WO2018098551A1 - Método e sistema para a inspeção automática de qualidade de materiais - Google Patents
Método e sistema para a inspeção automática de qualidade de materiais Download PDFInfo
- Publication number
- WO2018098551A1 WO2018098551A1 PCT/BR2017/050368 BR2017050368W WO2018098551A1 WO 2018098551 A1 WO2018098551 A1 WO 2018098551A1 BR 2017050368 W BR2017050368 W BR 2017050368W WO 2018098551 A1 WO2018098551 A1 WO 2018098551A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- capturing
- inspected
- defects
- light
- Prior art date
Links
- 239000000463 material Substances 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000007689 inspection Methods 0.000 title claims abstract description 40
- 230000007547 defect Effects 0.000 claims abstract description 65
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 30
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 11
- 239000011521 glass Substances 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 9
- 230000000875 corresponding effect Effects 0.000 description 6
- 238000005286 illumination Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000007635 classification algorithm Methods 0.000 description 4
- 239000002131 composite material Substances 0.000 description 4
- 239000013078 crystal Substances 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 4
- 239000010410 layer Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 229920000642 polymer Polymers 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000009957 hemming Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 239000002356 single layer Substances 0.000 description 3
- 239000012780 transparent material Substances 0.000 description 3
- 238000003466 welding Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000005357 flat glass Substances 0.000 description 2
- 239000005329 float glass Substances 0.000 description 2
- 238000002329 infrared spectrum Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000010422 painting Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 230000000946 synaptic effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 238000002211 ultraviolet spectrum Methods 0.000 description 2
- 238000001429 visible spectrum Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 239000000499 gel Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
- G01B11/303—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces using photoelectric detection means
-
- 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
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/18—Measuring force or stress, in general using properties of piezo-resistive materials, i.e. materials of which the ohmic resistance varies according to changes in magnitude or direction of force applied to the material
- G01L1/183—Measuring force or stress, in general using properties of piezo-resistive materials, i.e. materials of which the ohmic resistance varies according to changes in magnitude or direction of force applied to the material by measuring variations of frequency of vibrating piezo-resistive material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/08—Testing mechanical properties
- G01M11/081—Testing mechanical properties by using a contact-less detection method, i.e. with a camera
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
-
- 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
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- 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
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- 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
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8829—Shadow projection or structured background, e.g. for deflectometry
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8829—Shadow projection or structured background, e.g. for deflectometry
- G01N2021/8832—Structured background, e.g. for transparent objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30156—Vehicle coating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/12—Acquisition of 3D measurements of objects
- G06V2201/121—Acquisition of 3D measurements of objects using special illumination
Definitions
- This patent application relates to a method and system for the automatic inspection of material quality, specifically through the steps of: (i) capturing images of a light pattern reflected by or distorted through the inspected material; (ii) processing of the captured images; and (iii) identification of material defects.
- the external quality of a product is the first impression that may motivate a customer to buy it or not.
- a high quality body surface for example, is a competitive advantage in the automotive industry.
- the surface quality of a glass is critical in assessing its market value.
- the manufacture of a car body has several stages, such as: stamping, hemming, welding, painting and final assembly.
- stamping flat steel sheets of just under 1 mm thickness are formed in a press between a lower die (die) and an upper die (punch) when the latter descends on the sheet and exerts the shear force.
- presses are queued, each performing a draw, cut and fold function, so that at the end of the sequence of operations, a new body part is produced.
- Hemming is the process of bending and folding the flaps of an outer panel over an inner panel for closing hoods, doors or rear covers.
- the joining of the stamped parts is usually done by spot welding, forming the body, which goes through some layers of paint and drying ovens.
- the production of the parts goes through a strict quality control, in order to guarantee the uniformity in the manufacture and the fidelity with the designed model.
- This quality control aims to ensure not only the perfect coupling between parts to assemble the product in each of the following steps, but also a high quality body finish that meets customer expectations.
- the surface quality inspection method is done visually by a trained inspector to identify and classify defects.
- the defects are best observed if the piece reflects light in a specular way, that is, like a mirror.
- the metal surface must be covered with a thin layer of reflective oil when inspecting parts immediately after stamping, or be painted when inspecting the vehicle body at the end of the work.
- the light source has a known geometric pattern, for example, parallel lines composed of equally spaced tubular lamps. If the surface shows unwanted undulation, the pattern of light lines reflected in the part is distorted.
- Defletometry is defined as the set of procedures used to acquire topographic information on specular surfaces by analyzing the reflections of a known light pattern.
- Defects are classified according to their level of severity and the source of the error, eg tool mark, radius, corner sinking or local undulation. Besides being an intense and repetitive work, this method is subject to the subjectivity of the inspector evaluation.
- a common system in geometric analysis is a three-dimensional or 3D scanner, such as US6738507B2, which uses a set of monochrome lasers or lights to reconstruct the measured part topology in a computer.
- This measurement has a mesh of separate points. approximately 60 micrometers and can be compared to the dimensions of the CAD (computer aided design) drawing of the part design.
- the part is often painted with a white matte powder, so that the equipment laser is diffusedly reflected on the part, unlike the methods and systems described in this document, where light is reflected by or distorted. by the inspected surface.
- Dimensional control of parts through the 3D scanner focuses on the variation between the measured height on the part and the projected one.
- the height variation is not the unit most sensitive to the undulation surface defects, but the part curvature variation (which is its second derivative). Even ripples with slight height variations of 30 micrometres can be visually observed by an inspector when he reflects fringes of light on a piece.
