is 0 is starting point, and the pixel that the last one pixel value is 0 is terminating point), then the bright band width of each column is len
=end-start+1.It is of course also possible to directly count in each column pixel, the number of pixels that pixel value is 0, as the column
Bright band width does not do excessive limitation herein.In one embodiment, the first array generated is denoted as Len={ len1,
len2,...,lenn, wherein the pixel columns of n expression third template image.
Next, generating characterization by the average value for calculating each element and its at least one adjacent element in the first array
Second array of bright band width.Optionally, the element value of i-th of element and its m adjacent element in front and back in the first array is calculated
Mean value, be denoted as:
So, the second array generated is just denoted as W={ w1,w2,...,wn, wherein n indicates third template image
Pixel columns.
Second step is 0 element by least two adjacent elements in the first array Len of statistics, generates at least one
First ray.Assuming that the first array is Len={ 3,1,0,0,1,0,0,0,0,1,2,0 }, then it is corresponding to generate 2 First rays,
It is denoted as respectively: zero1={ 0,0 }, zero2={ 0,0,0,0 }.Then, the length for counting each First ray generated, when
When detecting that the length of at least one First ray is greater than breaking length threshold value, determine that there are different for the First ray corresponding position
Often and Exception Type is that groove tip fracture is abnormal.Optionally, breaking length threshold value is determined generally according to production requirement, is connect
Upper example, if setting breaking length threshold value is 3, zero2Length be more than breaking length threshold value, can determine that zero2Corresponding pixel
There are groove tip fracture exceptions for column.
Third step calculates the difference of corresponding element in the first array Len and the second array W, obtains difference array, difference number
Each of group element is denoted as δi=leni-wi。
Whether 4th step, being detected at bright band based on difference array has prominent exception.Specifically, pass through statistics difference array
In at least two adjacent elements be all larger than 0 element, generate at least one second sequence.Assuming that difference array be δ=1,1,0,
0,1,0,0,1,2,3,0 }, then corresponding to generate 2 the second sequences, it is denoted as respectively: out1={ 1,1 }, out2={ 1,2,3 }.And
Afterwards, the length and its corresponding maximum value in difference array for counting each second sequence generated, when detecting at least one
The length of a second sequence is greater than prominent limitation of length value and the maximum value of the corresponding element of the second sequence in difference array
When greater than prominent threshold value, determining that the second sequence corresponding position has abnormal and Exception Type is that groove top width is abnormal.
Optionally, breaking length threshold value is determined generally according to production requirement, connects example, prominent if it is 1 that prominent limitation of length value, which is arranged,
Threshold value is 2, then can determine that out2There are groove top width exceptions for corresponding pixel column.
So far, it just detected the groove exception of zirconium pipe and Exception Type be accordingly determined.In conclusion according to the present invention
Method 200, by the first image and the second image under different radiation sources collected simultaneously and accordingly generate more
A template image can accurately detect the multiple defect at nuclear power zirconium pipe bevel.
Another embodiment according to the present invention, due to the abnormal process of detection be unfolded image (that is, third image and
4th image) on carry out, the abnormal position in order to will test reverts to original image (that is, the first image and second
Image) in, in the exception that detects groove and after determining Exception Type, further comprise the steps of: according to detected abnormal the
Position of the exception in the first image or the second image is accordingly determined in position in three images or the 4th image.
According to a kind of embodiment, for each exception detected, it is first determined detected is abnormal in third image
Or the 4th enclosure rectangle in image.
Specifically, for each exception detected, starting column of the exception in third image or the 4th image are determined
colks, end column colke, initial row rowks, termination row rowke, using this 4 parameters as determine enclosure rectangle parameter, according to
This 4 parameters can determine each abnormal enclosure rectangle respectively.
Then, position mapping relations are based on, calculated according to the position coordinates of enclosure rectangle the exception in the first image or
Position in second image.
For considering for aesthetics, detected exception is irised out using ellipse in the first image and the second image.
