CN114494129A - Contrast enhancement method for surface slight deformation defect - Google Patents
Contrast enhancement method for surface slight deformation defect Download PDFInfo
- Publication number
- CN114494129A CN114494129A CN202111594118.8A CN202111594118A CN114494129A CN 114494129 A CN114494129 A CN 114494129A CN 202111594118 A CN202111594118 A CN 202111594118A CN 114494129 A CN114494129 A CN 114494129A
- Authority
- CN
- China
- Prior art keywords
- edge
- light
- defect
- light source
- bright
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005286 illumination Methods 0.000 claims abstract description 64
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 18
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 18
- 238000010586 diagram Methods 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 22
- 238000003384 imaging method Methods 0.000 claims description 17
- 230000000694 effects Effects 0.000 claims description 13
- 230000002708 enhancing effect Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 230000007797 corrosion Effects 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 8
- 230000001678 irradiating effect Effects 0.000 claims description 5
- 239000002131 composite material Substances 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 description 7
- 239000010959 steel Substances 0.000 description 7
- 238000005452 bending Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000002194 synthesizing effect Effects 0.000 description 3
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a contrast enhancement method for a surface slight deformation defect, which comprises the following steps: set up the slight deformation defect contrast enhancement device in surface to illumination source is to examining the surface irradiation, and move gradually to a direction illumination source, in order to ensure illumination source's marginal light covers wholly examine the surface, gather the removal in-process examine many reflection light line graphs on surface, get rid of bright background in many reflection light line graphs obtains many no stripe interference images, will many no stripe interference images carry out image synthesis, obtain the synthetic image of target, have realized the contrast enhancement to the slight deformation defect in surface, through contrast enhancement can be better acquire image information, detect the defect.
Description
RELATED APPLICATIONS
The benefit and priority of the chinese patent application entitled "a method, apparatus and storage medium for detecting surface defects of a workpiece" filed 2021, 12, month, 14, application No. 202111527576.X, is hereby incorporated by reference in its entirety.
Technical Field
The invention relates to the technical field of machine vision and digital image processing, in particular to a contrast enhancement method for a surface slight deformation defect.
Background
The quality of products in industrial production is becoming more and more strict, and the need of enterprises for a strong surface defect detection system is more and more urgent. At present, most of enterprises still adopt the traditional manual visual inspection method, and the surface of the product is observed one by experienced workers for surface detection, and the method has the following defects: low efficiency, low accuracy, high labor cost and large subjective influence of worker experience. In view of the defects which are difficult to overcome in the manual inspection, the automated surface defect detection which is mainly based on the machine vision can reduce the cost in all aspects, improve the detection efficiency and accuracy and further improve the product outlet quality, is becoming the current mainstream detection means, and is favored by more and more industries.
In the current stage, the surface defect detection based on machine vision mainly acquires an image of the surface of an object to be detected through an industrial camera, analyzes information such as gray scale, texture, color and the like of the surface of the object to be detected through an image processing technology, and judges whether defects exist. The existing surface detection technology can be well applied to the obvious defects in industrial on-line detection; for the surface tiny deformation defect, such as the defect of a slight dent of a steel plate, the defect is detected by analyzing the bending degree of the stripe light by using the structured light as a light source, however, the method can not completely acquire the information of the defect, influences the subsequent analysis of the defect, and the pit defect has little influence on the bending of the stripe, so the detection effect is not ideal.
The contrast of the surface slight deformation defect is low and no obvious edge exists under uniform light, the imaging effect is low, and the defect information cannot be completely acquired under stripe light, so that how to acquire a complete and clear image of the defect is a difficult point in industrial detection.
From the above, it can be seen that how to provide a method capable of enhancing the contrast of the surface light deformation defect is a problem to be solved at present.
Disclosure of Invention
Therefore, the invention aims to provide a contrast enhancement method for a surface slight deformation defect, so as to solve the problems that the prior art cannot completely acquire defect information and is not ideal for slight deformation detection. In order to solve the technical problem, the invention provides a contrast enhancement method for a surface slight deformation defect, which comprises the following steps: setting a contrast enhancement device for the surface slight deformation defect;
providing an illumination light source, wherein the illumination light source is a combined light source which comprises light and dark areas and can move, and the edge area of the light area close to the dark area forms the edge light of the combined light source;
irradiating the surface to be inspected by the illumination light source, and gradually moving the illumination light source to one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected;
collecting a plurality of reflected light ray diagrams of the surface to be detected in the moving process;
and removing bright backgrounds from the multiple reflected ray diagrams and carrying out image synthesis to obtain a target synthetic image. Preferably, the illumination light source is a stripe light.
