CN112991338A - Defect detection method and device for laser cutting part - Google Patents
Defect detection method and device for laser cutting part Download PDFInfo
- Publication number
- CN112991338A CN112991338A CN202110457308.9A CN202110457308A CN112991338A CN 112991338 A CN112991338 A CN 112991338A CN 202110457308 A CN202110457308 A CN 202110457308A CN 112991338 A CN112991338 A CN 112991338A
- Authority
- CN
- China
- Prior art keywords
- area
- edge
- image
- gray
- region
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 230000007547 defect Effects 0.000 title claims abstract description 57
- 238000003698 laser cutting Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 33
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 23
- 230000009466 transformation Effects 0.000 claims abstract description 23
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims abstract description 18
- 238000002679 ablation Methods 0.000 claims description 17
- 239000002893 slag Substances 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000013519 translation Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000007254 oxidation reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000012768 molten material Substances 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/02—Affine transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30136—Metal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Laser Beam Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a defect detection method and a defect detection device for laser cutting parts, wherein the method comprises the following steps: acquiring an image of a part to be detected; performing Gaussian filtering processing on a part image to be detected, and then performing threshold segmentation to obtain a part area and a part edge; performing affine transformation on a preset reference edge through template matching positioning to obtain an aligned reference edge; and dividing the part area by using the aligned reference edge to obtain a burr area. Acquiring and processing an image of a part to be detected to obtain a part area and part edge data, and then processing the part area and the part edge data by combining reference data obtained based on a qualified part image to obtain a corresponding defect area to realize defect detection; the scheme has no special requirements on the image, improves the automation level of laser cutting quality detection, and has wide application; the problems of low efficiency and large workload caused by the traditional dependence on artificial naked eye detection are solved, and the detection precision is high.
Description
Technical Field
The invention relates to the field of visual detection, in particular to a defect detection method and device for laser cutting parts.
Background
The laser cutting is to irradiate the workpiece with focused high-power-density laser beam to melt, vaporize and ablate the irradiated material quickly or reach the burning point, and simultaneously blow off the molten material by means of high-speed airflow coaxial with the beam, so as to continuously form a cutting seam along with the movement of the beam relative to the workpiece, thereby completing the cutting of the material. The laser cutting has the advantages of high precision, narrow cutting seam, high speed, good adaptability and activity, capability of cutting complex shapes and no limitation of material properties.
When laser oxygen cutting is performed, laser is used as a preheating heat source, and active gas such as oxygen is used as cutting gas. On one hand, the blown gas reacts with cutting metal to generate oxidation reaction and release a large amount of oxidation heat; on the other hand, molten oxide and melt are blown out of the reaction zone to form a cut in the metal. When laser oxygen cutting is carried out, the defects of burrs, sharp corner ablation, slag adhering and the like are easily generated, and the cutting quality is influenced. At present, the cutting quality detection of laser cutting parts generally depends on manual naked eye detection, the efficiency is low, the workload is large, and the condition of false detection exists; and the information of the specific position, size, area and the like of the defect cannot be accurately fed back.
Disclosure of Invention
The invention provides a defect detection method and device for laser cutting parts, and aims to solve the problem of low efficiency and accuracy of artificial naked eye detection.
In a first aspect, a defect detection method for laser cutting a part is provided, which includes:
acquiring an image of a part to be detected;
performing Gaussian filtering processing on a part image to be detected, and then performing threshold segmentation to obtain a part area and a part edge;
performing affine transformation on a preset reference edge through template matching positioning to obtain an aligned reference edge; the preset reference edge is obtained by processing the qualified part image;
and dividing the part area by using the aligned reference edge to obtain a burr area.
Further, still include:
performing affine transformation on a preset reference part area through template matching positioning to obtain an aligned reference part area; the method comprises the following steps that a preset reference part area is obtained by processing a qualified part image;
and (4) solving the difference between the aligned reference part area and the part area to obtain a sharp-corner ablation area.
Further, still include:
performing local threshold segmentation on the part area, and extracting a low-gray area;
performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity;
and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region.