Process (the parameter R being related in following calculating process of determining oval each parameter described belowinnerAnd nlIt is illustrated respectively in second
In image, the internal diameter of zirconium end surfaces and the pixel columns of third image or the 4th image, through abovementioned steps S220 and step S230
It calculates, details are not described herein again).
Semi-major axis:
Semi-minor axis:
Long axis direction starting point: Ak(xka,yka), long axis direction terminating point: Bk(xkb,ykb)
Further,
The elliptical center of circle: Ok(xko,yko),
Wherein,
Oval inclination angle:
To sum up, according to oval semi-major axis ak, semi-minor axis bk, center of circle Ok(xko,yko), angle of inclination betak, so that it may calculate as follows
Shown in elliptical parametric equation, and then determine ellipse in third image and the 4th image, that is, determine abnormal position.
xk=xko+ak·cosβk·cosθ-bk·sinβk·sinθ
yk=yko+ak·sinβk·cosθ-bk·cosβk·sinθ
Fig. 8 A and Fig. 8 B are respectively illustrated according to an embodiment of the invention to be shown in the first image and the second image
The abnormal schematic diagram detected.As shown, having irised out abnormal area with elliptical shape in the corresponding position of annulus.It should
Understand, in order to facilitate observation of, ellipse is enlarged and displayed with the thick line of white in Fig. 8 A and Fig. 8 B, in practical applications, can adopt
Ellipse is shown with other colors (e.g., red), to distinguish display abnormal area and zirconium end surfaces groove region.
Compared with prior art, method 200 of the invention has the following beneficial effects:
Firstly, method 200 overcomes traditional groove detection device single light source single using the multiple imaging of combined light source
Imaging, can only detection part groove face exception disadvantage.According to the method for the present invention 200, to the first image and the second image
It is detected respectively, detection range is wider, and precision is higher.
Secondly, the zirconium end surfaces annulus in original image has been launched into the band of rectangle by method 200, circle is not removed only
Interference of the ring center nuclear fuel to detection, while also increasing area-of-interest accounting, reduce operand, improve detection efficiency.
Again, it is contemplated that error influences when due to retaining wall on slope, and each groove face pattern is not quite similar, so in method
In 200, constructed template image is not fixed, based on current unfolded image (that is, third image and the 4th figure
Picture), three template images are constructed in the way of being averaged, and as the standard picture of groove, can adaptively be restored every
The state without exception of a groove face.
It is mapped in addition, method 200 is also utilized from third image/the 4th image to the first image/second image position, it will
The abnormal position detected in third image/the 4th image is mapped to the corresponding position in the first image/second image, and
It is come out using oval marks, is observed convenient for user.
The present invention discloses together:
A9, the method as described in A7, wherein based on the step of the 4th the second template image of picture construction include: building with
Second template image of the 4th image same size;For each pixel in each column pixel in the 4th image, calculate pixel with
The mean value of the pixel value of at least one adjacent pixel;Determine the difference of the pixel value of mean value and pixel;If difference is more than second pre-
If mean value, then is assigned to the pixel of corresponding position in the second template image by value;If difference is no more than the second preset value, by the 4th
The pixel value of corresponding position is assigned to the pixel of corresponding position in the second template image in image.A10, the method as described in A7,
In, it include: the third Prototype drawing of building Yu third image same size based on the step of third picture construction third template image
Picture;For each pixel in column pixel each in third image, calculating pixel is equal with the pixel value of at least one adjacent pixel
Value;Determine the difference of pixel value and mean value;If difference is more than third preset value, mean value is assigned in third template image corresponding
The pixel of position;If difference is no more than third preset value, the pixel value of corresponding position in third image is assigned to third template
The pixel of corresponding position in image.A11, the method as described in A10, wherein be based on third picture construction third template image
The step of before, further comprise the steps of: and third image pre-processed, to remove image interference.A12, any one of such as A8-11
The method, wherein the step of being based at least one template image, detecting the exception of groove and determine Exception Type packet
It includes: calculating the error image of the first template image and the 4th image;Determine at least one connected region in error image;Work as inspection
When measuring at least one connected region the first preset condition of satisfaction, determine that there are different for detected connected region corresponding position
Often and Exception Type is tube wall curvature abnormalities.A13, the method as described in any one of A9-11, wherein be based at least one mould