Preferably, the edge light is a portion of 14% to 75% of the maximum brightness of the stripe lightThe width of the dark area at the bright and dark boundary of the detected surface is WedgeRegion of width WedgeThe selection of the defect detection method can be calculated according to the gray value proportion of different positions of the detected surface, and can also be judged according to the actual imaging effect of the defect.
Preferably, the acquiring a plurality of reflected light ray diagrams of the surface to be inspected in the moving process comprises:
collecting step length of the illumination light source as WedgeK pieces of reflected light ray diagrams of the surface to be detected in the moving process;
wherein k is selected according to the following formula:
k＝max(Wdark/Wedge-2,Wbright/Wedge)+1
Wdarkwidth of dark stripe, WbrightWidth of bright stripes, WedgeThe selection can be calculated according to the gray value proportion of different positions of the surface to be detected, and can also be judged according to the actual imaging effect of the defect, and the width W of the dark stripedark＝2*WedgeIn this case, the dark stripe regions are all edge light detection regions, and k is Wbright/Wedge+1, according to the width W of the bright stripebrightThe minimum scan period is chosen to ensure coverage of the examined area.
Preferably, the removing the bright background from the multiple reflected light ray diagrams and performing image synthesis to obtain the target synthetic image includes:
converting the multiple reflected light ray diagrams into multiple image signals respectively and transmitting the image signals to a computer;
respectively carrying out expansion corrosion operation on a plurality of input image signals of the plurality of reflection ray diagrams by using a local maximum difference method to determine the maximum value and the minimum value near a specified neighborhood so as to obtain a plurality of expansion corrosion images;
linearly combining the multiple expansion corrosion images to obtain multiple fringe interference-free images;
taking the average value of the gray levels of the corresponding positions in the image information of the plurality of non-fringe interference images as the gray level value of the target composite image;
and carrying out proportion adjustment on the gray value of the target synthetic image to obtain the target synthetic image.
The invention provides a contrast enhancement method for a surface slight deformation defect, which comprises the following steps: the method comprises the steps that a contrast enhancement device for the slightly deformed defect of the surface is arranged, an illumination light source is provided, the illumination light source is a combined light source which comprises a light area and a dark area, wherein the light area is movable between the light area and the dark area, the edge area close to the dark area forms edge light of the combined light source, the illumination light source irradiates the surface to be inspected and gradually moves the illumination light source in one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected, if the surface to be inspected is free of defects, light rays are reflected on the surface in a mirror surface mode, if the surface to be inspected is defective, part of light rays are scattered, and as the light rays entering the defects account for the larger proportion of the total light rays, the interference of the peripheral light rays on defect imaging is smaller, and the contrast enhancement of the slightly deformed defect of the surface to be inspected is realized; and removing the bright background from the multiple reflected light ray diagrams, and carrying out image synthesis to obtain a target synthetic image, thereby further enhancing the contrast of the surface slight deformation defect in the algorithm. According to the method for enhancing the contrast of the surface slight deformation defect, provided by the invention, the edge light of the illumination light source is utilized to irradiate the surface to be detected, the contrast of the surface slight deformation is enhanced, the collected light pictures are subjected to bright background removal and synthesis, the contrast of the surface slight deformation is further enhanced, and the image information can be better obtained through contrast enhancement, so that the defect can be detected.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a flow chart of one embodiment of a method for contrast enhancement of surface light deformation defects according to the present invention;
FIG. 2 is an edge light schematic;
FIG. 3 is a schematic view of a stripe light source;
FIG. 4 is a schematic diagram of bright fringe edge defect imaging;
FIG. 5 is a schematic view of a surface light deformation defect;
FIG. 6 is a schematic diagram of a defect detection apparatus according to an embodiment;
FIG. 7 is a schematic diagram of fringe light movement;
FIG. 8 is a schematic view of the imaging of slight dents on the surface of a steel plate;
FIG. 9 is a schematic of a striped light lower surface light defect imaging;
FIG. 10 is a schematic view of a composite image;
fig. 11 is a block diagram of an apparatus for contrast enhancement of a surface light deformation defect according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide a method for enhancing the contrast ratio of the surface slight deformation defect, which enhances the contrast ratio of the surface slight deformation defect.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. 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 embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a contrast enhancement method for a surface light deformation defect according to an embodiment of the present invention; the specific operation steps are as follows:
step S101: setting a contrast enhancement device for the surface slight deformation defect;
step S102: irradiating the surface to be inspected by using an illumination light source, and gradually moving the illumination light source towards one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected;
step S103: collecting a plurality of reflected light ray diagrams of the surface to be detected in the moving process;
step S104: and removing bright backgrounds from the multiple reflected ray diagrams and carrying out image synthesis to obtain a target synthetic image.