- Another geometric analysis system is the part profile line-by-line scanner as disclosed in US7962303B2. This profilometer measures the profile
- US4920385A relates to a more complex optical array with moving mirrors that focus a laser beam, which is specularly reflected on the inspected part, reflected a second time on a retroreflective wall (reflecting the light in the same direction as the incident beam, such as 3M Company Scotchlight material), reflected a third time on the same inspected part and returning to a camera positioned near the light source.
- a retroreflective wall reflecting the light in the same direction as the incident beam, such as 3M Company Scotchlight material
- the aforementioned patent also introduces the need for polarizing filters to improve the signal-to-noise ratio acquired by the camera.
- the purpose of the present patent application is to propose an automatic solution for inspection of products, parts of products or packaging, which improves the objectivity, reproducibility, repeatability and speed of current material quality inspection processes.
- the methods and systems disclosed herein may be applied to the inspection of any material, reflective (ie, reflecting lights) or translucent (which is permeable but distorting lights), such as metallic, polymeric, composite, glass, polymer, acrylic, crystal, among others.
- the claimed methods and systems provide a solution for the automation of quality inspection of parts such as body surfaces, glass and car interiors. after the various steps of the production process, such as stamping, hemming, welding, painting or final assembly.
- the methods and systems claimed herein can evaluate, for example, irregularities in the mold that imprinted it on a press, so that this mold (tool) can be corrected.
- Objective measurement of the severity of surface defects provides an important tool for standardizing inspection, reporting and defect tracking processes. Also, the integration of inspection reports into the factory production process enables quick decision-making on necessary process corrections.
- Suitable materials for the application of the methods and systems of the present patent application may be reflective or translucent, for example, metallic, polymeric, composite, glass, polymer, acrylic, crystal surfaces, among others, basically by the steps of: capture of images reflected by or distorted through the material inspected; processing of captured images; and identification of material defects using artificial intelligence techniques.
- a set of lights with a defined geometric pattern focuses on a material to be inspected.
- the material to be inspected may be reflective, that is, it reflects the reflected, or translucent, or transparent light, and refracts or distorts the incident light.
- light reflected by or distorted through the material may be captured by an image pickup device, for example, but not limited to a camera.
- a defect in a material can then be perceived by distortions it causes in the pattern of the image that will be captured by the pickup apparatus.
- FIGURE 1 presents the system for the automatic inspection of quality reflective materials.
- FIGURE 2 presents the processing sequence in an apparatus for processing the captured image, identifying and classifying defects of the material inspected.
- FIGURE 3 shows the complete flow of the material quality inspection method.
- FIGURE 4 presents a possible embodiment which consists of a system for the automatic inspection of optical distortion quality on translucent, transparent, semi-transparent materials or any material that distorts the light on it.
- FIGURE 5 illustrates a possible implementation of artificial artificial neural network through single layer perceptrons.
- FIGURE 6 illustrates a possible implementation of the artificial neural network through multilayer perceptrons.
- FIGURE 7A and FIGURE 7B illustrate a possible embodiment in which the inspected part 110 is an automotive body 720, the light source 100 is shaped like a curved portal with illumination on its inside, the pickup apparatus 120 is comprised of at least one camera 730 and the software processing apparatus 200 is comprised of a computer 750.
- the present patent application relates, in a first possible embodiment, to a method for the automatic inspection of the quality of materials comprising the imaging steps reflected by or distorted through an inspected material; processing of captured images; and identification of material defects using artificial intelligence techniques.
- the method described here may involve the steps of:
- the present patent application relates to a method for automatic inspection of the surface of automobiles, such as bodies, chassis, windows, mirrors, bumpers, lamps and other auto parts.
- a method for automatic inspection of the surface of automobiles such as bodies, chassis, windows, mirrors, bumpers, lamps and other auto parts.
- such a method may involve the steps of:
- the projected light is emitted by a light source selected from the group comprising, but not limited to one set of tubular fluorescent lamps; or tubular LED lamps; or a screen illuminated by a projector or laser; or an LCD, plasma, OLED or LED screen; or a set of lamps having a sheet of material in front of them alternating translucent regions and black matte regions; or any device capable of creating a light and shadow pattern.
- a light source selected from the group comprising, but not limited to one set of tubular fluorescent lamps; or tubular LED lamps; or a screen illuminated by a projector or laser; or an LCD, plasma, OLED or LED screen; or a set of lamps having a sheet of material in front of them alternating translucent regions and black matte regions; or any device capable of creating a light and shadow pattern.
- the image is captured or captured by an image capture apparatus, which may be, for example, a video and / or photographic camera, an infrared camera, or an ultraviolet camera or any array of images.
- electromagnetic sensors capable of capturing an image.
- the method for automatic material quality inspection suitable for reflective materials comprises capturing or capturing the image reflected by the material.
- the image captured is the specular reflection of the material inspected.
- the method for automatic material quality inspection is suitable for transparent, semi-transparent or translucent materials, ie allowing the incident light to fully or partially pass through, refracting or distorting it. which comprises capturing or capturing the image distorted by the material.
- the image captured is the optical distortion of light passing through or passing through the inspected material.
- image processing comprises transforming the image into a binary image, with only two possible pixel values: white and black. This new binary image contains white fringes on a black background.
- the extracted features may be geometric features of the segment: the distance along the segment and the Euclidean distance between the beginning and the end of the segment.