Plate image detects the exception of groove and includes: to calculate the second template image and the 4th image the step of determining Exception Type
Error image;Determine at least one connected region in error image;When detecting that it is pre- that at least one connected region meets second
If when condition, it is abnormal at groove chamfering for determining that the connected region corresponding position detected has abnormal and Exception Type.A14,
Method as described in any one of A10-11, wherein be based at least one template, detect the exception and Exception Type of groove
Step includes: to construct the first array and the second array based on third template image;Pass through at least two phases in the first array of statistics
Neighbors is 0 element, generates at least one First ray, and be greater than in the length for detecting at least one First ray and break
When splitting length threshold, determining that the First ray corresponding position has abnormal and Exception Type is that groove tip fracture is abnormal;Meter
The difference for calculating corresponding element in the first array and the second array, obtains difference array;Pass through in statistics difference array at least two
Adjacent element is all larger than 0 element, generates at least one second sequence, and big in the length for detecting at least one the second sequence
When protruding limitation of length value and the maximum value of the corresponding element of the second sequence in difference array is greater than prominent threshold value, really
It is that groove top width is abnormal that fixed second sequence corresponding position, which has abnormal and Exception Type,.A15, the method as described in A14,
Wherein, the step of being based on third template image, constructing the first array and the second array includes: to carry out two-value to third template image
Change processing, obtains the third template image of binaryzation;Each column pixel in third template image by traversing binaryzation, system
The pixel number that bright band is characterized in each column pixel is counted, to generate the first array of characterization bright band width;By calculating in the first array
The average value of each element and its at least one adjacent element generates the second array of characterization bright band width.Appoint in A16, such as A2-15
Method described in one, wherein according to the detected abnormal position in third image or the 4th image, determine exception
The step of position in the first image or the second image, comprises determining that detected abnormal in third image or the 4th image
In enclosure rectangle;Based on position mapping relations, calculated according to the position coordinates of enclosure rectangle the exception in the first image or
Position in second image.
Various technologies described herein are realized together in combination with hardware or software or their combination.To the present invention
Method and apparatus or the process and apparatus of the present invention some aspects or part can take insertion tangible media, such as can
Program code (instructing) in mobile hard disk, USB flash disk, floppy disk, CD-ROM or other any machine readable storage mediums
Form, wherein when program is loaded into the machine of such as computer etc, and when being executed by the machine, the machine becomes to practice
Equipment of the invention.
In the case where program code executes on programmable computers, calculates equipment and generally comprise processor, processor
Readable storage medium (including volatile and non-volatile memory and or memory element), at least one input unit, and extremely
A few output device.Wherein, memory is configured for storage program code;Processor is configured for according to the memory
Instruction in the said program code of middle storage executes date storage method and/or data query method of the invention.
By way of example and not limitation, readable medium includes readable storage medium storing program for executing and communication media.Readable storage medium storing program for executing
Store the information such as computer readable instructions, data structure, program module or other data.Communication media is generally such as to carry
The modulated message signals such as wave or other transmission mechanisms embody computer readable instructions, data structure, program module or other
Data, and including any information transmitting medium.Above any combination is also included within the scope of readable medium.
In the instructions provided here, algorithm and display not with any certain computer, virtual system or other
Equipment is inherently related.Various general-purpose systems can also be used together with example of the invention.As described above, it constructs this kind of
Structure required by system is obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can
With using various programming languages realize summary of the invention described herein, and the description that language-specific is done above be for
Disclosure preferred forms of the invention.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, knot is not been shown in detail
Structure and technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims than feature more features expressly recited in each claim.More precisely, as following
As claims reflect, inventive aspect is all features less than single embodiment disclosed above.Therefore, it abides by
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
As a separate embodiment of the present invention.