Further, the process of obtaining the part area and the part edge comprises the following steps:
performing threshold segmentation on the part image to be detected after Gaussian filtering processing to obtain a part area;
performing expansion operation on the part area to obtain an expanded part area;
and solving the difference between the expanded part area and the part area to obtain the part edge.
Further, the performing affine transformation on the preset reference edge through template matching positioning to obtain the aligned reference edge includes:
obtaining a rotation and translation matrix from a preset reference edge to a part edge through template matching positioning;
and carrying out affine transformation on the preset reference edge based on the rotation and translation matrix to obtain the aligned reference edge.
Further, the obtaining of the aligned reference part region by performing affine transformation on the preset reference part region through template matching positioning includes:
obtaining a rotation and translation matrix from a preset reference edge to a part edge through template matching positioning;
and carrying out affine transformation on the preset reference part area based on the rotation and translation matrix to obtain the aligned reference part area.
Further, still include:
acquiring a qualified part image;
drawing an area containing an edge to be detected on the qualified part image, performing Gaussian filtering and threshold segmentation processing on the image in the area, and separating the part from the background to obtain a reference part area;
performing expansion operation on the reference part area to obtain an expansion reference part area;
and obtaining the reference edge by calculating the difference between the expansion reference part area and the reference part area.
Further, still include:
performing expansion operation on the reference edge to obtain a detection area;
before the part image to be detected is subjected to Gaussian filtering processing, the method further comprises the following steps:
and cutting the image of the part to be detected based on the detection area to obtain the image of the detection area.
Further, still include:
and outputting a detection result, wherein the detection result comprises a defect type, a defect position, a defect size, a defect area and a defect image.
In a second aspect, there is provided a defect detection apparatus for laser cutting a part, comprising:
an image acquisition module: the method comprises the steps of obtaining an image of a part to be detected;
an image preprocessing module: the device is used for performing Gaussian filtering processing on a part image to be detected and then performing threshold segmentation to obtain a part area and a part edge;
the device also comprises at least one of a burr detection module, a sharp corner ablation detection module and a slag adhering detection module; wherein:
burr detection module: the template matching positioning module is used for carrying out affine transformation on a preset reference edge to obtain an aligned reference edge; the preset reference edge is obtained by processing the qualified part image; dividing the part area by using the aligned reference edge to obtain a burr area;
the sharp corner ablation detection module: the method comprises the steps of carrying out affine transformation on a preset reference part area through template matching positioning to obtain an aligned reference part area; the method comprises the following steps that a preset reference part area is obtained by processing a qualified part image; the difference between the aligned reference part area and the part area is obtained to obtain a sharp corner ablation area;
a slag adhering detection module: the method is used for carrying out local threshold segmentation on the part area and extracting a low gray level area; performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity; and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region.
Advantageous effects
The invention provides a defect detection method and a device for laser cutting parts, which have the following advantages:
(1) acquiring and processing an image of a part to be detected to obtain a part area and part edge data, and then processing the part area and the part edge data by combining reference data obtained based on a qualified part image to obtain a corresponding defect area to realize defect detection; the scheme has no special requirements on the image, can conveniently detect the cutting quality of the laser cutting part, improves the automation level of the laser cutting quality detection, and has wide application;
(2) the problems of low efficiency and large workload caused by the traditional dependence on manual visual detection are solved, and the detection precision is high;
(3) the scheme can detect three defects of burrs, sharp corner ablation and slag adhering;
(4) parts in the image can be separated through Gaussian filtering and threshold segmentation processing, so that the scheme can detect under the condition that the obtained parts are not strictly aligned, and has better robustness.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a defect detection method for laser cutting a part according to an embodiment of the present invention;
FIG. 2 is a flowchart of a defect detection method for laser cutting a part according to an embodiment of the present invention;
FIG. 3 is a flowchart of a defect detection method for laser cutting a part according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Before the defect detection of the laser cutting part is carried out, a reference part area, a reference edge and a detection area are obtained as preset data, and the obtaining method comprises the following steps:
acquiring a qualified part image;
drawing an area containing an edge to be detected on the qualified part image, performing Gaussian filtering and threshold segmentation processing on the image in the area, and separating the part from the background to obtain a reference part area R1;
performing an expanding operation on the reference part region R1 to obtain an expanded reference part region R2;
subtracting the expansion reference part region R2 from the part reference region R1 to obtain a reference edge C = (R2-R1);
the reference edge C is subjected to a dilation operation to obtain a detection region R.
