Quantitative image analysis method for evaluating color-based coating performance

Abstract

A method for quantifying defects on a coated substrate, the method comprising: a) providing a system for acquiring and analyzing images; b) loading the coated substrate on a holder, wherein the coated substrate comprises a coating layer formed on a surface of the substrate; c) illuminating the coated substrate with an illumination system; d) acquiring at least one image of the coated substrate with an imaging system; e) transforming the at least one image of the coated substrate with an analysis unit to provide at least one transformed image and quantifying defects on the coated substrate based on the at least one transformed image; and f) providing an output, wherein the output comprises a value identifying an amount or percentage of defects on the coated substrate, and / or a generated image showing the amount or percentage of defects on the coated substrate.

Description

TECHNICAL FIELD

[0001] The present invention relates generally to a method for quantitative analysis of images to determine color-based defects on coated substrates. BACKGROUND

[0002] The appearance of a coated substrate is one of the most important performance evaluation metrics used by consumers and researchers. Defects in a coated substrate can manifest themselves 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 can manifest as surface defects caused by shadows or appearance variations. Resistance to defects caused by, for example, water, corrosion, dirt, grease, and weathering can manifest as color variations in the coated substrate. Other defects in a coated substrate can be more difficult to observe visually, such as migration / exudation or extraction of components within the coated substrate.

[0003] Such defects in a coated substrate are typically observed or measured by a human. Due to the inherent difficulty in rating many of the defects in a coated substrate, the measurement of defects tends to be difficult to quantify accurately and / or reproducibly. Most defect measurements are highly subjective and at best measure the level of a defect on a simple scale, such as a numerical scale of 1 to 5, where a human observer assigns a value based on their interpretation of the surface of the coated substrate. Variations in the values assigned by one observer and the next are common, and the quantification of defects often results in rough estimates. Due to the subjective nature of the measurements, observations are often normalized within each study. Thus, data acquired from one study by human observation 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 No. US 2022 / 0082508 discloses a method for providing a coating composition related prediction procedure, the method comprising providing a database of qualitative and / or quantitative characterizations of coating surfaces, and training a machine learning model to develop a composition quality prediction procedure for predicting properties of a coating surface to be produced. However, the database of qualitative and / or quantitative characterizations is generated by manually identifying and labeling digital images, where the qualitative and / or quantitative characterization of the image is based on a scale having values assigned by a human observer. Thus, the database is compiled with data based on human observation.

[0005] There is a need for a method that can more accurately and reproducibly detect defects in a coated substrate to identify and quantify the defects. SUMMARY

[0006] The present invention relates to a method for quantifying defects on a coated substrate, the method comprising:

[0007] a) providing a system for acquiring and analyzing images, the system comprising:

[0008] i) an imaging system for acquiring one or more images of the coated substrate;

[0009] ii) an illumination system comprising at least one light source for illuminating the coated substrate;

[0010] iii) a holder for holding the coated substrate in a position to be illuminated by the at least one light source;

[0011] iv) an analysis unit configured to transform the one or more images and quantitatively analyze one or more transformed images to determine defects on the coated substrate,

[0012] b) loading a coated substrate on the holder, wherein the coated substrate comprises a coating formed on a surface of a substrate;

[0013] c) illuminating the coated substrate with the illumination system;

[0014] d) acquiring at least one image of the coated substrate with the imaging system;

[0015] e) transforming the at least one image of the coated substrate with the analysis unit, wherein transforming the at least one image of the coated substrate comprises processing the at least one image of the coated substrate with an algorithm selected from the group consisting of image thresholding, wavelet transform, morphological transform, color detection, pattern detection, clustering, and combinations thereof to provide at least one transformed image, and quantifying defects on the coated substrate based on the at least one transformed image; and

[0016] f) providing an output, wherein the output comprises a value identifying the amount or percentage of the defects on the coated substrate, and / or a generated image showing the amount or percentage of the defects on the coated substrate. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a schematic of a system for acquiring and analyzing images according to embodiments of the present invention.

[0018] Figure 2 is a schematic of the position of a light source relative to a coated substrate according to embodiments of the present invention.

[0019] Figure 3 is an image from a weathering test analyzed by an image analysis system according to embodiments of the present invention.

[0020] Figure 4 is an image from an early rainfastness test analyzed by the image analysis system according to embodiments of the application.

[0021] Figure 5 is an image from an adhesion test analyzed by the image analysis system according to embodiments of the application.