Those skilled in the art should understand that the module of the equipment in example disclosed herein or unit or groups
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in the example
In different one or more equipment.Module in aforementioned exemplary can be combined into a module or furthermore be segmented into multiple
Submodule.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
In addition, be described as herein can be by the processor of computer system or by executing by some in the embodiment
The combination of method or method element that other devices of the function are implemented.Therefore, have for implementing the method or method
The processor of the necessary instruction of element forms the device for implementing this method or method element.In addition, Installation practice
Element described in this is the example of following device: the device be used for implement as in order to implement the purpose of the invention element performed by
Function.
As used in this, unless specifically stated, come using ordinal number " first ", " second ", " third " etc.
Description plain objects, which are merely representative of, is related to the different instances of similar object, and is not intended to imply that the object being described in this way must
Must have the time it is upper, spatially, sequence aspect or given sequence in any other manner.
Although the embodiment according to limited quantity describes the present invention, above description, the art are benefited from
It is interior it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.Additionally, it should be noted that
Language used in this specification primarily to readable and introduction purpose and select, rather than in order to explain or limit
Determine subject of the present invention and selects.Therefore, without departing from the scope and spirit of the appended claims, for this
Many modifications and changes are obvious for the those of ordinary skill of technical field.For the scope of the present invention, to this
It invents done disclosure to be illustrative and be not restrictive, it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. a kind of detection method of groove exception, comprising steps of
The image for acquiring the zirconium end surfaces groove under the irradiation of different light sources, as the first image and the second image;
Based on second image, the ring-data of zirconium end surfaces is determined;
Based on the ring-data, third image corresponding with the first image and the second image and the 4th figure are generated
Picture;
Using third image and the 4th image, construct for detecting at least one abnormal template image;
Based at least one described template image, detects the exception of groove and determine Exception Type.
2. the method as described in claim 1, after the exception for detecting groove and the step of determine Exception Type, further include
Step:
According to position of the detected exception in third image or the 4th image, determine the exception in the first figure
Position in picture or the second image.
3. method according to claim 1 or 2, wherein the first image is the zirconium end surfaces slope under single axis light irradiation
The image of mouth, second image are the image of the zirconium end surfaces groove under the irradiation simultaneously of axis light and ring light.
4. method as claimed in any one of claims 1-3, wherein the ring-data includes that the center of circle of zirconium end surfaces is sat
Mark, outer diameter length and interior electrical path length.
5. method as claimed in claim 4, wherein it is described to be based on the second image, determine the step of the ring-data of zirconium end surfaces
Suddenly include:
Based on second image, the bianry image about zirconium end surfaces is generated;
Calculate the central coordinate of circle and outer diameter length of annulus in the bianry image;
According to the outer diameter length, the interior electrical path length of the annulus in bianry image is determined.
6. method according to any one of claims 1 to 5, wherein it is described be based on ring-data, generate with the first image and
The step of corresponding third image of second image and four images includes:
Based on ring-data, the size of third image and the 4th image is determined;
Using the pixel value of adjacent pixel of the respective pixel in the first image or the second image, determine the pixel respectively
Pixel value in three images or the 4th image.
7. such as method of any of claims 1-6, wherein described to utilize third image and the 4th image, building is used
Include: in the step of at least one abnormal template image of detection
Based on the 4th the first template image of picture construction and the second template image;
Based on third picture construction third template image.