It should be noted that the qualified part image and the part image to be detected described below are both obtained by an image acquisition system based on the same structure, and the qualified part image and the part image to be detected may be one or more images according to the difference of the actual laser cutting part structure.
Example 1
As shown in fig. 1, the present embodiment provides a defect detection method for laser-cut parts, including:
s1: and acquiring an image of the part to be detected.
S2: and performing Gaussian filtering processing on the part image to be detected, and then performing threshold segmentation to obtain a part area and a part edge. Specifically, the process of obtaining the part area and the part edge includes:
performing threshold segmentation on the part image to be detected after Gaussian filtering processing, and extracting a foreground to obtain a part region TR 1;
performing an expansion operation on part region TR1 to obtain an expanded part region TR 2;
the expanded part region TR2 is subtracted from the part region TR1 to obtain the part edge TC = (TR2-TR 1).
S3: performing affine transformation on a preset reference edge through template matching positioning to obtain an aligned reference edge; and dividing the part area by using the aligned reference edge to obtain a burr area. The method specifically comprises the following steps:
obtaining a rotation translation matrix from a preset reference edge C to a part edge TC through template matching positioning;
performing affine transformation on the preset reference edge C based on the rotation translation matrix to obtain an aligned reference edge C2;
the part region TR1 is divided by the aligned reference edge C2, so that the burr portion is divided from the part region TR1, resulting in a burr region.
Example 2
The embodiment provides a defect detection method for laser cutting parts, as shown in fig. 2, on the basis of embodiment 1, the method further includes:
s4: performing affine transformation on a preset reference part area through template matching positioning to obtain an aligned reference part area; and (4) solving the difference between the aligned reference part area and the part area to obtain a sharp-corner ablation area. The method specifically comprises the following steps:
obtaining a rotation translation matrix from a preset reference edge C to a part edge TC through template matching positioning;
affine transformation is carried out on the preset reference part region R1 based on the rotation and translation matrix, and the aligned reference part region R3 is obtained;
the aligned reference part region R3 is subtracted from part region TR1 to obtain the sharp-angled ablated region.
Example 3
The embodiment provides a defect detection method for laser cutting parts, which is based on embodiment 1 or embodiment 2, and further comprises the following steps:
s5: performing local threshold segmentation on the part area, and extracting a low-gray area; specifically, a gray threshold value can be set according to the gray value of the part region part in the qualified part image, and a low gray region is obtained when the gray threshold value is lower than a preset gray threshold value;
performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity;
and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region. The method specifically comprises the following steps: the area of the low-gray sub-area is smaller than a preset area value and is not considered as a defect area; the low gray sub-region is not in communication with the cut edge and is not considered to be a defective region; the regional gray variance of the low gray sub-region is larger than the preset gray variance, the difference value between the regional average gray and the gray value of the qualified part is smaller than the preset value, the part is not considered as a defect region, and other low gray sub-regions are considered as defect regions.
As shown in fig. 3, it is an embodiment based on embodiment 2.
Example 4
The embodiment provides a defect detection method for laser cutting parts, which is based on embodiment 1, embodiment 2 or embodiment 3, and further comprises the following steps:
before the part image to be detected is subjected to Gaussian filtering processing, the part image to be detected is cut based on the detection region R (obtained based on the qualified part product image processing), and a detection region image is obtained.
By cutting the image of the part to be detected based on the detection area and then performing Gaussian filtering and threshold segmentation processing, the calculation cost can be reduced.
Example 5
The embodiment provides a defect detection method for laser cutting parts, which comprises the following steps on the basis of embodiment 1, embodiment 2, embodiment 3 or embodiment 4:
and outputting a detection result, wherein the detection result comprises a defect type, a defect position, a defect size, a defect area and a defect image.
The defect position, the defect size and the defect area can be obtained by identifying the position, the size and the area based on the obtained burr area, the sharp-corner ablation area and the slag adhering area, and the defect image comprises the burr area, the sharp-corner ablation area and the slag adhering area.