- the curvature statistics calculated for each segment point can also be characteristic such as: the sum of the curvatures, the mean, the variance, the standard deviation, the obliquity, the kurtosis or combinations of these statistics.
- the curvatures of the points can be used considering their sign or in modulus for the calculation of the characteristics.
- the classification of the defects found can be done, for example, by calculating the white fringe midline, represented by the thin curves. Software calculates the curve regions corresponding to defects in the part and shows them as curve segments. [041]
- the defects of materials sought in the inspection cause a median size ripple on the fringes obtained after image processing. From the fringe geometry and curvature, features are extracted that feed a defect classification algorithm.
- defect identification software capable of transforming the captured image into a set of curves, each corresponding to one of these light fringes, and identifying a variation of the pattern of these curves resulting from a possible defect. , is used to fulfill the characterization stage of the defects found.
- calculated characteristics for each fringe segment serve as input to an artificial neural network, which outputs the classification of material defects.
- FIGURE 5 illustrates a possible implementation of the artificial neural network.
- light source 100 is selected from the group comprising, but not limited to a set of tubular fluorescent lamps; or tubular LED lamps; or a screen illuminated by a projector or laser; or an LCD, plasma, OLED or LED screen; or a set of lamps having a sheet of material in front of them alternating translucent regions and black matte regions; or any device capable of creating a light and shadow pattern.
- imager 120 may be, for example, a video and / or photographic camera, an infrared camera, or ultraviolet camera or any array of electromagnetic sensors capable of capturing an image.
- an apparatus capable of processing and analyzing data is used to comply with at least the steps of image processing, feature extraction and classification of defects found.
- Such an apparatus may be, for example, a computer, mobile device, microprocessor or any other apparatus comprising image processing software as well as defect identification and classification software.
- FIGURE 1 shows a system for automatic quality inspection of materials within the scope of the claims of the present patent application.
- the system contains a light source 100 that generates a light pattern, for example by creating parallel lines of light 101 on a black background 102.
- Illumination may be created by: a set of tubular fluorescent lamps; or tubular LED lamps; or a screen illuminated by a projector or laser; or an LCD, plasma, OLED or LED screen; or a set of lamps having a sheet of material in front of them alternating translucent regions and black matte regions; or any device capable of creating a light and shadow pattern.
- the luminous rays 111 of the lights 101 fall on the inspected part 110 and are reflected in a specular manner. as indicated by the reflected radius 112.
- the inspected material 110 may be metal, polymer, composite, glass or any other type of reflective material.
- Material 110 may be flat, curved, regular, wavy, concave, convex, or may comprise a mixture of such shapes.
- a pickup device 120 captures the reflected rays 112. Waving defects in the inspected part 110 alter the angle of the reflected rays 112, and thus the image captured by an image pickup apparatus 120.
- Imaging apparatus 120 may be, for example, a video and / or photographic camera, an infrared camera, or an ultraviolet camera or any array of electromagnetic sensors capable of capturing an image.
- the frequency range of the electromagnetic waves emitted by the light apparatus 100 and captured by the pickup apparatus 120 is preferably in the visible spectrum, however it may be in the infrared or ultraviolet spectrum.
- the image captured by said image capture apparatus 120 is transmitted to an apparatus 200 capable of processing the captured image, identifying and classifying defects.
- Apparatus 200 is, for example, a computer, mobile device, microprocessor or any other apparatus capable of processing and analyzing data.
- the apparatus 200 contains image processing software as well as defect identification and classification software.
- a light source 100 composed of fluorescent tube or LED lamps
- all regions of the inspected part 110 are illuminated by the lights 101 at some point due to the movement of the light source 100 made, for example, by a rack 104. coupled to the lamp structure driven by a motor 103.
- the shape of the light pattern is not limited to parallel lines, just as light source 100 need not necessarily be flat.
- the movement of rack 104 could move this blade containing stripes 101 and 102 without the need to move the lamps to its side. bottom.
- the fringes can be moved by varying the position of the inspected part or the camera.
- translation, rotation or changing of light patterns can be done by changing the projected image in case the light source 100 is an LCD, plasma, OLED or LED screen.
- FIGURE 2 shows the image processing sequence on apparatus 200 or 430.
- the captured image has luminous fringes 201 corresponding to the reflection. specular reflection of the lights 101 on the inspected part 110, or light fringes 431 corresponding to the lights that passed through the inspected part 410, as well as shadow regions 202 or 432 where there was no direct incidence of light from the light source 100 or 400.
- This first fringed 201 or 431 light and dark 202 or 432 image contains pixels with different color depths. It is transformed into a binary image with only two possible pixel values: white and black. This new binary image contains white fringes 203 on a black background 204.
- the next step is to calculate the midline of the white fringes 203, represented by thin curves 205.
- the software calculates the regions of the curves 205 corresponding to part defects and shows them. as curve segments 206.
- Such binary image processing steps correspond to apparatus 430.
- FIGURE 3 shows the complete flow of the material quality inspection method.
- Steps 301 and 302 refer to actions illustrated in FIGURE 1 or FIGURE 4, while steps 303 to 312 refer to the embedded software processes in apparatus 200 or 430 and illustrated in FIGURE 2.
- the method begins with projecting light 301 using light source 100 or 400 that is reflected on the inspected part 110 or passes through the inspected part 410 and by image capture 302 by the capture apparatus 120 or 420.
- This captured image contains light fringes of light 201 or 431 reflected over a darker area of part 202 or 432 where there was no direct light.
- the image is made up of an array of pixels, each pixel with different colors and brightness.