The invention provides a contrast enhancement method for a surface slight deformation defect, which comprises the following steps: the method comprises the steps that a contrast enhancement device for the slightly deformed defect of the surface is arranged, an illumination light source is provided, the illumination light source is a combined light source which comprises a light area and a dark area, wherein the light area is movable between the light area and the dark area, the edge area close to the dark area forms edge light of the combined light source, the illumination light source irradiates the surface to be inspected and gradually moves the illumination light source in one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected, if the surface to be inspected is free of defects, light rays are reflected on the surface in a mirror surface mode, if the surface to be inspected is defective, part of light rays are scattered, and as the light rays entering the defects account for the larger proportion of the total light rays, the interference of the peripheral light rays on defect imaging is smaller, and the contrast enhancement of the slightly deformed defect of the surface to be inspected is realized; and removing the bright background from the multiple reflected light ray diagrams, and carrying out image synthesis to obtain a target synthetic image, thereby further enhancing the contrast of the surface slight deformation defect in the algorithm. According to the method for enhancing the contrast of the surface slight deformation defect, provided by the invention, the edge light of the illumination light source is utilized to irradiate the surface to be detected, the contrast of the surface slight deformation is enhanced, the collected light image is subjected to background removal and synthesis, and the contrast of the surface slight deformation is further enhanced.
Based on the above embodiment, the present embodiment further describes the above process with a steel plate as a surface to be inspected, and the specific steps are as follows:
step S201: setting a contrast enhancement device for the surface slight deformation defect;
step S202: irradiating the surface to be detected by using an illumination light source, and gradually moving the illumination light source in one direction to ensure that the edge light of the illumination light source covers the whole surface to be detected;
the illumination light source is combined light which can move between bright and dark areasThe light area edge area close to the dark area forms the edge light of the combined light source, the edge light adopts 14-75% of the maximum brightness of the stripe light, namely the dark area width at the bright-dark boundary of the detected surface is WedgeRegion of width WedgeThe selection can be calculated according to the gray scale value proportion of different positions of the detected surface, and can also be judged according to the actual imaging effect of the defect, please refer to fig. 2, wherein fig. 2 is an edge light diagram;
the illumination light source can be stripe light, and is made by adhering reflective or non-reflective sticker on a specific surface light source, the area with the sticker is used as a dark area, and the light-emitting area without the sticker is a bright area, as shown in fig. 3. Setting the illumination light source to be overexposed, gradually moving the surface dent to be detected and acquiring an image, as shown in fig. 4, wherein fig. 4(a) is far away from a bright stripe, the imaging effect of a defect is not obvious, fig. 4(b) and fig. 4(c) are respectively the positions of two sides of the bright stripe, which can enhance the contrast of the slightly deformed defect of the surface, and the contrast of the dent is the maximum when the boundary of a bright and dark area is close to the dark area within 5mm, namely W is found through actual measurement under the condition of overexposure of the light source, namelyedgeAnd 5mm is taken, so that the width of each bright and dark stripe on the surface to be detected can be set to be 10mm in the embodiment, and the bright and dark areas to be detected are switched by the mutual movement among the illumination light source, the surface to be detected and the image acquisition device.
Referring to FIG. 5, FIG. 5 is a schematic diagram illustrating a surface light deformation defect;
in this embodiment, the illumination light source is an important link of image input, which directly affects the quality of the acquired image information, and since the defects of the surface defect to be detected, which need to be detected, are various in types, different in positions and different in sizes, a proper light source needs to be selected to achieve the best effect. In the embodiment, the dark area of the bright and dark boundary of the stripe is used as a light source, and a schematic diagram of the light source refers to fig. 5(a), after light is emitted into the surface to be measured, when the surface to be measured has no defect, the emergent direction cannot be changed, and the light detected by the image acquisition device is uniform; referring to fig. 5(b), when the surface to be detected has a slight concave-convex defect, the emergent light changes, the light detected by the image acquisition device also changes, and because the proportion of the light entering the defect under the fringe light to the total light is large, the interference of the surrounding light to the defect imaging is small, and the contrast of the defect with slight surface deformation is enhanced.
