Quantitative image analysis system for evaluating surface-based coating performance

Abstract

A method for quantifying surface defects on a coated substrate includes: a) providing a system for acquiring and analyzing images; b) loading a coated substrate, wherein the coated substrate includes a coating formed on the surface of the substrate, onto a holder; c) illuminating the coated substrate using an illumination system, wherein illuminating the coated substrate includes illuminating the coated substrate at an incident angle of 15° to 85° with respect to a plane parallel to the surface of the coated substrate to generate shadows of any defects on the surface of the coated substrate; d) acquiring one or more images of the coated substrate using an imaging system; e) using an analysis unit to transform one or more images of the coated substrate and provide one or more transformed images, and quantifying surface defects on the coated substrate based on one or more transformed images; and f) providing an output, wherein the output includes a value that identifies the amount or percentage of defects on the coated substrate, and / or a generated image showing the amount or percentage of surface defects on the coated substrate.

Description

Technical Field

[0001] The present invention generally relates to a method for quantitatively analyzing an image of defects based on the surface on a coated substrate.

Background Art

[0002] The appearance of a coated substrate is one of the most important performance evaluation criteria used by consumers and researchers. Defects in a coated substrate can appear in many different ways, including color abnormalities, surface or texture differences, or other visible deviations. For example, the smoothness or leveling of a coated substrate may appear as a surface defect caused by a shadow or change in appearance. For example, resistance to defects caused by water, corrosion, dirt, grease, and weathering may appear as a change in the color of the coated substrate. Other defects within the coated substrate, such as movement / secretion or extraction of components within the coated substrate, may be more difficult to visually observe.

[0003] Such defects in a coated substrate are typically observed or measured by humans. Since it is difficult to evaluate many of the defects in a coated substrate, defect measurement is often difficult to accurately and / or reproducibly quantify. Most measurements of defects are very subjective and are typically measured on a simple scale, such as a numerical scale of 1 to 5, and a human observer assigns a value based on the interpretation of the surface of the coated substrate. It is common for the values assigned by one observer to vary from those assigned by the next observer, and defect quantification generally has to be done approximately. Due to the subjective nature of the measurement, the observations are typically normalized in each study. Therefore, data obtained by human observation from one study cannot be reliably combined with data from another study.

[0004] Attempts have been made to automate the defect detection process. U.S. Patent Application Publication 2022 / 0082508 discloses a method for providing a coating composition-related prediction program, which includes providing a database of qualitative and / or quantitative characterizations of coating surfaces and training a machine learning model to develop a composition quality prediction program for predicting the properties of manufactured coating surfaces. However, the database of qualitative and / or quantitative characterizations is generated by manually identifying and labeling digital images, and the qualitative and / or quantitative characterization of the images is based on a scale with values ​​assigned by human observers. Thus, the database is compiled with data based on human observations.

[0005] To identify and quantify defects, a process is needed that can detect defects within coated substrates more accurately and reproducibly. [Overview of the project]

[0006] The present invention is a method for quantifying surface defects on a coated substrate, a) A system for acquiring and analyzing images, said system i) An imaging system for acquiring one or more images of a coated substrate, ii) A lighting system including a light source for illuminating a coated substrate, iii) A holder for holding the coated substrate in a position illuminated by a light source, iv) To provide a system comprising an analysis unit configured to convert one or more images and quantitatively analyze one or more converted images for defects on a coated substrate, b) A coated substrate, wherein the coated substrate includes a coating formed on the surface of the substrate, and the coated substrate is loaded onto a holder. c) Illuminating a coated substrate using an illumination system, wherein illuminating the coated substrate includes illuminating the coated substrate at an incident angle of 15° to 85° with respect to a plane parallel to the surface of the coated substrate to generate shadows of any defects on the surface of the coated substrate, d) Acquire one or more images of the coated substrate using an imaging system, e) Transforming one or more images of a coated substrate using an analysis unit, wherein the transformation of one or more images of the coated substrate includes processing one or more images of the coated substrate using an algorithm selected from the group consisting of image thresholding, wavelet transform, morphological transformation, color detection, pattern detection, clustering, and combinations thereof, to provide one or more transformed images, and quantifying surface defects on the coated substrate based on the one or more transformed images. f) A method comprising providing an output which includes a value that identifies the amount or percentage of defects on a coated substrate, and / or a generated image showing the amount or percentage of surface defects on the coated substrate. [Brief explanation of the drawing]