8. the method for claim 7, wherein include: based on the step of the 4th the first template image of picture construction
First template image of building and the 4th image same size;
For each pixel in each column pixel in the 4th image,
Calculate the mean value of the pixel and the pixel value of at least one adjacent pixel;
Determine the pixel value of the pixel and the difference of the mean value;
If difference is more than the first preset value, the mean value is assigned to the pixel of corresponding position in the first template image;
If difference is no more than the first preset value, it is right in the first template image that the pixel value of corresponding position in the 4th image is assigned to
Answer the pixel of position.
9. a kind of calculating equipment, comprising:
At least one processor;With
It is stored with the memory of program instruction, wherein described program instruction is configured as being suitable for by least one described processor
It executes, described program instruction includes for executing the instruction such as any one of claim 1-8 the method.
10. a kind of readable storage medium storing program for executing for being stored with program instruction, when described program instruction is read and is executed by calculating equipment,
So that the calculating equipment executes such as method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910477151.9A CN110211113B (en) | 2019-06-03 | 2019-06-03 | Detection algorithm and calculation equipment for groove abnormity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910477151.9A CN110211113B (en) | 2019-06-03 | 2019-06-03 | Detection algorithm and calculation equipment for groove abnormity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110211113A true CN110211113A (en) | 2019-09-06 |
CN110211113B CN110211113B (en) | 2021-09-07 |
Family
ID=67790469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910477151.9A Active CN110211113B (en) | 2019-06-03 | 2019-06-03 | Detection algorithm and calculation equipment for groove abnormity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110211113B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113334389A (en) * | 2021-08-02 | 2021-09-03 | 宝信软件(南京)有限公司 | Steel pipe end robot track self-adaption and deviation rectification system and method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102218406A (en) * | 2011-01-04 | 2011-10-19 | 华南理工大学 | Intelligent detection device of defects of mobile phone outer shell based on machine vision |
CN104502356A (en) * | 2015-01-05 | 2015-04-08 | 江苏大学 | Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision |
CN104512579A (en) * | 2014-10-22 | 2015-04-15 | 中国电子科技集团公司第四十一研究所 | Defect detecting method for bracing wire on transparent packing material |
US20160012759A1 (en) * | 2014-07-09 | 2016-01-14 | Samsung Display Co., Ltd. | Vision inspection apparatus and method of detecting mura thereof |
CN106251361A (en) * | 2016-08-30 | 2016-12-21 | 兰州交通大学 | A kind of rail surface defects image self-adapting division method |
CN107228860A (en) * | 2017-06-28 | 2017-10-03 | 北京因时机器人科技有限公司 | A kind of gear defect detection method based on image rotation cyclophysis |
US20170330316A1 (en) * | 2016-05-11 | 2017-11-16 | International Business Machines Corporation | Image analysis methods for plated through hole reliability |
CN107664644A (en) * | 2017-09-30 | 2018-02-06 | 电子科技大学 | A kind of apparent automatic detection device of object based on machine vision and method |
CN108844961A (en) * | 2018-08-01 | 2018-11-20 | 佛山科学技术学院 | A kind of temperature controller case vision detection system and method |
-
2019
- 2019-06-03 CN CN201910477151.9A patent/CN110211113B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102218406A (en) * | 2011-01-04 | 2011-10-19 | 华南理工大学 | Intelligent detection device of defects of mobile phone outer shell based on machine vision |
US20160012759A1 (en) * | 2014-07-09 | 2016-01-14 | Samsung Display Co., Ltd. | Vision inspection apparatus and method of detecting mura thereof |
CN104512579A (en) * | 2014-10-22 | 2015-04-15 | 中国电子科技集团公司第四十一研究所 | Defect detecting method for bracing wire on transparent packing material |
CN104502356A (en) * | 2015-01-05 | 2015-04-08 | 江苏大学 | Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision |
US20170330316A1 (en) * | 2016-05-11 | 2017-11-16 | International Business Machines Corporation | Image analysis methods for plated through hole reliability |
CN106251361A (en) * | 2016-08-30 | 2016-12-21 | 兰州交通大学 | A kind of rail surface defects image self-adapting division method |
CN107228860A (en) * | 2017-06-28 | 2017-10-03 | 北京因时机器人科技有限公司 | A kind of gear defect detection method based on image rotation cyclophysis |
CN107664644A (en) * | 2017-09-30 | 2018-02-06 | 电子科技大学 | A kind of apparent automatic detection device of object based on machine vision and method |
CN108844961A (en) * | 2018-08-01 | 2018-11-20 | 佛山科学技术学院 | A kind of temperature controller case vision detection system and method |
Non-Patent Citations (5)
Title |
---|
HADIZADEH H等: ""Random Texture Defect Detection Using 1-D Hidden Markov Models Based on Local Binary Patterns"", 《ICE TRANSACTIONS ON INFORMATION AND SYSTEMS》 * |
WANG YING等: ""Pipe Defect Detection and Reconstruction Based on 3D Points Acquired by the Circular Structured Light Vision"", 《GEOMETRICAL VISION MEASUREMENT IN MECHANICAL ENGINEERING》 * |
张坤: ""面向数码产品外壳表面缺陷的适应性智能视觉检测技术研究"", 《中国优秀硕士学位论文全文数据库·信息科技辑》 * |
李凯: ""粉末冶金齿轮的视觉检测技术研究"", 《中国优秀硕士学位论文全文数据库·工程科技Ⅰ辑》 * |
王延江等著: "《数字图像处理》", 30 November 2016, 东营:中国石油大学出版社 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113334389A (en) * | 2021-08-02 | 2021-09-03 | 宝信软件(南京)有限公司 | Steel pipe end robot track self-adaption and deviation rectification system and method |
Also Published As
Publication number | Publication date |
---|---|
CN110211113B (en) | 2021-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20150276392A1 (en) | Graphical feedback during 3d scanning operations for obtaining optimal scan resolution | |
CN107636488B (en) | Method and apparatus for improving resolution of time-of-flight pixel arrays | |
CN102901444B (en) | Method for detecting component size based on matching pursuit (MP) wavelet filtering and detecting system thereof | |
CN106791804B (en) | For the smear detecting method and device of camera module | |
CN107578047B (en) | Eccentricity detection method for power cable | |
CN106845314B (en) | A kind of method for rapidly positioning of two dimensional code | |
CN110197180A (en) | Character defect inspection method, device and equipment | |
CN109859204A (en) | Convolutional neural networks Model Checking and device | |
CN111726612A (en) | Lens module dirt detection method, system, equipment and computer storage medium | |
CN109799073A (en) | A kind of optical distortion measuring device and method, image processing system, electronic equipment and display equipment | |
CN108955901A (en) | A kind of infrared measurement of temperature method, system and terminal device | |
CN108197596B (en) | Gesture recognition method and device | |
CN110211113A (en) | A kind of detection algorithm and calculating equipment of groove exception | |
CN106951811A (en) | A kind of image processing method and terminal | |
CN113111817A (en) | Semantic segmentation face integrity measurement method, system, equipment and storage medium | |
CN110879131A (en) | Imaging quality testing method and imaging quality testing device for visual optical system, and electronic apparatus | |
US9177223B2 (en) | Edge detection in images | |
JP2008145175A (en) | Array period obtaining method of wire of cable, shape state measuring method of cable, shape state measuring system of cable used for this, and shape state measuring program of cable | |
CN206019845U (en) | A kind of can be used for coding obtains the colorimetric card of body surface Accurate color value | |
CN109740337B (en) | Method and device for realizing identification of slider verification code | |
CN109658360B (en) | Image processing method and device, electronic equipment and computer storage medium | |
CN116660270A (en) | Power cable detection method, device and storage medium | |
CN107122084B (en) | Method and device for identifying touch operation on infrared touch screen and terminal equipment | |
JP2021050959A (en) | Inspection device and program | |
CN114782615A (en) | Real-time rendering method and device of indoor scene, electronic equipment and storage medium |
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 |