CORROSION DETERMINATION

FIELD OF THE INVENTION

The present invention relates generally to a method for determining presence of corrosion on a substrate. More particularly, the present invention relates to a method for analyzing visual inspection image of a substrate for corrosion appearance detection.

BACKGROUND OF THE INVENTION

Salt spray test is a standardized and well-known corrosion testing method which is necessary to assess and evaluate corrosion resistance properties of a material and/or surface coating. The salt spray test is conducted by stimulating a corrosive environment created by a dense salt water mist where a substrate is exposed for a predetermined period of time. The appearance of corrosion on the substrate surface is evaluated via frequent interim inspection throughout the salt spray test, where one or more images of the substrate surface will be captured during each inspection interval. The captured images are examined by unaided eyes to check for corrosion on the substrate surface. Test result from visual inspection is commonly qualitative, in which the corrosion appearance is determined by a “pass/fail assessment”. Sometimes, the test result may be quantified by measuring percentage of corrosion present on the substrate surface.

Few shortcomings have arose from the conventional method of analyzing visual inspection image for determining presence of corrosion on a substrate. First, the visual inspection acceptance criteria from the test result could be unreliable and questionable due to inconsistent image capturing parameters, such as orientation and alignment of the substrate for each inspection interval (i.e. the captured images of a test substrate may offset in position) and contrast between initial inspection image and subsequent interim inspection image. Furthermore, there is high complexity and repeatability in process of preparing set-up for imaging substrate with unusual shapes and high metallic surfaces such as screw thread, nut head and wire-frame. Also, process of quantifying corrosion defect ratio on the substrate surface could be tedious and laborious as it is typically performed by manual calculation based on tracing on grid paper.

There have been a number of solutions provided for efficiently analyzing visual inspection image of the substrate for corrosion determination and few of them are discussed below.

U.S. Patent No. 9,582,899 B2 provides a system and method of providing real time digitally enhanced imaging for prediction, application, and inspection of coatings. According to the prior art, a real-time image is acquired and subsequently being processed to enhance digital imaging data. The enhanced digital imaging data is then digitally processed to quantify a level of surface properties such as contamination on substrate or substrate variations. The method also provides a visual representation of level of surface contamination as well a visual representation of the enhanced digital imaging data to show the surface of the substrate with most of the contamination. The prior art enables a user to discern variations beyond that which can be discerned by observing with the naked eye, such as variations in the thickness of a self-inspecting coating being applied to the substrate.

International Publication No. WO 03/083460 A1 provides a system and method of performing automated inspection of a surface followed by processing inspection data acquired from the surface. According to the prior art, a sequence of camera control parameters are automatically applied to acquire a sequence of images of a surface of interest, subsequently the sequence of images are automatically processed to evaluate the surface of interest. The evaluation is performed by introducing the processed images to a feature detection phase to distinguish corrosion which may exhibit characteristic edge patterns from other image content. The prior art allows the inspection and processing process to be performed with limited or no operator involvement and also to maintain a high level of consistency between each inspection and between each processing of inspection data across multiple inspections of the surface.

“Detection and Quantitative Assessment of Corrosion on Pipelines through Image Analysis” by Bondada, V., et al. (2018) provides a method for detection and quantification of corrosion on a pipe using digital image processing. Based on the prior art, detection is carried out by deliberately capturing only surface of the pipe, followed by image processing including image filtering and transformation of colour space. Then, a mean saturation value of all pixels in the processed image is computed and a threshold is applied on the computed mean saturation value for corrosion detection. Quantification is then carried out by measuring corrosion area, damaged area and by locating centers of densely corroded regions in the image. Pipeline corrosion is identified and damage thereof is quantified in order to assist management in maintenance of pipeline integrity to prioritize their remedial measures.

The aforesaid documents and other similar solutions may strive to provide an efficient way for analyzing visual inspection image of a substrate in order to detect corrosion appearance; however, they still have a number of limitations and shortcomings such as, but not limited to, lacking of consistency in visual inspection image quality which may affect accuracy of the test results, particularly discrepancy in position and alignment of the substrate during image acquisition at each inspection interval. Also, application of the existing methods may be limited to the substrate with specific dimension and outline, in which the existing methods may not be applicable for other type of substrates with different sizes and outlines. Accordingly, there remains a need in the prior art to have a method of analyzing visual inspection image of a test substrate for corrosion determination, which overcomes the aforesaid shortcomings.

SUMMARY OF THE INVENTION

The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. Its sole purpose is to present some concepts of the invention in a simplified form as a prelude to the more detailed description that is presented later.

An objective of the present invention is to provide a method of analyzing visual inspection image of a substrate for detecting corrosion appearance on the substrate and for visually quantifying the corrosion level. It is an objective of the present invention to provide a method of analyzing visual inspection image of a substrate for corrosion determination which may efficiently position and align the substrate to ensure consistency in image quality at each inspection interval.