[0007] [Figure 1] This is a schematic diagram of a system for acquiring and analyzing images according to an embodiment of the present invention. [Figure 2] This is a schematic diagram showing the position of the light source relative to the coated substrate according to an embodiment of the present invention. [Figure 3] This is a converted color image from an unfolded chart used in a smoothness test, analyzed by an image analysis system according to an embodiment of the present invention. [Figure 4] This is a texture image converted from an unfolded chart used in a smoothness test, analyzed by an image analysis system according to an embodiment of the present invention. [Figure 5] This is a black and white image generated by illumination of a test specimen from a leveling test method with white light from above, as analyzed by an image analysis system according to an embodiment of the present invention. [Figure 6] This is a texture image converted from a leveling test method, analyzed by an image analysis system according to an embodiment of the present invention. [Modes for carrying out the invention]

[0008] The inventors have found a method for reproducibly and accurately identifying and quantifying defects in a coated substrate.

[0009] As used herein, the term “coated substrate” refers to a substrate having a coating on its surface, such as a paint coating on a metal or paper substrate. The coating preferably has a thickness of less than 500 μm, more preferably less than 300 μm, even more preferably less than 200 μm, and preferably greater than 50 nm, more preferably greater than 100 nm, and even more preferably greater than 250 nm. Multilayer coatings may have greater thicknesses. The coated substrate may include, for example, multiple layers including a primer or a base coat.

[0010] Preferably, the coated substrate includes a coating selected from polyurethane coating, epoxy coating, acrylic coating (e.g., acrylic coating, vinyl-acrylic coating, and styrene-acrylic coating), alkyd coating, and zinc-rich coating. More preferably, the coated substrate includes a paint. The substrate may include metal, plastic, wood, glass, composite material, glass fiber, paper, fabric, leather, or other substrates. For testing purposes, it is preferable that the substrate has a flat or planar surface.

[0011] Defects within or on coated substrates can be caused by a variety of issues. Examples of defects include, but are not limited to, color defects, surface or texture defects, and migration / secretion or extraction defects.

[0012] Color defects may include stains due to dirt, household stains (e.g., wine, pencil, lipstick, crayon, ink, marker, etc.), adhesion defects where the coating does not adhere sufficiently to the substrate, concealment defects where the coating allows the underlying substrate or sublayer to be visible, oil resistance which evaluates the penetration of oil through the coating, early rain resistance which tests the coating's ability to withstand runoff by rain immediately after application and curing, and efflorescence resistance which tests the coating's ability to withstand efflorescence and alkali burnout.

[0013] Texture or surface defects may be indicated by problems with smoothness or leveling, resulting in an irregular or imperfect surface of the coating. Other texture or surface problems may include, for example, cracking or delamination.

[0014] Migration / secretion and / or extraction occur when components separate from other components or migrate through a coating. Migration / secretion and / or extraction can result from incompatibility of materials in contact with the coating or components within the coating. For example, surfactant leaching can occur when a water-soluble material leaches onto the surface of the coating when the coating comes into contact with water. Other examples include the migration of binders or additives, which may be affected by time, temperature, or environmental conditions. Migration / secretion and / or extraction can result in visible defects, although often such defects are not readily apparent. However, the inventors have surprisingly found that defects of migration / secretion and / or extraction can be identified and analyzed using infrared or ultraviolet spectroscopy. Species that may migrate / secrete or be extracted may have different properties observable in infrared or ultraviolet spectroscopy. For example, when analyzing surfactant leaching, the inventors have found that migrating components have different thermal conductivity than the remaining components, making these defects readily identifiable in infrared spectroscopy.