[0022] Figure 6 is an image from an application of hiding power test analyzed by the image analysis system according to embodiments of the application.

[0023] Figure 7 is an image from a home stain resistance test analyzed by the image analysis system according to embodiments of the application. DETAILED DESCRIPTION

[0024] The present inventors have discovered a method for reproducibly and accurately identifying and quantifying defects in a coated substrate.

[0025] As used herein, the term "coated substrate" refers to a substrate that includes a coating on its surface. The coating preferably has a thickness of less than 500 pm, more preferably less than 300 pm, and even more preferably less than 200 pm, and preferably a thickness of greater than 50 nm, more preferably greater than 100 nm, and even more preferably greater than 250 nm. Multilayer coatings can have greater thicknesses. The coated substrate can also include multiple layers, including for example a primer or base coat.

[0026] Preferably, the coated substrate includes a coating selected from polyurethane coatings, epoxy coatings, acrylic coatings (including for example acrylic, vinyl-acrylic, and styrene-acrylic coatings), alkyd resin coatings, and zinc-rich coatings. More preferably, the coated substrate comprises paint. The substrate can comprise metal, plastic, wood, glass, composite, fiberglass, paper, fabric, leather, or other substrates. For testing, it is preferred that the substrate have a flat or planar surface.

[0027] Defects in or on a coated substrate can be caused by a variety of different issues. Examples of defects include, but are not limited to, color defects, surface or texture defects, and migration / bleed or extraction defects.

[0028] Color defects may include stains from dirt, household stains (e.g., wine, pencil, lipstick, crayon, ink, marker, etc.), adhesion defects where the coating does not adhere adequately to the substrate, hidden defects where the coating allows the underlying substrate or sublayer to show through, grease resistance which assesses the penetration of oil through the coating, early rain resistance which tests the ability of the coating to resist rain washout shortly after the coating is applied and cured, and weathering resistance which tests the coating's ability to resist efflorescence formation and efflorescence.

[0029] Texture or surface defects can be indicated by smoothness or leveling problems where the coating may have an irregular or imperfect surface. Other texture or surface problems can include, for example, cracking or flaking.

[0030] Migration / secretion and / or extraction can occur when a component separates from other components or travels through a coating. Migration / secretion and / or extraction can occur due to material contact with the coating or incompatibility of components within the coating. For example, when a coating is in contact with water, surfactant leaching can occur when water-soluble materials leach into the surface of the coating. Other examples include the migration of adhesives or additives when affected by time, temperature, or environmental conditions. Although migration / secretion and / or extraction can result in visible defects, such defects are generally not easily visible. However, the present inventors have surprisingly discovered that infrared and / or ultraviolet spectroscopy can be used to identify and analyze migration / secretion and / or extraction defects. Substances that migrate / secrete or can be extracted can have different properties that can be observed in infrared and / or ultraviolet spectroscopy. For example, when analyzing surfactant leaching, the present inventors have found that the migrating component has a different thermal conductivity than the remaining components, making those defects easily identifiable in infrared spectroscopy.

[0031] For analyzing coated substrates, a system for analyzing and quantifying defects is provided. Figure 1 A schematic diagram of a system 100 for analyzing and quantifying defects is shown in FIG. The system 100 comprises an imaging system 10 , an illumination system 20 , a holder 30 for holding a coated substrate 35 , and an analyzing unit 40 .

[0032] The imaging system 10 is configured to acquire one or more images of the coated substrate 35. The imaging system 10 can be configured to acquire images in multiple channels, where each of the multiple channels comprises a predetermined range of wavelengths. For example, each of the channels can consist of wavelengths associated with a single color of light in the visible spectrum (e.g., red = 620 nm to 780 nm, orange = 585 nm to 620 nm, etc.). Alternatively, each channel can consist of a predetermined range of wavelengths (e.g., channel 1 = 400 nm to 500 nm, channel 2 = 500 nm to 600 nm, etc.). In yet another example, one channel can comprise the visible spectrum and a second channel can comprise the ultraviolet or infrared spectrum. In another example, one channel can comprise wavelengths in the near infrared range (800 nm to 1000 nm) and a second channel can comprise wavelengths longer than the infrared wavelengths (e.g., 1000 nm to 1500 nm).