Example 6
The embodiment provides a defect detecting device for laser cutting part, includes:
an image acquisition module: the method comprises the steps of obtaining an image of a part to be detected;
an image preprocessing module: the device is used for performing Gaussian filtering processing on a part image to be detected and then performing threshold segmentation to obtain a part area and a part edge;
the defect detection device also comprises at least one of a burr detection module, a sharp corner ablation detection module and a slag adhering detection module; selecting one or more combinations of a burr detection module, a sharp corner ablation detection module and a slag adhering detection module according to different requirements of actual defect type detection; wherein:
burr detection module: the template matching positioning module is used for carrying out affine transformation on a preset reference edge to obtain an aligned reference edge; the preset reference edge is obtained by processing the qualified part image; dividing the part area by using the aligned reference edge to obtain a burr area;
the sharp corner ablation detection module: the method comprises the steps of carrying out affine transformation on a preset reference part area through template matching positioning to obtain an aligned reference part area; the method comprises the following steps that a preset reference part area is obtained by processing a qualified part image; the difference between the aligned reference part area and the part area is obtained to obtain a sharp corner ablation area;
a slag adhering detection module: the method is used for carrying out local threshold segmentation on the part area and extracting a low gray level area; performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity; and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region.
In specific implementation, the image of the part to be detected and the image of the qualified part are obtained by shooting through a camera. When the device is implemented, the clamp, the light source and the camera are arranged firstly, and the requirements are as follows:
the anchor clamps are used for fixing the laser cutting part of waiting to shoot, because the size of laser cutting part, the shape is different, need arrange light source and camera according to particular case. The light source is mainly arranged on the back side of the part, so that the requirement on uniform illumination is met, the edge of the part is protruded, and the brightness is not high enough. The number of the cameras is determined by the shape of the part and detection requirements, the lens of the camera is arranged on the back side of the part, the axis of the lens is perpendicular to the surface of the part as much as possible, the cutting seam area is required to be capable of imaging clearly, and no metal reflection saturation area is formed near the cutting seam. A small aperture and a large object distance are used as much as possible, and a certain depth of field is ensured. Focusing is carried out according to specific conditions, and camera parameters (such as aperture size and exposure time) are adjusted, so that images shot by the camera are clear, and the gray scale is moderate.
When collecting the part image to be detected and the qualified part image, fixing the part through the clamp, and then triggering the camera to shoot to obtain the image of the part.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A defect detection method for laser cutting a part, comprising:
acquiring an image of a part to be detected;
performing Gaussian filtering processing on a part image to be detected, and then performing threshold segmentation to obtain a part area and a part edge;
performing template matching positioning based on the edge of the part, and performing affine transformation on a preset reference edge to obtain an aligned reference edge; the preset reference edge is obtained by processing the qualified part image;
and dividing the part area by using the aligned reference edge to obtain a burr area.
2. The method of claim 1 for detecting defects in laser cut parts, further comprising:
performing template matching positioning based on the edge of the part, and performing affine transformation on a preset reference part area to obtain an aligned reference part area; the method comprises the following steps that a preset reference part area is obtained by processing a qualified part image;
and (4) solving the difference between the aligned reference part area and the part area to obtain a sharp-corner ablation area.
3. The method of claim 1 or 2, further comprising:
performing local threshold segmentation on the part area, and extracting a low-gray area;
performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity;
and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region.
4. The method of claim 1, wherein the step of obtaining the part area and the part edge comprises:
performing threshold segmentation on the part image to be detected after Gaussian filtering processing to obtain a part area;
performing expansion operation on the part area to obtain an expanded part area;
and solving the difference between the expanded part area and the part area to obtain the part edge.
5. The method for detecting the defects of the laser cutting part as claimed in claim 1, wherein the step of obtaining the aligned reference edge by performing template matching positioning based on the part edge and performing affine transformation on the preset reference edge comprises:
obtaining a rotation and translation matrix from a preset reference edge to a part edge through template matching positioning;
and carrying out affine transformation on the preset reference edge based on the rotation and translation matrix to obtain the aligned reference edge.