[0015] A system for analyzing and quantifying defects is provided for analyzing coated substrates. A schematic diagram of the defect analysis and quantification system 100 is shown in Figure 1. The system 100 comprises an imaging system 10, an illumination system 20, a holder 30 for holding the coated substrate 35, and an analysis unit 40.

[0016] The imaging system 10 is configured to acquire one or more images of the coated substrate 35. The imaging system 10 may include, for example, a camera or an image sensor. The imaging system 10 may further include filters for preferentially or selectively transmitting or blocking light of a predetermined wavelength, such as one or more channels of a predetermined wavelength.

[0017] The lighting system 20 includes a light source for illuminating the coated substrate 35. The lighting system 20 is preferably configured to emit radiation in the visible light spectrum. The light source preferably comprises a single light source, as a result of which surface defects appear as shadows when illuminated. Preferably, the light source is a point source or a directional light source. Preferably, the lighting system 20 is configured to enable adjustment of the light intensity, the angle of incidence on the coated substrate 35, or the wavelength of the light emitted. To reduce the potential influence of external lighting, the system 100 may be covered or surrounded (not shown) such that only the light from the lighting system 20 is used to acquire an image.

[0018] As shown in FIG. 2, the lighting system 20 is configured to illuminate the coated substrate at an angle of incidence α of 15° to 85°, preferably 20° to 70°.

[0019] The substrate holder 30 is used to hold the coated substrate 35 for imaging by the imaging system 10. The holder 30 is configured to hold the coated substrate in a position where it is illuminated by the lighting system 20 when it is imaged. The holder 30 may be configured to hold a single coated substrate 35 or a plurality of coated substrates. The holder 30 may be stationary or adapted to automatically load / unload test pieces.

[0020] Preferably, one or more of the imaging system 10 and the holder 30 are adjustable such that the position of the coated substrate 35 can be changed with respect to the imaging system 10. For example, as shown in FIG. 1, the imaging system 10 may be mounted on an arm 101 attached to a vertical support 102. The arm 101 may be configured to be adjustable such that the distance between the imaging system 10 and the holder 30 can be selected. Alternatively, the arm 101 may be movable between two or more positions. In another alternative, the holder 30 may be adjustable to raise or lower the holder 30 using a base 103, or the angle of the holder with respect to a fixed position may be adjusted.

[0021] Preferably, one or more of the lighting system 20 and the holder 30 are adjustable such that the position of the coated substrate 35 can be changed relative to the lighting system 20. For example, as shown in FIG. 2, the lighting system 20 may be adjustable in height or angle relative to the holder 30 to change the incident angle α of the light 25. For example, the lighting system 20 may be adjustable to allow for a shallower or steeper incident angle on the coated substrate 35 in order to control the size of the generated shadow. For example, a coated substrate having small surface defects may be illuminated at a larger incident angle to increase the size of the shadow, while a coated substrate having larger surface defects may be illuminated at a smaller incident angle to decrease the size of the shadow. By controlling the incident angle, the size of the shadow can be controlled to minimize the amount of overlap between adjacent surface defects.

[0022] Furthermore, the lighting system 20 may be adjustable to allow for rotation of the lighting system 20 around the coated substrate 35 such that the incident angle α is the same, but the light is directed at the coated substrate 35 from a different angle, for example, from the side rather than the front of the coated substrate 35. By allowing for different lighting angles, multiple images can be acquired to identify defects that may not be considered in a single image. For example, larger surface defects and small surface defects aligned with the light source may fall within the shadow of the larger surface defect. By rotating the light source relative to the coated substrate 35, multiple images are acquired and compared by an analysis unit 40 described below to identify all surface defects on the coated substrate. Furthermore, by acquiring multiple images at different angles, a more accurate quantification of the defects may be possible. For example, a wide but narrow defect may produce a large shadow at one angle but a small shadow at another angle. Thus, the acquisition and analysis of multiple images allows for a more accurate analysis of the surface defects. Such an analysis would be very difficult for a human observer attempting to perform a similar analysis.