[0033] To identify and quantify color-based defects, the imaging system can be configured to acquire images in the channel most relevant to the color of the defect. For example, when analyzing a coated substrate for early rainfastness testing, the substrate can be provided with a blue primer and coated with a white paint. When exposed to water, the defect will expose the underlying blue primer. The imaging system 10 can then be configured to acquire at least one image in a channel comprising blue wavelengths. A second channel can be used as a control.

[0034] The imaging system 10 can comprise, for example, a camera, a thermal imaging system, an ultraviolet imaging system, or an image sensor. The imaging system 10 can further comprise a filter for preferentially or selectively transmitting or blocking light of predetermined wavelengths, such as at least one channel of predetermined wavelengths. For example, when the imaging system 10 is configured to detect in the ultraviolet spectrum, a filter can be used to block channels of visible light. Alternatively, if ultraviolet light is used to cause a particular component to fluoresce, a filter can be used to selectively transmit the fluorescent wavelengths, and the imaging system can be configured to acquire images in a channel comprising the fluorescent wavelengths. Similarly, when using the infrared spectrum, a filter can be used to block visible wavelengths and allow transmission of infrared wavelengths.

[0035] The illumination system 20 includes at least one light source for illuminating the coated substrate 35. The illumination system 20 can be configured to emit radiation in the visible spectrum, the infrared spectrum, the ultraviolet spectrum, and combinations thereof. Preferably, the illumination system is configured to emit radiation in a wavelength associated with at least one of the plurality of channels used by the imaging system 10. For example, when detecting migration / bleeding and / or extraction defects, the illumination system 20 can be configured to emit radiation in the infrared spectrum and / or the ultraviolet spectrum, and the imaging system can be configured to acquire images in the same wavelength. The at least one light source can include a single light source or a plurality of light sources. When a single light source is used, the light source can include a ring light or a diffuser to provide uniform illumination to the coated substrate 35. When a plurality of light sources is used, the light sources can be arranged to provide uniform illumination. The plurality of light sources can also be controlled individually or within predetermined groups to control the illumination of the coated substrate 35. Preferably, the illumination system 20 is configured to allow adjustment of the intensity of the light, the angle of incidence on the coated substrate 35, or the wavelength of the emitted light.

[0036] 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 to be illuminated by the illumination system 20 when it is imaged. The holder 30 can be configured to hold a single coated substrate 35 or a plurality of coated substrates. The holder 30 can be stationary or adapted to allow automated loading / unloading of the sample.

[0037] Preferably, at least one of the imaging system 10 and the holder 30 is adjustable such that the position of the coated substrate 35 can be changed relative to the imaging system 10. For example, as shown in FIG. 1, the imaging system 10 can be mounted on an arm 101 attached to a vertical support 102. The arm 101 can 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 can be movable between more than one position. In another alternative, the holder 30 can be adjustable to raise or lower the holder 30 using a base 103, or the angle of the holder relative to a fixed position can be adjusted. Figure 1

[0038] Preferably, at least one of the illumination system 20 and the holder 30 is adjustable relative to the other such that the position of the coated substrate 35 can be changed relative to the illumination system 20. For example, the illumination system 20 can be adjustable in height or angle relative to the holder 30 to change the angle of the illumination as shown in FIG. 1. Alternatively, the holder 30 can be adjustable in height or angle relative to the illumination system 20. Figure 2 ​The illustrated light 25 has an angle of incidence a. For example, the illumination system 20 can be adjustable to allow for shallower or steeper angles of incidence on the coated substrate 35. Additionally, the illumination system 20 can be adjustable to allow the illumination system 20 to be rotated around the coated substrate 35 so that the angle of incidence a is the same but the light is directed onto the coated substrate 35 from a different angle, e.g., from the side of the coated substrate 35 rather than the front. To reduce the potential impact of external lighting, the system 100 can be covered or enclosed (not shown) so that only light from the illumination system 20 is used to acquire the images.

[0039] The system 100 further comprises an analysis unit 40 configured to transform the images acquired by the imaging system 10 into transformed images. The analysis unit 40 further quantitatively analyzes the transformed images to identify and / or quantify the amount or percentage of defects in or on the coating of the coated substrate 35. The analysis unit 40 can comprise, for example, a computer, a workstation, a notebook computer, a tablet computer, or a smartphone. The analysis unit 40 can comprise an application or program adapted to transform and analyze the images from the imaging system 10. The information obtained and / or generated by the system 100 can be stored locally within the analysis unit 40, a server, a cloud storage, or a media storage device.