6. The method for detecting the defect of the laser cutting part as claimed in claim 2, wherein the step of performing affine transformation on the preset reference part region by performing template matching positioning based on the part edge to obtain the aligned reference part region comprises:
obtaining a rotation and translation matrix from a preset reference edge to a part edge through template matching positioning;
and carrying out affine transformation on the preset reference part area based on the rotation and translation matrix to obtain the aligned reference part area.
7. The method of claim 1 for detecting defects in laser cut parts, further comprising:
acquiring a qualified part image;
drawing an area containing an edge to be detected on the qualified part image, performing Gaussian filtering and threshold segmentation processing on the image in the area, and separating the part from the background to obtain a reference part area;
performing expansion operation on the reference part area to obtain an expansion reference part area;
and obtaining the reference edge by calculating the difference between the expansion reference part area and the reference part area.
8. The method of claim 7, further comprising:
performing expansion operation on the reference edge to obtain a detection area;
before the part image to be detected is subjected to Gaussian filtering processing, the method further comprises the following steps:
and cutting the image of the part to be detected based on the detection area to obtain the image of the detection area.
9. The method of claim 1 for detecting defects in laser cut parts, further comprising:
and outputting a detection result, wherein the detection result comprises a defect type, a defect position, a defect size, a defect area and a defect image.
10. A defect detection device for laser cutting a part, comprising:
an image acquisition module: the method comprises the steps of obtaining an image of a part to be detected;
an image preprocessing module: the device is used for performing Gaussian filtering processing on a part image to be detected and then performing threshold segmentation to obtain a part area and a part edge;
the device also comprises at least one of a burr detection module, a sharp corner ablation detection module and a slag adhering detection module; wherein:
burr detection module: the method comprises the steps of performing template matching positioning based on the edge of a part, and performing affine transformation on a preset reference edge to obtain an aligned reference edge; the preset reference edge is obtained by processing the qualified part image; dividing the part area by using the aligned reference edge to obtain a burr area;
the sharp corner ablation detection module: the method comprises the steps of carrying out template matching positioning based on the edge of a part, and carrying out affine transformation on a preset reference part area to obtain an aligned reference part area; the method comprises the following steps that a preset reference part area is obtained by processing a qualified part image; the difference between the aligned reference part area and the part area is obtained to obtain a sharp corner ablation area;
a slag adhering detection module: the method is used for carrying out local threshold segmentation on the part area and extracting a low gray level area; performing open operation on the low-gray-scale area, and separating the low-gray-scale area into a plurality of low-gray-scale sub-areas according to connectivity; and based on a preset threshold value, screening a plurality of low-gray sub-regions through the region area, the region gray variance and the region average gray to obtain a slag adhering region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110457308.9A CN112991338B (en) | 2021-04-27 | 2021-04-27 | Defect detection method and device for laser cutting part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110457308.9A CN112991338B (en) | 2021-04-27 | 2021-04-27 | Defect detection method and device for laser cutting part |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112991338A true CN112991338A (en) | 2021-06-18 |
| CN112991338B CN112991338B (en) | 2021-07-27 |
Family
ID=76340342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110457308.9A Active CN112991338B (en) | 2021-04-27 | 2021-04-27 | Defect detection method and device for laser cutting part |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991338B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119469A (en) * | 2021-10-13 | 2022-03-01 | 东方晶源微电子科技（北京）有限公司 | Image processing method, device and system for semiconductor electron beam defect monitoring |
| CN114406502A (en) * | 2022-03-14 | 2022-04-29 | 扬州市振东电力器材有限公司 | Laser metal cutting method and system |