[0023] System 100 further comprises an analysis unit 40 configured to transform images acquired by the imaging system 10. The analysis unit 40 further quantitatively analyzes the transformed images to identify and / or quantify the amount or percentage of defects within or on the coating of the coated substrate 35. The analysis unit 40 may comprise, for example, a computer, workstation, notebook computer, tablet computer, or smartphone. The analysis unit 40 may comprise an application or program adapted to transform and analyze images from the imaging system 10. The information acquired and / or generated by System 100 may be stored locally in the analysis unit 40, a server, cloud storage, or a media storage device.

[0024] The analysis unit 40 is preferably configured to transform the acquired image by processing the acquired image using an algorithm selected from image thresholding, wavelet transform, morphological transformation, color detection, pattern detection, contrast detection, clustering, and combinations thereof. The transformed image is then analyzed by the analysis unit 40 to identify and / or quantify defects within or on the coating of the coated substrate 35 and may provide an analysis output. Preferably, the output includes a value indicating the amount / percentage of defects, and / or an image or dataset identifying the location, size and / or amount / percentage of defects.

[0025] Preferably, the analysis unit 40 includes or is connected to a display including a graphical user interface (GUI). The GUI is preferably configured to display the output of the analysis unit 40. For example, the GUI may display a value that quantifies the amount or percentage of defects present in the coated substrate 35. Alternatively, the GUI may display a converted image that identifies the location, size, and / or amount / percentage of defects.

[0026] The method for identifying and quantifying defects in a coated substrate according to the present invention includes providing a system for acquiring and analyzing images; loading a substrate into a holder; illuminating the coated substrate using an illumination system; acquiring one or more images of the coated substrate using an imaging system; converting one or more images of the coated substrate using an analysis unit to provide one or more converted images; identifying and quantifying defects in the coated substrate based on one or more converted images; and providing an output.

[0027] Illuminating a coated substrate using an illumination system to identify and quantify defects based on the migration / secretion and / or extraction of one or more components within the coating of the coated substrate includes illuminating the coated substrate with infrared, ultraviolet, or both types of radiation. The image acquired by the imaging system includes infrared and / or ultraviolet images. Migration / secretion and / or extraction can be determined by the transformed image, which shows regions with different absorbances or reflectances at different wavelengths in the infrared or ultraviolet spectrum based on the migrating / secreted or extracted components. [Examples]

[0028] A system with a configuration similar to that shown in Figure 1 was prepared using a 5MP camera as the imaging system, an 8-channel multispectral light ring as the illumination system, and a customizable specimen holder for holding coated substrates for imaging and analysis. The 8-channel multispectral light ring was configured to emit channels consisting of ultraviolet, blue, green, yellow, red, far-red, infrared, and white light. The camera was configured to have the ability to acquire images in each of the channels emitted by the illumination system.

[0029] Next, all or a subset of the acquired images were transformed using an image analysis algorithm. The image analysis algorithm identified and quantified defects on the coating surface.

[0030] Smoothness test A coated substrate was prepared by applying a coating of paint to the substrate using a roller. The coated substrate was tested by human testers and by an image analysis system according to the present invention. In the case of human testers, smoothness was estimated based on observations of the roller pattern, surface uniformity, and surface roughness. Human testers provided subjective scores based on observations on a scale of 1 to 5.

[0031] The coated substrate was also analyzed by the process of the present invention. Images were acquired using the system described above. For one test, a color image was reconstructed from the resulting images from each of the optical channels, as shown in Figure 3. For another test, a texture image was reconstructed from four images illuminated with white light from the top, left, right, and bottom of the specimen, as shown in Figure 4. In both tests, the acquired images were processed and transformed by applying a wavelet transform to locate defects and quantify smoothing by constructing a linear regression between pixel variances. Quantifiable and reproducible values ​​for the amount of surface defects were provided by the image analysis process of the present invention.