[0040] The analysis unit 40 is preferably configured to transform the acquired images by processing the acquired images with an algorithm selected from the group consisting of image thresholding, wavelet transform, morphological transform, color detection, pattern detection, contrast detection, clustering, and combinations thereof. The transformed images can then be analyzed by the analysis unit 40 to identify and / or quantify the defects in or on the coating of the coated substrate 35 and provide an output of the analysis. Preferably, the output comprises a value that symbolizes the number / percentage of defects, and / or an image or data set that identifies the location, size, and / or number / percentage of defects.

[0041] Preferably, the analysis unit 40 comprises or is connected to a display comprising a graphical user interface (GUI). The GUI is preferably configured to display the output of the analysis unit 40. For example, the GUI can display a value that quantifies the amount or percentage of defects present in the coated substrate 35. Alternatively, the GUI can display a transformed image that identifies the location, size, and / or number / percentage of defects.

[0042] A method of 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 on a holder; illuminating the coated substrate with an illumination system; acquiring at least one image of the coated substrate with an imaging system; transforming the at least one image of the coated substrate with an analysis unit to provide at least one transformed image; and identifying and quantifying defects on the coated substrate based on the at least one transformed image; and providing an output.

[0043] Example

[0044] A system with a similar arrangement as shown in FIG. 1 is prepared using a 5MP camera as the imaging system, an 8-channel multi-spectral light ring as the illumination system, and a customizable sample holder for holding a coated substrate for imaging and analysis. The 8-channel multi-spectral light ring is configured to emit in channels consisting of ultraviolet light, blue light, green light, yellow light, red light, far infrared light, infrared light, and white light. The camera is configured to have the ability to acquire images in each of the channels emitted by the illumination system. Figure 1

[0045] Then, all or a subset of the acquired images are transformed using an image analysis algorithm that transforms the acquired images. The image analysis algorithm identifies and quantifies defects in the coated surface.

[0046] Weathering test (predictive example)

[0047] To test the weather resistance of the primer, a coated substrate is prepared by coating a substrate with a primer and a topcoat. The bottom of the coated substrate will be in contact with an alkaline liquid to determine if the primer can block the penetration of the alkaline liquid.

[0048] The sample will be analyzed by human observation and by the system of the present invention. Figure 3 A representative image to be analyzed is shown, where the expected light color areas show the areas of corrosion, i.e., areas where the coating failed to block the migration of the alkaline solution, and the expected dark color areas show the areas of no corrosion, i.e., areas where the coating was effective. The human observation is performed by estimating the areas where a color change is observable. The analysis by the system of the present invention is quantifiable and reproducible.

[0049] Early rainfastness test (predictive example)

[0050] To test the water resistance of a wet paint that is cured for 20 minutes, a substrate with a blue primer will be coated with a white paint topcoat. The topcoat will be cured for 20 minutes, after which water will be applied to the top of the coated substrate for a predetermined period of time. As the water runs off the coated substrate, it is expected that portions of the white topcoat will flake off, revealing the underlying blue primer.​Figure 4 Images of coated substrates after similar water resistance testing are shown.

[0051] Then, the sample will be analyzed manually and analyzed by the system of the present invention. Human observation is used to estimate the amount or percentage of blue color that is displayed through the white surface layer. The sample is also analyzed by the system of the present invention, which is expected to provide reproducible and quantifiable results.

[0052] Adhesion test

[0053] A paint sample is applied to a substrate and cured. A crosshatch tool is used to mark a set of lines. Adhesion tape is applied and pulled away from the crosshatch area. The adhesion of the paint is quantified by a human tester who counts the number of grid cells where the paint remains in the crosshatch area. The system of the present invention also uses frequency space to analyze the image of the sample ( Figure 5 ) to locate the area and quantify the percentage of paint remaining.

[0054] The system of the present invention is also able to quantify the adhesion of a clearcoat based on the light distribution used.It is difficult for a human tester to observe a clearcoat accurately and reproducibly.

[0055] Application hiding power test

[0056] The paint sample was applied to a Leneta chart, i.e., a chart with a combination of black and white areas, at a natural spreading rate. After the paint dried, the painted chart was analyzed by a human tester who provided a rating of 1 to 5 based on how much of the underlying black area was visible. An image of the same sample was analyzed using the system of the present invention ( Figure 6 ), the system uses wavelet transform to locate regions and quantifies coverage by constructing a linear regression between pixel intensity and manual ratings. Compared to human observation, the analysis performed by the system of the present invention is more quantitative and reproducible.