- Defect identification software must be able to transform the captured image into a set of curves, each corresponding to one of these light fringes, and to identify a variation in the pattern of these curves resulting from a possible defect.
- Image processing begins by binarization of image 305, i.e. the separation of pixels belonging to light fringes 203 from the rest of the image, with darker tone 204. In a second moment, each fringe 203 is finely tuned. which is represented by a single pixel width 205 curve, known as the erosion of the fringes 306.
- the curves 205 can be found by edge detection between light and dark fringe 204 or by edge detection between light fringes 201 or 431 and dark fringes 202 or 432. Edge detection can be implemented by applying various techniques, such as a gradient filter or Sobel filter. If the edge detection process does not generate a unit thickness curve, erosion of this edge is applied to obtain a one pixel wide curve.
- each of these curves 205 each representing a fringe
- the curvature 308 is calculated.
- a material defect is correlated with an abrupt variation of the fringe curvature.
- Each fringe is divided into segments.
- the criteria for dividing the fringe into segments can simply be to split each fringe into segments of the same pixel size.
- the points with a calculated curvature of zero may be used as dividing points of the fringe. It is also possible to consider overlapping between the segments or to analyze each fringe pixel as one if it were a segment.
- features 309 are extracted that feed a defect classification algorithm 304.
- the features here Mentioned may be geometric features of the segment: the distance along the segment and the Euclidean distance between the beginning and the end of the segment.
- the curvature statistics calculated for each segment point may also be characteristic such as: the sum of the curvatures, the mean, the variance, the standard deviation, the obliquity, the kurtosis or combinations of these statistics.
- the curvatures of the points can be used considering their sign or in modulus in the calculation of the characteristics. Additionally, bends can be discounted from a tolerance value below which bends would be disregarded in the calculation of defects.
- segment characteristics in the fringe of the analyzed segment can provide information if the segment analyzed has characteristics with values close to or different from its surroundings. Characteristics extracted from the context region can be, for example, distances or statistics of calculated curvatures, such as sum of curvatures, mean, variance, standard deviation, obliquity, kurtosis or combinations of these statistics. Context characteristics can be weighted by the distance to the segment analyzed. The context can be subdivided into regions, generating different characteristics that will serve as inputs to the classification algorithm 310.
- the calculated characteristics 309 for each fringe segment serve as input to an artificial neural network 310, which outputs the classification of surface defects 311.
- a possible implementation of the artificial neural network is through single layer or multilayer perceptrons. , as illustrated in FIGURE 5 and FIGURE 6.
- Classification 310 may be implemented, for example, by single-layer perceptrons, multilayer perceptrons, decision trees, convolutional neural networks, or combinations of these algorithms. Details about artificial neural networks are presented in the book Neural Networks and Learning Machines (Haykin, 2009). Synaptic weights of the artificial neural network are trained through a set of images with identified defects, ie through supervised training performed in the software calibration phase. After training this network, it is able to classify similar objects with regard to identifying and classifying material defects.
- FIGURE 5 illustrates a possible implementation of artificial neural network with only one neuron 500 called perceptron, where the characteristics 501 named xi, x2,. . . x n calculated at 309 are multiplied by synaptic weights 502 named wo, wi, ... w n , summed in operation 503 and multiplied by the activation function 504, yielding the result of defect classification 505.
- FIGURE 6 demonstrates an example of multi-layered artificial neural network 600 601, 602 and 603 interacting to form defect classification 604, where each neuron in these layers is represented by a circle and has an internal structure with weights. similar to structure 500.
- the number of inputs, outputs, neurons, and layers may change depending on the features extracted in 309, defect classes, and desired complexity.
- Segments 206 classified as defect 311 are overlaid on the original 201-202 or 431-432 image in the form of a report to the quality inspector.
- light patterns can be rotated, enlarged in size, or differ in shape.
- a single imager 120 may not capture the entire inspection area in a single image. Therefore, it is foreseeable that a set of pick-ups 120 will be used, or that the focus of the apparatus will be shifted relative to the inspected part 110.
- the source of illumination 100, the inspected part 110, and the parts of the apparatus may be moved with each other. pickup apparatus 120.
- FIGURE 7A and FIGURE 7B show possible embodiments, in the form of an inspection cell, comprising a system where the inspected part 110 is a automotive body 720, the light source 100 has the shape of a curved portal 710 with internal illumination, the pickup apparatus 120 consists of at least one camera 730 and the software processing apparatus 200 consists of a computer 750.
- the pickups may be fixed or mobile, for example using a robotic arm 740.
- FIGURE 4 presents another possible embodiment, which consists of a system for the automatic inspection of optical distortion quality in translucent, transparent or semi-transparent materials.
- the inspected material 410 may be glass, crystal, acrylic or any other transparent material.
- Material 401 may be flat or curved.
- the inspection system contains a light source 400 that generates a light pattern, for example by creating parallel lines of light 401 on a black background 402.
- Illumination may be created by: a set of tubular fluorescent lamps; or tubular LED lamps; or a screen illuminated by a projector or laser; or an LCD, plasma, OLED or LED screen; or a set of lamps having a sheet of material in front of them alternating translucent regions and black matte regions; or any device capable of creating a light and shadow pattern.
- the light rays of the lights 401 strike the inspected material 410 and are distorted due to the refractive index of the material 401.
- An image capture apparatus 420 captures the refracted rays through the material 401.
- the image capture apparatus 420 may be for example, a video and / or photographic camera, an infrared camera, an ultraviolet camera, or any array of electromagnetic sensors capable of capturing an image.