Because the defect detection device structure occupies a great proportion to the quality influence of the whole acquisition scheme, the structural layout directly influences the uniformity of illumination. Therefore, the structure of the defect detecting apparatus of the present embodiment is shown in fig. 6.
Step S203: collecting a plurality of reflected light ray diagrams of the surface to be detected in the moving process;
the image acquisition device observes the reflected image of the illumination light source through the surface to be detected, wherein the image acquisition device adopts an industrial camera which is provided with an image acquisition card, the image acquisition device used in the embodiment is a CMOS (complementary metal oxide semiconductor) camera, after light rays are emitted into the surface to be detected, when no defect exists in the surface to be detected, the emergent direction cannot be changed, and the light detected by the target surface of the CMOS camera is uniform; when the surface to be detected has slight concave-convex defects, the emergent light can change, and the light detected by the target surface of the CMOS camera also changes along with the emergent light.
Collecting step length of the illumination light source as WedgeK pieces of reflected light ray diagrams of the surface to be detected in the moving process;
wherein k is selected according to the following formula:
k＝max(Wdark/Wedge-2,Wbright/Wedge)+1
Wdarkwidth of dark stripe, WbrightWidth of bright stripes, WedgeThe selection can be calculated according to the gray value proportion of different positions of the surface to be detected, and can also be judged according to the actual imaging effect of the defect, and the width W of the dark stripedark＝2*WedgeIn this case, the dark stripe regions are all edge light detection regions, and k is Wbright/Wedge+1, according to the width W of the bright stripebrightSelecting the minimum scan period when WedgeGet Wedge～3*WedgeIn the meantime, the full-coverage detection of the surface to be detected can be completed by scanning the surface to be detected for 2-4 steps;
according to the formula, in order to ensure that the light defects are detected, the width of each bright and dark stripe is set to be 2WedgeStep length of WedgeCollecting 4 images in total to realize the full coverage of the surface to be detected;
moving the illumination light source in one direction by step length WedgeAnd collecting images, and moving for a total of four times to obtain 4 light images about the surface to be inspected, please refer to fig. 7, where fig. 7 is a schematic diagram of stripe light movement.
Step S204: removing bright backgrounds in the multiple reflected light ray diagrams to obtain multiple fringe interference-free images;
the computer is connected with the industrial camera to read image information, an image processing system is arranged in the computer to transmit a plurality of acquired reflected light images to the computer, the acquired light images are preprocessed firstly, the purposes of eliminating black and white stripe backgrounds and highlighting detection defects are achieved through local maximum difference filtering, the input black and white stripe images are respectively subjected to expansion and corrosion operations, the maximum value and the minimum value near a specified neighborhood are determined through expansion and corrosion, and then the expanded and corroded images are subjected to linear combination, so that the image without stripe interference is obtained.
Step S205: carrying out image synthesis on the plurality of non-fringe interference images to obtain a target synthetic image;
synthesizing all the preprocessed images, wherein a synthesis algorithm is used for searching an average value of gray scales at corresponding positions in each image as a most main reference gray value, and a target synthesized image containing defects is obtained by carrying out appropriate proportion adjustment on the reference gray value;
the new synthetic image obtained through the algorithm covers the surface to be detected, and the contrast of the surface slight deformation defect is further enhanced.
Step S206: extracting defect characteristics of the target synthetic image to obtain a surface defect characteristic diagram to be detected;
according to the invention, the contrast of the surface slight deformation defect is enhanced by the illumination of the bright area edge area of the fringe light, and the appropriate width of the bright and dark fringes and the moving step length and the moving times of the illumination light source are selected according to the width of the edge light area, so that the illumination light source is moved to shoot a plurality of light images, and the collected light images can be ensured to cover the surface to be detected; and synthesizing the image without the stripe interference after the black and white background is removed by the local maximum difference method, wherein the newly synthesized image not only removes the interference of the black and white background, but also enhances the contrast of the surface slight deformation defect.