[0032] Leveling Test A coated substrate was prepared by applying paint at a set spreading speed using a threaded steel rod to generate a coating with parallel ridges and valleys to simulate brushstrokes. The coated substrate was analyzed by a human tester and according to the process of the present invention. The human tester observed the coated substrate to determine the degree to which the applied coating flowed and formed a uniform film with a smooth surface, based on the test method of ASTM D 4062. An evaluation on a scale of 1 to 10 was provided.

[0033] Next, the coated substrate was analyzed using the process according to the present invention. In one test, a black and white image was generated using white light illuminating the test specimen from above, as shown in Figure 5. In another test, a textured image was reconstructed from four images illuminated with white light from the top, left, right, and bottom of the test specimen, as shown in Figure 6. In both tests, the acquired images were analyzed by an algorithm that included edge detection to detect defective areas and wavelet transform to provide a quantifiable leveling score.

Claims

1. A method for quantifying surface defects on a coated substrate, a) A system for acquiring and analyzing images, wherein the system is i) An imaging system for acquiring one or more images of the coated substrate, ii) A lighting system including a light source for illuminating the coated substrate, iii) A holder for holding the coated substrate in a position illuminated by the light source, iv) To provide a system comprising an analysis unit configured to convert one or more images and quantitatively analyze the one or more converted images for defects on the coated substrate, b) A coated substrate, wherein the coated substrate includes a coating formed on the surface of the substrate, and the coated substrate is loaded onto the holder. c) Illuminating the coated substrate using the illumination system, wherein illuminating the coated substrate includes illuminating the coated substrate at an incident angle of 15° to 85° with respect to a plane parallel to the surface of the coated substrate, thereby generating shadows of any defects on the surface of the coated substrate. d) Acquiring one or more images of the coated substrate using the imaging system, e) Converting one or more images of the coated substrate using the analysis unit, wherein the conversion of one or more images of the coated substrate includes processing one or more images of the coated substrate using an algorithm selected from the group consisting of image thresholding, wavelet transform, morphological transformation, color detection, pattern detection, clustering, and combinations thereof to provide one or more converted images, and quantifying the surface defects on the coated substrate based on the one or more converted images. F) To provide an output which includes a value that identifies the amount or percentage of the defects on the coated substrate, and / or a generated image showing the amount or percentage of the surface defects on the coated substrate, A method that includes this.

2. The method according to claim 1, wherein the light source is selected from a point light source and a directional light source.

3. The method according to any one of the imaging system and the holder is adjustable to change one or more parameters selected from the angle between the imaging system and the holder, the distance between the imaging system and the holder, and the relative position between the imaging system and the holder, and acquiring one or more images of the coated substrate using the imaging system includes adjusting the relative position between the imaging system and the holder to acquire two or more images of the coated substrate at different positions.

4. The method according to any one of the above claims, wherein one or more of the illumination system and the holder are adjustable to change one or more parameters selected from the angle between the illumination system and the holder, the distance between the illumination system and the holder, and the relative position between the illumination system and the holder, and acquiring one or more images of the coated substrate using the imaging system includes adjusting the relative position between the illumination system and the holder to acquire two or more images of the coated substrate at different positions.

5. The method according to claim 4, wherein the step of illuminating the coated substrate includes illuminating the coated substrate at a plurality of angles, and acquiring one or more images of the coated substrate includes acquiring one or more images at each of the plurality of angles.

6. The method according to claim 5, wherein the plurality of angles are different angles of incidence ranging from 15° to 85° with respect to a plane parallel to the surface of the coated substrate.

7. The method according to claim 5, wherein the plurality of angles are different angles formed by rotating the holder with respect to the light source, and the holder is rotated in a plane parallel to the surface of the coated substrate.

8. The method according to any one of the above claims, wherein the surface defects of the coated substrate are selected from smoothness defects and leveling defects.

9. The method according to any one of the above claims, further comprising displaying the output on a graphical user interface (GUI).

10. The method according to any one of the above claims, wherein the coating includes a paint.

Images