- the frequency range of the electromagnetic waves emitted by the luminous apparatus 400 and captured by the apparatus 420 it is preferably in the visible spectrum, however it may be comprised in the infrared or ultraviolet spectrum.
- the image captured by said image capture apparatus 420 is transmitted to an apparatus 430 capable of processing the captured image, identifying and classifying defects.
- Apparatus 430 is, for example, a computer, mobile device, microprocessor or any other apparatus capable of processing and analyzing data.
- Variations in the refractive index along material 401 cause ripples in the 431 light and dark stripe 432 patterns captured by the pickup device 420 and passed on to the 430 device.
- the 430 contains software for image processing as well as classification. optical distortion defects as described in FIGURE 2 and FIGURE 3.
- 410 being a flat glass
- a way of automating the measurement of the optical distortion defect level due to the variation of the refractive index along the part is presented, replacing the subjective verification currently made in the manufacturing industry. glass, which is visual inspection by an operator.
- a preferred implementation of the system of FIGURE 4 follows the dimensions of the Brazilian float glass inspection standard (ABNT NBR NM 294, 2004): the distance between the light source 400 and the inspected part 410 is 4.5 meters; the distance between the inspected part 410 and the pickup device 420 is 4.5 meters; light source 400 features 25mm wide light stripes and 25mm wide dark stripes; and preferably screen 410 consists of a translucent white background traversed by black parallel bands and illuminated from behind with fluorescent lamps.
- the quality of float glass is classified by the angle from which the distortion of refractory stripes 431 and 432 is above a tolerance. Distortion processing and calculation follows steps 301-312.
- the main indicative of distortion defect is a set of neighboring points with high curvature in a fringe. In the case of a streak on a glass, this distortion is noticed on several fringes, in the same vertical line along the glass, in the direction that it came out of the blast furnace.
- the methods and systems described in the present patent application serve for automatic inspection of the surface of automobiles, such as bodies, chassis, windows, mirrors, bumpers, lamps and other auto parts.
- automobiles such as bodies, chassis, windows, mirrors, bumpers, lamps and other auto parts.
- examples described in this report are not limiting, allowing a person skilled in the art to alter some aspects or components of the methods and systems described, equivalent to the solutions described herein, without departing from the scope herein claimed.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Optics & Photonics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112019011092A BR112019011092A2 (pt) | 2016-12-01 | 2017-11-30 | método e sistema para a inspeção automática de qualidade de materiais |
US16/428,393 US11024020B2 (en) | 2016-12-01 | 2019-05-31 | Method and system for automatic quality inspection of materials and virtual material surfaces |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR102016028266-7 | 2016-12-01 | ||
BR102016028266-7A BR102016028266A2 (pt) | 2016-12-01 | 2016-12-01 | Método e sistema para a inspeção automática de qualidade de materiais |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/428,393 Continuation-In-Part US11024020B2 (en) | 2016-12-01 | 2019-05-31 | Method and system for automatic quality inspection of materials and virtual material surfaces |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018098551A1 true WO2018098551A1 (pt) | 2018-06-07 |
Family
ID=62241020
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/BR2017/050368 WO2018098551A1 (pt) | 2016-12-01 | 2017-11-30 | Método e sistema para a inspeção automática de qualidade de materiais |
Country Status (3)
Country | Link |
---|---|
US (1) | US11024020B2 (pt) |
BR (3) | BR102016028266A2 (pt) |
WO (1) | WO2018098551A1 (pt) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110702035A (zh) * | 2019-10-25 | 2020-01-17 | 四川大学青岛研究院 | 一种基于面结构光的家电喷涂质量检测系统及方法 |
WO2020070673A1 (en) * | 2018-10-01 | 2020-04-09 | Guardian Glass, LLC | Method and system for detecting inclusions in float glass based on spectral reflectance analysis |
EP3715779A1 (de) * | 2019-03-29 | 2020-09-30 | FRAUNHOFER-GESELLSCHAFT zur Förderung der angewandten Forschung e.V. | Verfahren und vorrichtung zur bestimmung von verformungen an einem objekt |
EP3748538A1 (en) * | 2019-06-04 | 2020-12-09 | Alexis Gruet | Identification of structural imperfections on a reflective surface |
US11055531B1 (en) * | 2018-08-24 | 2021-07-06 | United Services Automobiie Association (USAA) | Augmented reality method for repairing damage or replacing physical objects |