Based on the above embodiment, the method is adopted to perform the operation process of defect contrast enhancement: the following steps are specifically performed by taking a steel plate as an example, and the main contents are to confirm that the steel plate is provided with the dents and the pits:
first, a steel plate to be measured is placed on a placement table, which is a fixed device and cannot be moved. The image of the object to be detected, which is not acquired by the scheme of the invention, has poor detection effect on the surface slight deformation defect by adopting a common illumination mode as shown in fig. 8 (a).
In the embodiment of the present disclosure, the stripe light is used as the illumination light source, the illumination light source is controlled to display bright stripes with a certain width, the bright stripes move 4 times in one direction, the image acquisition device performs image acquisition and storage corresponding to each movement, as shown in fig. 9, and fig. 9 is a schematic diagram of imaging of a slight defect on the lower surface of the stripe light.
After the acquisition is finished, image processing can be carried out, firstly, all the acquired images are preprocessed, the purposes of eliminating black and white stripe backgrounds and highlighting detection defects are achieved through local maximum difference filtering, then, a plurality of images are synthesized, a synthesis algorithm is used for carrying out value taking by searching an average value of gray scales at corresponding positions in each image, and a new synthesized image is obtained after proportion adjustment. After all the pictures are subjected to calculation processing, the image of fig. 10 can be obtained, and the defect contrast is further enhanced in the algorithm of fig. 10.
And after the image of the image shown in FIG. 10 is obtained, preprocessing and image feature extraction are sequentially carried out according to a general visual processing algorithm, and dents in the defect are distinguished from concave-convex points on the basis of the roundness value and the length-width comparison value of the steel plate defect.
The invention provides a contrast enhancement method for a surface slight deformation defect, which comprises the following steps: the method comprises the steps that a contrast enhancement device for the slightly deformed defect of the surface is arranged, an illumination light source is provided, the illumination light source is a combined light source which comprises a light area and a dark area, wherein the light area is movable between the light area and the dark area, the edge area close to the dark area forms edge light of the combined light source, the illumination light source irradiates the surface to be inspected and gradually moves the illumination light source in one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected, if the surface to be inspected is free of defects, light rays are reflected on the surface in a mirror surface mode, if the surface to be inspected is defective, part of light rays are scattered, and as the light rays entering the defects account for the larger proportion of the total light rays, the interference of the peripheral light rays on defect imaging is smaller, and the contrast enhancement of the slightly deformed defect of the surface to be inspected is realized; and removing bright backgrounds in the multiple reflection ray diagrams to obtain multiple non-fringe interference images, and carrying out image synthesis on the multiple non-fringe interference images to obtain a target synthetic image, thereby further enhancing the contrast of the surface slight deformation defect in the algorithm.
The contrast enhancement device for the surface slight deformation defect provided by the invention structurally ensures the uniformity of the illumination light source and is convenient to operate; according to the method for enhancing the contrast ratio of the slight surface deformation defect, the contrast ratio of the slight surface deformation defect is enhanced through the illumination of the bright area edge area of the fringe light, the proper bright and dark fringe width, the moving step length and the moving times of the illumination light source are selected according to the width of the edge light area, the illumination light source is moved to shoot a plurality of light images, the collected light images can cover the surface to be detected, the interference of the bright background is removed through removing and synthesizing the light images, and the contrast ratio of the slight surface deformation defect is further enhanced; the contrast enhancement method for the surface slight deformation defect provided by the invention enhances the contrast of the defects such as the small concave convex point and the like on the surface to be detected, solves the technical problems that the contrast of the surface slight deformation defect is low under uniform light and has no obvious edge, the imaging effect is low, the detection effect of the slight deformation is not ideal by analyzing the stripe bending, and can better acquire image information and detect the defect by contrast enhancement.
Referring to fig. 11, fig. 11 is a block diagram of a structure of a contrast enhancement apparatus for a surface slight deformation defect according to an embodiment of the present invention, where the apparatus may include:
the illumination light source module 100 is used for detecting the defects of the surface to be detected, irradiating the surface to be detected by the illumination light source, and gradually moving the illumination light source to one direction to ensure that the edge light of the illumination light source covers the whole surface to be detected;
the image acquisition module 200 is used for acquiring a plurality of reflected light ray diagrams of the surface to be detected in the moving process;
and the image synthesis module 300 is configured to remove the bright background from the multiple reflected light ray diagrams, and perform image synthesis to obtain a target synthesis image.