| CN114619152A (en) * | 2022-02-27 | 2022-06-14 | 江苏本峰新材料科技有限公司 | Intelligent cutting system for aluminum veneer production and manufacturing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153067A (en) * | 2017-05-30 | 2017-09-12 | 镇江苏仪德科技有限公司 | A kind of surface defects of parts detection method based on MATLAB |
| 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 |
| US20170372464A1 (en) * | 2016-06-28 | 2017-12-28 | Ngr Inc. | Pattern inspection method and pattern inspection apparatus |
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN111369545A (en) * | 2020-03-10 | 2020-07-03 | 创新奇智(重庆)科技有限公司 | Edge defect detection method, device, model, equipment and readable storage medium |
| CN111650205A (en) * | 2020-05-11 | 2020-09-11 | 东风汽车集团有限公司 | Part surface defect detection method and system based on structured light image matching |
-
2021
- 2021-04-27 CN CN202110457308.9A patent/CN112991338B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170372464A1 (en) * | 2016-06-28 | 2017-12-28 | Ngr Inc. | Pattern inspection method and pattern inspection apparatus |
| CN107153067A (en) * | 2017-05-30 | 2017-09-12 | 镇江苏仪德科技有限公司 | A kind of surface defects of parts detection method based on MATLAB |
| 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 |
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN111369545A (en) * | 2020-03-10 | 2020-07-03 | 创新奇智(重庆)科技有限公司 | Edge defect detection method, device, model, equipment and readable storage medium |
| CN111650205A (en) * | 2020-05-11 | 2020-09-11 | 东风汽车集团有限公司 | Part surface defect detection method and system based on structured light image matching |
Non-Patent Citations (1)
| Title |
|---|
| 朱秀昌，刘峰: "《数字图像处理与图像通信》", 30 April 2002, 北京邮电大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119469A (en) * | 2021-10-13 | 2022-03-01 | 东方晶源微电子科技（北京）有限公司 | Image processing method, device and system for semiconductor electron beam defect monitoring |
| CN114619152A (en) * | 2022-02-27 | 2022-06-14 | 江苏本峰新材料科技有限公司 | Intelligent cutting system for aluminum veneer production and manufacturing |
| CN114619152B (en) * | 2022-02-27 | 2022-11-29 | 江苏本峰新材料科技有限公司 | Intelligent cutting system for aluminum veneer production and manufacturing |
| CN114406502A (en) * | 2022-03-14 | 2022-04-29 | 扬州市振东电力器材有限公司 | Laser metal cutting method and system |
| CN114406502B (en) * | 2022-03-14 | 2022-11-25 | 扬州市振东电力器材有限公司 | Laser metal cutting method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112991338B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112991338B (en) | Defect detection method and device for laser cutting part | |
| CN111867268B (en) | Method for repairing PCB by laser | |
| EP0501683B1 (en) | Technique for enhanced two-dimensional imaging | |
| CN108645867B (en) | Rapid locating and batch detection method for micro defects on surface of large-caliber optical crystal | |
| KR970058838A (en) | Laser processing method and laser processing device | |
| CN108489986A (en) | A kind of increasing material manufacturing on-line checking and restorative procedure | |
| JP2019002788A (en) | Metal processing surface inspection method, and metal processing surface inspection device | |
| JP2014032076A (en) | Method of measuring position and shape of welding groove | |
| JP2008241255A (en) | Method of detecting alignment mark position and laser machining device using method thereof | |
| Lertrusdachakul et al. | Vision-based control of wire extension in GMA welding | |
| CN111242979B (en) | Method for recognizing and tracking splashing of three-dimensional space in laser welding process | |
| JP2010197313A (en) | Inspection system of product shape | |
| JP7219400B2 (en) | WORK INSPECTION METHOD AND APPARATUS AND WORK MACHINING METHOD | |
| JP2009002679A (en) | Tool defect inspection device | |
| KR102257219B1 (en) | Laser marking inspection and post-processing device | |
| Franceschetti et al. | Dross attachment estimation in the laser-cutting process via Convolutional Neural Networks (CNN) | |
| CN116930194B (en) | Defect detection system and method for friction stir welding, electronic equipment and medium | |
| JP3901961B2 (en) | Pattern correction apparatus and pattern correction method | |
| JPH10314967A (en) | Device and method for laser beam machining | |
| JPH09192983A (en) | Tool attrition amount measuring method | |
| JP2024077285A (en) | IMAGE PROCESSING APPARATUS, LASER PROCESSING SYSTEM, WORK RECOGNITION METHOD, AND WORK RECOGNITION PROGRAM | |
| JP2004198403A (en) | Inspection device for painting face | |
| JPH1110373A (en) | Method for inspecting appearance of welding trace | |
| JP7040949B2 (en) | Parameter identification device, laser machine, parameter identification method, and program | |
| JP3409695B2 (en) | Surface defect inspection method |
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 |