CN114309513A (zh) * | 2020-09-27 | 2022-04-12 | 上海梅山钢铁股份有限公司 | 一种连铸板坯模拟切割方法 |
WO2022115928A1 (pt) * | 2020-12-04 | 2022-06-09 | Autaza Tecnologia Ltda - Epp | Métodos e sistemas para a inspeção de qualidade de materiais e de superfícies tridimensionais em ambiente virtual |
Families Citing this family (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
BR102016028266A2 (pt) * | 2016-12-01 | 2018-06-19 | Autaza Tecnologia Ltda - Epp | Método e sistema para a inspeção automática de qualidade de materiais |
US10580615B2 (en) * | 2018-03-06 | 2020-03-03 | Globalfoundries Inc. | System and method for performing failure analysis using virtual three-dimensional imaging |
JP7079123B2 (ja) * | 2018-03-15 | 2022-06-01 | キヤノン株式会社 | 撮像装置及びその制御方法、撮像システム |
IT201800006253A1 (it) * | 2018-06-12 | 2019-12-12 | Metodo e impianto per la localizzazione di punti su una superficie complessa nello spazio | |
US11379967B2 (en) * | 2019-01-18 | 2022-07-05 | Kla Corporation | Methods and systems for inspection of semiconductor structures with automatically generated defect features |
US11006053B2 (en) * | 2019-07-30 | 2021-05-11 | GM Global Technology Operations LLC | Weld inspection system and method |
WO2021054059A1 (ja) * | 2019-09-20 | 2021-03-25 | 株式会社Screenホールディングス | 撮像装置 |
EP3819586B1 (en) * | 2019-11-08 | 2022-03-30 | M-XR Limited | Method for generating a three-dimensional model of an object |
LU101529B1 (de) * | 2019-12-12 | 2021-06-15 | Aim Systems Gmbh | Vorrichtung und Verfahren zur Bestimmung einer Materialeigenschaft eines Prüfkörpers in einem oberflächennahen Prüfkörperbereich |
US10996165B1 (en) * | 2020-03-19 | 2021-05-04 | The Boeing Company | Apparatus and method for measuring UV coating effectiveness |
KR102268909B1 (ko) * | 2020-04-10 | 2021-06-23 | 코그넥스코오포레이션 | Edge Field와 딥러닝 기반 검사 방법 |
US11301980B2 (en) * | 2020-04-21 | 2022-04-12 | GM Global Technology Operations LLC | System and method to evaluate the integrity of spot welds |
US11937019B2 (en) | 2021-06-07 | 2024-03-19 | Elementary Robotics, Inc. | Intelligent quality assurance and inspection device having multiple camera modules |
US11232554B1 (en) * | 2021-06-07 | 2022-01-25 | Elementary Robotics, Inc. | Machine-learning based camera image triggering for quality assurance inspection processes |
CN111707692A (zh) * | 2020-07-17 | 2020-09-25 | 碳升技术服务(北京)有限公司 | 汽车零部件的缺陷检测方法、系统及电子设备 |
CN111862067B (zh) * | 2020-07-28 | 2021-10-26 | 中山佳维电子有限公司 | 一种焊接缺陷检测方法、装置、电子设备以及存储介质 |
FR3113325B1 (fr) | 2020-08-04 | 2022-07-08 | Michelin & Cie | Système et Procédé de Reconnaissance Automatique des Interfaces dans des Profils de Produits des Pneumatiques |
CN116075855A (zh) * | 2020-08-19 | 2023-05-05 | 3M创新有限公司 | 机器人修复控制系统和方法 |
US11494892B2 (en) * | 2020-08-21 | 2022-11-08 | Abb Schweiz Ag | Surface defect detection system |
EP3971556A1 (en) * | 2020-09-17 | 2022-03-23 | Evonik Operations GmbH | Qualitative or quantitative characterization of a coating surface |
CN112304957A (zh) * | 2020-11-20 | 2021-02-02 | 天津朗硕机器人科技有限公司 | 一种基于机器视觉的外观缺陷智能检测方法及系统 |
FR3116806B1 (fr) * | 2020-11-27 | 2022-11-11 | Airbus Operations Sas | Drone volant pour l’inspection de surfaces et procédé d’inspection de surfaces au moyen d’un tel drone volant |
WO2022152374A1 (en) * | 2021-01-13 | 2022-07-21 | Eaton Intelligent Power Limited | A surface roughness measurement system |
US20240230547A1 (en) * | 2021-06-21 | 2024-07-11 | Nissan Motor Co., Ltd. | Coating evaluation device and coating evaluation method |
WO2022269301A1 (ja) * | 2021-06-21 | 2022-12-29 | 日産自動車株式会社 | 塗装評価装置及び塗装評価方法 |
US20240288375A1 (en) * | 2021-06-21 | 2024-08-29 | Nissan Motor Co., Ltd. | Coating evaluation device and coating evaluation method |
DE102021122939B4 (de) * | 2021-09-06 | 2023-06-01 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren zum Beurteilen einer Oberfläche eines Karosseriebauteils sowie Verfahren zum Trainieren eines künstlichen neuronalen Netzes |
DE102021123880A1 (de) * | 2021-09-15 | 2023-03-16 | Isra Vision Gmbh | Verfahren und Vorrichtung zur Erkennung von lokalen Fehlern auf einer spiegelnden Oberfläche |
EP4402450A1 (en) * | 2021-09-16 | 2024-07-24 | Schneider GmbH & Co. KG | Method and apparatus for quality control of ophthalmic lenses |
US11605159B1 (en) | 2021-11-03 | 2023-03-14 | Elementary Robotics, Inc. | Computationally efficient quality assurance inspection processes using machine learning |
US12051186B2 (en) | 2021-11-03 | 2024-07-30 | Elementary Robotics, Inc. | Automatic object detection and changeover for quality assurance inspection |
US11675345B2 (en) | 2021-11-10 | 2023-06-13 | Elementary Robotics, Inc. | Cloud-based multi-camera quality assurance architecture |
US12050454B2 (en) | 2021-11-10 | 2024-07-30 | Elementary Robotics, Inc. | Cloud-based multi-camera quality assurance lifecycle architecture |