The device for enhancing contrast with a slight surface deformation defect of this embodiment is used to implement the method for enhancing contrast with a slight surface deformation defect described above, and thus the specific implementation manner in the enhancement of contrast with a slight surface deformation defect of the surface can be seen in the previous embodiment portions of the method for enhancing contrast with a slight surface deformation defect described above, for example, the illumination light source module 100, the image acquisition module 200, and the image synthesis module 300 are respectively used to implement steps S101, S102, and S103 in the method for enhancing contrast with a slight surface deformation defect described above, so that the specific implementation manner thereof may refer to the description of the corresponding embodiments of each portion, and is not described herein again.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The contrast enhancement method and device for the surface light deformation defect provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (5)
1. A method for contrast enhancement of a surface light deformation defect, comprising:
setting a contrast enhancement device for the surface slight deformation defect;
providing an illumination light source, wherein the illumination light source is a combined light source which comprises light and dark areas and can move, and the edge area of the light area close to the dark area forms the edge light of the combined light source;
irradiating the surface to be inspected by the illumination light source, and gradually moving the illumination light source to one direction to ensure that the edge light of the illumination light source covers the whole surface to be inspected;
collecting a plurality of reflected light ray diagrams of the surface to be detected in the moving process;
and removing bright backgrounds from the multiple reflected ray diagrams and carrying out image synthesis to obtain a target synthetic image.
2. The method of claim 1, wherein the illumination source is a striped light.
3. The contrast enhancement method for the surface slight deformation defect according to claim 2, characterized in that the edge light adopts a part of 14% -75% of the maximum brightness of the stripe light, namely, the width of the dark area at the bright-dark boundary of the detected surface is WedgeRegion of width WedgeThe selection can be calculated according to the gray value proportion of different positions of the detected surface, and can also be calculated according to the actual defectAnd judging the imaging effect.
4. The method of claim 1, wherein the acquiring a plurality of reflection ray maps of the surface to be inspected during the movement comprises:
collecting the step length of the illumination light source as WedgeK pieces of reflected light ray diagrams of the surface to be detected in the moving process;
wherein k is selected according to the following formula:
k＝max(Wdark/Wedge-2,Wbright/Wedge)+1
Wdarkwidth of dark stripe, WbrightWidth of bright stripes, WedgeThe selection can be calculated according to the gray value proportion of different positions of the surface to be detected, and can also be judged according to the actual imaging effect of the defect, and the width W of the dark stripedark＝2*WedgeIn this case, the dark stripe regions are all edge light detection regions, and k is Wbright/Wedge+1, according to the width W of the bright stripebrightThe minimum scan period is chosen to ensure coverage of the examined area.
5. The method for enhancing contrast ratio of surface light deformation defect according to claim 1, wherein the removing bright background of the plurality of reflected light ray images and performing image synthesis to obtain the target synthetic image comprises:
converting the multiple reflected light ray diagrams into multiple image signals respectively and transmitting the image signals to a computer;
respectively carrying out expansion corrosion operation on a plurality of input image signals of the plurality of reflection ray diagrams by using a local maximum difference method to determine the maximum value and the minimum value near a specified neighborhood so as to obtain a plurality of expansion corrosion images;
linearly combining the multiple expansion corrosion images to obtain multiple fringe interference-free images;
taking the average value of the gray levels of the corresponding positions in the image information of the plurality of non-fringe interference images as the gray level value of the target composite image;
and carrying out proportion adjustment on the gray value of the target synthetic image to obtain the target synthetic image.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527576X | 2021-12-14 | ||
| CN202111527576 | 2021-12-14 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114494129A true CN114494129A (en) | 2022-05-13 |
| CN114494129B CN114494129B (en) | 2023-04-18 |
Family