[0057] Stain resistance test

[0058] The stain repellency test is performed by first applying a selected stain to the painted substrate. Possible stain types include household stains such as pencil, wine, crayon, coffee, narrow and wide marker stains, and dirt. The sample is then washed or scrubbed with a sponge for a defined number of cycles. The color change before and after washing is then used to quantify the paint's stain repellency. Figure 7 Images of painted substrates stained with various materials including lipstick, pencil, and crayon are shown.

Claims

1. A method for quantifying defects on a coated substrate, the method comprising: a) providing a system for acquiring and analyzing images, the system comprising i) an imaging system for acquiring one or more images of the coated substrate; ii) an illumination system comprising at least one light source for illuminating the coated substrate; iii) a holder for holding the coated substrate in a position to be illuminated by the at least one light source; iv) an analysis unit configured to transform the one or more images and quantitatively analyze one or more transformed images to determine defects on the coated substrate, b) loading a coated substrate on the holder, wherein the coated substrate comprises a coating formed on a surface of a substrate; c) illuminating the coated substrate with the illumination system; d) acquiring at least one image of the coated substrate with the imaging system; e) transforming the at least one image of the coated substrate with the analysis unit, wherein transforming the at least one image of the coated substrate comprises processing the at least one image of the coated substrate with an algorithm selected from the group consisting of image thresholding, wavelet transform, morphological transform, color detection, pattern detection, clustering, and combinations thereof to provide at least one transformed image, and quantifying defects on the coated substrate based on the at least one transformed image; and f) providing an output, wherein the output comprises a value identifying the amount or percentage of the defects on the coated substrate, and / or a generated image showing the amount or percentage of the defects on the coated substrate.

2. The method of claim 1, wherein the imaging system is configured to acquire images at a plurality of channels, wherein each channel of the plurality of channels comprises a predetermined range of wavelengths, wherein the plurality of channels comprises channels selected from at least one of a visible spectrum, an infrared spectrum, and an ultraviolet spectrum.

3. The method of claim 2, acquiring at least one image of the coated substrate comprises acquiring at least one visible light image in a channel in the visible spectrum and acquiring at least one infrared image in a channel in the infrared spectrum.

4. The method of claim 3, wherein transforming the at least one image of the coated substrate comprises transforming the at least one visible light image and transforming the at least one infrared image, and quantifying defects comprises identifying a maximum amount or percentage of defects in at least one transformed visible light image and at least one transformed infrared image to determine the amount or percentage of the defects on the coated substrate.

5. The method of any of the preceding claims, wherein at least one of the imaging system and the holder is adjustable to change at least one parameter selected from the group consisting of an angle between the imaging system and the holder, a distance between the imaging system and the holder, and a relative position between the imaging system and the holder, and acquiring at least one image of the coated substrate with the imaging system comprises adjusting the relative position between the imaging system and the holder to acquire at least two images of the coated substrate at different positions.

6. The method of any of the preceding claims, wherein at least one of the illumination system and the holder is adjustable to change at least one parameter selected from the group consisting of an angle between the illumination system and the holder, a distance between the illumination system and the holder, and a relative position between the illumination system and the holder, and acquiring at least one image of the coated substrate with the imaging system comprises adjusting the relative position between the illumination system and the holder to acquire at least two images of the coated substrate at different positions.

7. The method of any of the preceding claims, wherein the defects in the coated substrate are color-based defects.

8. The method of claim 7, wherein the defects are selected from the group consisting of stains, adhesion failures, hiding power, dynamic sensitivity, surfactant leaching, weathering resistance, and combinations thereof.

9. The method of any of the preceding claims, wherein the at least one light source comprises a ring light or a diffuse light source.

10. The method of any of the preceding claims, wherein the at least one light source emits light in at least one spectrum selected from the group consisting of the visible spectrum, the infrared spectrum, and the ultraviolet spectrum.

11. The method of any of the preceding claims, wherein the imaging system further comprises at least one optical filter, wherein the at least one optical filter preferentially transmits or preferentially blocks light at a wavelength in one of the plurality of channels.

12. The method of any of the preceding claims, further comprising displaying the output on a graphical user interface (GUI).

13. The method of any of the preceding claims, wherein the coating comprises paint.

Images