CN113899755A (zh) * | 2021-11-17 | 2022-01-07 | 武汉华星光电半导体显示技术有限公司 | 屏幕折痕程度的检测方法和视觉检测设备 |
CN113899754A (zh) * | 2021-11-17 | 2022-01-07 | 武汉华星光电半导体显示技术有限公司 | 屏幕褶皱程度的检测方法和视觉检测设备 |
US11605216B1 (en) | 2022-02-10 | 2023-03-14 | Elementary Robotics, Inc. | Intelligent automated image clustering for quality assurance |
CN114299065B (zh) * | 2022-03-03 | 2022-06-17 | 科大智能物联技术股份有限公司 | 丝锭外观成型不良缺陷检测与分级方法、存储介质及设备 |
CN114594103B (zh) * | 2022-04-12 | 2023-05-16 | 四川大学 | 核工业设备表面缺陷自动检测及报告自动生成方法及系统 |
CN115236085A (zh) * | 2022-07-19 | 2022-10-25 | 中冶赛迪信息技术(重庆)有限公司 | 一种利用投射曲线识别表面质量的方法 |
WO2024138009A2 (en) * | 2022-12-22 | 2024-06-27 | Arizona Board Of Regents On Behalf Of The University Of Arizona | Multi-spectral and polarization structured light illumination for three-dimensional imaging |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5175601A (en) * | 1991-10-15 | 1992-12-29 | Electro-Optical Information Systems | High-speed 3-D surface measurement surface inspection and reverse-CAD system |
US5216481A (en) * | 1990-12-19 | 1993-06-01 | Toyo Glass Co., Ltd. | Method of and apparatus for inspecting transparent object for defect |
JPH05164696A (ja) * | 1991-12-11 | 1993-06-29 | Nissan Motor Co Ltd | 塗装面評価装置 |
US5307152A (en) * | 1992-09-29 | 1994-04-26 | Industrial Technology Institute | Moire inspection system |
US20070206182A1 (en) * | 2003-10-21 | 2007-09-06 | Daihatsu Motor Co., Ltd. | Surface Defect Inspecting Method And Device |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4920385A (en) | 1984-02-14 | 1990-04-24 | Diffracto Ltd. | Panel surface flaw inspection |
US6476913B1 (en) * | 1998-11-30 | 2002-11-05 | Hitachi, Ltd. | Inspection method, apparatus and system for circuit pattern |
US6639685B1 (en) | 2000-02-25 | 2003-10-28 | General Motors Corporation | Image processing method using phase-shifted fringe patterns and curve fitting |
US6738507B2 (en) | 2001-01-09 | 2004-05-18 | Ford Global Technologies, Llc | Apparatus and method for correlating part design geometry, manufacturing tool geometry, and manufactured part geometry |
JP3788279B2 (ja) * | 2001-07-09 | 2006-06-21 | 株式会社日立製作所 | パターン検査方法及び装置 |
JP2006216865A (ja) * | 2005-02-04 | 2006-08-17 | Canon Inc | 判別方法及び装置、露光装置、並びにデバイス製造方法 |
JP4282643B2 (ja) | 2005-08-30 | 2009-06-24 | ダイハツ工業株式会社 | 歪評価装置及び歪評価方法 |
US8134681B2 (en) * | 2006-02-17 | 2012-03-13 | Nikon Corporation | Adjustment method, substrate processing method, substrate processing apparatus, exposure apparatus, inspection apparatus, measurement and/or inspection system, processing apparatus, computer system, program and information recording medium |
JP4616864B2 (ja) * | 2007-06-20 | 2011-01-19 | 株式会社日立ハイテクノロジーズ | 外観検査方法及びその装置および画像処理評価システム |
US8126255B2 (en) * | 2007-09-20 | 2012-02-28 | Kla-Tencor Corp. | Systems and methods for creating persistent data for a wafer and for using persistent data for inspection-related functions |
JP5820735B2 (ja) * | 2012-01-27 | 2015-11-24 | 昭和電工株式会社 | 表面検査方法及び表面検査装置 |
DE102012104282A1 (de) | 2012-05-16 | 2013-11-21 | Isra Vision Ag | Verfahren und Vorrichtung zur Inspektion von Oberflächen eines untersuchten Objekts |
FR2993662B1 (fr) * | 2012-07-23 | 2015-05-15 | Msc & Sgcc | Procede et installation pour la detection notamment de defauts refractants |
US20160284075A1 (en) * | 2013-03-14 | 2016-09-29 | Essess, Inc. | Methods, apparatus, and systems for structural analysis using thermal imaging |
US20140268105A1 (en) * | 2013-03-15 | 2014-09-18 | Zygo Corporation | Optical defect inspection system |
US9816939B2 (en) * | 2014-07-22 | 2017-11-14 | Kla-Tencor Corp. | Virtual inspection systems with multiple modes |
BR102016028266A2 (pt) * | 2016-12-01 | 2018-06-19 | Autaza Tecnologia Ltda - Epp | Método e sistema para a inspeção automática de qualidade de materiais |
US10607119B2 (en) * | 2017-09-06 | 2020-03-31 | Kla-Tencor Corp. | Unified neural network for defect detection and classification |
-
2016
- 2016-12-01 BR BR102016028266-7A patent/BR102016028266A2/pt not_active Application Discontinuation
-
2017
- 2017-11-30 WO PCT/BR2017/050368 patent/WO2018098551A1/pt active Application Filing
- 2017-11-30 BR BR112019011092A patent/BR112019011092A2/pt unknown
-
2019
- 2019-05-31 US US16/428,393 patent/US11024020B2/en active Active
- 2019-11-29 BR BR132019025379A patent/BR132019025379E2/pt unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5216481A (en) * | 1990-12-19 | 1993-06-01 | Toyo Glass Co., Ltd. | Method of and apparatus for inspecting transparent object for defect |
US5175601A (en) * | 1991-10-15 | 1992-12-29 | Electro-Optical Information Systems | High-speed 3-D surface measurement surface inspection and reverse-CAD system |
JPH05164696A (ja) * | 1991-12-11 | 1993-06-29 | Nissan Motor Co Ltd | 塗装面評価装置 |
US5307152A (en) * | 1992-09-29 | 1994-04-26 | Industrial Technology Institute | Moire inspection system |