ID=81495048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111594118.8A Active CN114494129B (en) | 2021-12-14 | 2021-12-23 | Contrast enhancement method for surface slight deformation defect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494129B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104749190A (en) * | 2015-04-02 | 2015-07-01 | 华中农业大学 | Online visual inspection device and online visual inspection method for cracks on surface of poultry eggs |
| US20170122878A1 (en) * | 2013-12-27 | 2017-05-04 | Jfe Steel Corporation | Surface defect detecting method and surface defect detecting apparatus |
| CN110827235A (en) * | 2019-09-24 | 2020-02-21 | 苏州苏相机器人智能装备有限公司 | Steel plate surface defect detection method |
| US20200088650A1 (en) * | 2017-05-29 | 2020-03-19 | Konica Minolta, Inc. | Surface Defect Inspection Device and Method |
| CN112150441A (en) * | 2020-09-24 | 2020-12-29 | 菲特（天津）检测技术有限公司 | Smooth paint surface defect detection method based on machine vision |
| CN112611761A (en) * | 2020-11-27 | 2021-04-06 | 常州柯柏电子科技有限公司 | Method and system for detecting surface defects of high-reflectivity object |
-
2021
- 2021-12-23 CN CN202111594118.8A patent/CN114494129B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170122878A1 (en) * | 2013-12-27 | 2017-05-04 | Jfe Steel Corporation | Surface defect detecting method and surface defect detecting apparatus |
| CN104749190A (en) * | 2015-04-02 | 2015-07-01 | 华中农业大学 | Online visual inspection device and online visual inspection method for cracks on surface of poultry eggs |
| US20200088650A1 (en) * | 2017-05-29 | 2020-03-19 | Konica Minolta, Inc. | Surface Defect Inspection Device and Method |
| CN110827235A (en) * | 2019-09-24 | 2020-02-21 | 苏州苏相机器人智能装备有限公司 | Steel plate surface defect detection method |
| CN112150441A (en) * | 2020-09-24 | 2020-12-29 | 菲特（天津）检测技术有限公司 | Smooth paint surface defect detection method based on machine vision |
| CN112611761A (en) * | 2020-11-27 | 2021-04-06 | 常州柯柏电子科技有限公司 | Method and system for detecting surface defects of high-reflectivity object |
Non-Patent Citations (3)
| Title |
|---|
| XU-HUA LIU, ZHI-YONG HE, YU SUN: "On study of a method for detecting micro-deformation defects of steel plate surface", 《PROCEEDINGS VOLUME 11568, AOPC 2020: OPTICS ULTRA PRECISION MANUFACTURING AND TESTING; 115680M (2020)》 * |
| YIYANG HUANG, HUIMIN YUE, YUYAO FANG, WEI WANG, AND YONG LIU: "Structured-light modulation analysis technique for contamination and defect detection of specular surfaces and transparent objects", 《OPTICS EXPRESS》 * |
| 徐少鹏: "基于机器视觉的偏光片缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114494129B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6515344B2 (en) | Defect detection apparatus and defect detection method | |
| US9171364B2 (en) | Wafer inspection using free-form care areas | |
| JP6594294B2 (en) | Image quality evaluation of microscopic images | |
| JP4150390B2 (en) | Appearance inspection method and appearance inspection apparatus | |
| CN109716495B (en) | Method and system for optical measurement of opening size in wafer | |
| CA3061262C (en) | Fluorescent penetrant inspection system and method | |
| KR20120088750A (en) | Method for analysing the quality of a glass panel | |
| US20160088213A1 (en) | Inspection apparatus, coordinate detection apparatus, coordinate detection method, and wavefront aberration correction method | |
| JP2009259036A (en) | Image processing device, image processing method, image processing program, recording medium, and image processing system | |
| JP4279833B2 (en) | Appearance inspection method and appearance inspection apparatus | |
| JP2002148195A (en) | Surface inspection apparatus and surface inspection method | |
| CN111879789A (en) | Metal surface defect detection method and system | |
| CN117309892B (en) | Defect detection method, device and system for blue film of battery and light source controller | |
| JP3324699B2 (en) | Method and apparatus for measuring fiber diameter distribution | |
| CN114494129B (en) | Contrast enhancement method for surface slight deformation defect | |
| JP3752849B2 (en) | Pattern defect inspection apparatus and pattern defect inspection method | |
| CN115830021A (en) | Metal surface defect detection method for hardware processing | |
| JP2003329428A (en) | Device and method for surface inspection | |
| JP2006270334A (en) | Shading correction method and image inspection device | |
| JP2022161475A (en) | Defect detection device, defect detection method, image processing device and image processing program | |
| JP5949690B2 (en) | Evaluation method and evaluation apparatus | |
| JP6185539B2 (en) | Optical connector ferrule end face inspection device and inspection program | |
| CN111179248A (en) | Transparent smooth curved surface defect identification method and detection device | |
| CN109791039B (en) | Method for generating three-dimensional information of sample using optical microscope | |
| CN115661026A (en) | Cylindrical mirror defect detection method and device |
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 |