US20070206182A1 (en) * | 2003-10-21 | 2007-09-06 | Daihatsu Motor Co., Ltd. | Surface Defect Inspecting Method And Device |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11055531B1 (en) * | 2018-08-24 | 2021-07-06 | United Services Automobiie Association (USAA) | Augmented reality method for repairing damage or replacing physical objects |
US11709253B1 (en) | 2018-08-24 | 2023-07-25 | United Services Automobile Association (Usaa) | Augmented reality method for repairing damage or replacing physical objects |
WO2020070673A1 (en) * | 2018-10-01 | 2020-04-09 | Guardian Glass, LLC | Method and system for detecting inclusions in float glass based on spectral reflectance analysis |
US11940383B2 (en) | 2018-10-01 | 2024-03-26 | Guardian Glass, LLC | Method and system for detecting inclusions in float glass based on spectral reflectance analysis |
EP3715779A1 (de) * | 2019-03-29 | 2020-09-30 | FRAUNHOFER-GESELLSCHAFT zur Förderung der angewandten Forschung e.V. | Verfahren und vorrichtung zur bestimmung von verformungen an einem objekt |
WO2020201217A1 (de) * | 2019-03-29 | 2020-10-08 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Verfahren und vorrichtung zur bestimmung von verformungen an einem objekt |
EP3748538A1 (en) * | 2019-06-04 | 2020-12-09 | Alexis Gruet | Identification of structural imperfections on a reflective surface |
WO2020245314A1 (en) * | 2019-06-04 | 2020-12-10 | Alexis Gruet | Identification of structural imperfections on a reflective surface |
CN110702035A (zh) * | 2019-10-25 | 2020-01-17 | 四川大学青岛研究院 | 一种基于面结构光的家电喷涂质量检测系统及方法 |
CN114309513A (zh) * | 2020-09-27 | 2022-04-12 | 上海梅山钢铁股份有限公司 | 一种连铸板坯模拟切割方法 |
WO2022115928A1 (pt) * | 2020-12-04 | 2022-06-09 | Autaza Tecnologia Ltda - Epp | Métodos e sistemas para a inspeção de qualidade de materiais e de superfícies tridimensionais em ambiente virtual |
Also Published As
Publication number | Publication date |
---|---|
BR112019011092A2 (pt) | 2019-10-01 |
BR132019025379E2 (pt) | 2020-04-22 |
US20190287237A1 (en) | 2019-09-19 |
BR102016028266A2 (pt) | 2018-06-19 |
US11024020B2 (en) | 2021-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018098551A1 (pt) | Método e sistema para a inspeção automática de qualidade de materiais | |
KR102646521B1 (ko) | 편광 큐를 이용한 표면 모델링 시스템 및 방법 | |
Ren et al. | State of the art in defect detection based on machine vision | |
US20190318469A1 (en) | Defect detection using coherent light illumination and artificial neural network analysis of speckle patterns | |
CN104508423B (zh) | 用于被检查对象的表面的检查的方法和装置 | |
CN111272763A (zh) | 用于工件检查的系统和方法 | |
Arnal et al. | Detecting dings and dents on specular car body surfaces based on optical flow | |
US11674907B2 (en) | Method and device for recognising and analysing surface defects in three-dimensional objects having a reflective surface, in particular motor vehicle bodies | |
Eshkevari et al. | Automatic dimensional defect detection for glass vials based on machine vision: A heuristic segmentation method | |
CN112243519A (zh) | 光学测试件的材料测试 | |
Stavropoulos et al. | A vision-based system for real-time defect detection: a rubber compound part case study | |
de la Calle Herrero et al. | Inspection system for rail surfaces using differential images | |
US20220178838A1 (en) | Method and apparatus for determining deformations on an object | |
Jaffery et al. | Scope and prospects of non-invasive visual inspection systems for industrial applications | |
US20240087105A1 (en) | Systems and Methods for Paint Defect Detection Using Machine Learning | |
JP2013539052A (ja) | レトロ反射型撮像 | |
CA3109406C (en) | Systems and methods for surface modeling using polarization cues | |
TWI407078B (zh) | Micro - lens array surface profile detection system and its detection method | |
CN111344553B (zh) | 曲面物体的缺陷检测方法及检测系统 | |
Arnqvist et al. | Efficient surface finish defect detection using reduced rank spline smoothers and probabilistic classifiers | |
Akhtar et al. | A robotics inspection system for detecting defects on semi-specular painted automotive surfaces | |
Wei et al. | Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review | |
US20240221143A1 (en) | Methods and systems for the automatic quality inspection of materials using infrared radiation | |
Tezerjani | High resolution visual pipe characterization system using an omnidirectional camera | |
BR102022025677A2 (pt) | Métodos e sistemas para a inspeção automática de qualidade de materiais utilizando radiação infravermelha |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17875696 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112019011092 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112019011092 Country of ref document: BR Kind code of ref document: A2 Effective date: 20190530 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17875696 Country of ref document: EP Kind code of ref document: A1 |