Also, it is an objective of the present invention to provide a method of analyzing visual inspection image of a substrate for corrosion determination which is independent on the size and outline of a substrate, hence applicable to various substrates with different dimension.

It is further an objective of the present invention to create a shadow image as an alignment template that is derived from initial inspection image to reduce alignment variation in each visual inspection image. Accordingly, these objectives may be achieved by following the teachings of the present invention. The present invention provides a method of analyzing visual inspection image of a substrate for corrosion determination.

The method comprises the steps of obtaining a plurality of processed images of the substrate at a different time interval, wherein the plurality of processed images comprising a plurality of pixels; selecting at least two processed images and comparing thereof, pixel by pixel, according to a rule; copying pixel that meets the rule to a blank image. The blank image that filled with copied pixels forms a test image for corrosion determination. Further, each of the processed images is obtained by the steps of acquiring a first image of the substrate; processing the first image according to a parameter to obtain a shadow image as template; overlaying and aligning the substrate on the shadow image at a time interval to acquire a second image; and processing the second image according to the parameter. The foregoing and other objects, features, aspects and advantages of the present invention will become better understood from a careful reading of a detailed description provided herein below with appropriate reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

A more complete appreciation of the invention and many of the attendant advantages thereof will be readily as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:

Figure 1 is a flow diagram of a method of analyzing visual inspection image of a substrate for corrosion determination in accordance to an embodiment of the present invention;

Figure 2 is a flow diagram of acquiring a first image of a substrate and processing thereof to obtain a shadow image in respect of the method of analyzing visual inspection image of the substrate for corrosion determination in accordance to a preferred embodiment of the present invention ;

Figure 3 is a flow diagram of acquiring a subsequent image of a substrate by overlaying and aligning the substrate on a shadow image at a time interval, and processing the image according to a parameter in respect of the method of analyzing visual inspection image of the substrate for corrosion determination in accordance to a preferred embodiment of the present invention;

Figures 4 is a flow diagram of selecting and comparing at least two processed images, pixel by pixel, according to a rule, and copying pixel that meets the rule to a blank image in respect of the method of analyzing visual inspection image of a substrate for corrosion determination in accordance to a preferred embodiment of the present invention;

Figures 5 is a flow diagram of conducting a corrosion determination using a test image formed by copying pixels that meet the rule to a blank image in respect of the method of analyzing visual inspection image of a substrate for corrosion determination in accordance to a preferred embodiment of the present invention; Figures 6 illustrates examples of corrosion determination in accordance to a preferred embodiment of the present invention; and

Figure 7 illustrates an example embodiment of (a) a shadow image created from a first image which has been processed; and (b) an image of a substrate aligned with the shadow image acquired at an inspection interval.

It is noted that the drawings may not be to scale. The drawings are intended to depict only typical aspects of the invention, and therefore should not be considered as limiting the scope of the invention. In the drawings, like numberings represent like elements between the drawings.

DETAILED DESCRIPTION OF THE INVENTION

While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described, and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents and alternatives falling within the scope of the present invention as defined by the appended claim. As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense (i.e. meaning must). Further, the words "a" or "an" mean "at least one" and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein is solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles and the like is included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.

In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element or group of elements with transitional phrases "consisting of", "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa. The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only, and are not intended to limit the scope of the claims. In addition, a number of materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary, and are not intended to limit the scope of the invention.

Referring to the drawings, the invention will now be described in more detail. Figure 1 is a flow diagram showing a method (100) of analyzing visual inspection image of a substrate for corrosion determination in accordance to an embodiment of the present invention. The method (100) starts off with obtaining a plurality of processed images of a substrate at a different time interval (120). Then, the process is continued by selecting at least two processed images from a plurality of processed images and comparing thereof, pixel by pixel, according to a rule (140). Subsequently, a test image is formed by copying all the pixels that meet the rule to a blank image (160), followed by performing a corrosion determination using the test image (180).

In accordance to an embodiment of the present invention, the substrate may comprise a metal material, coating or any material for corrosion determination, such as, but not limited to the substrate which undergoes corrosion testing.

In accordance to an embodiment of the present invention, the corrosion includes white rust, pit, red rust and any contamination of the substrate surface that may appear during or upon corrosion testing.

In accordance to an embodiment of the present invention, the plurality of images may be processed using an image processing software.

In accordance to an embodiment of the present invention, each of the processed images is obtained (120) by the steps of acquiring a first image of the substrate (121 a), processing the first image (121 b) to obtain a shadow image as a template, overlaying and aligning the substrate on the shadow image at a time interval (122a) to acquire subsequent images (122b), followed by processing thereof (122c).

Figure 2 shows the process of acquiring the first image of the substrate (121 a) and processing thereof (121 b) to obtain the shadow image in accordance to a preferred embodiment of the present invention. The process is initiated by acquiring the first image of the substrate (121 a) using an imaging device during initial inspection. The substrate is placed in a closed environment with a homogenous light intensity, for instance, a box studio equipped with a light source. The imaging device is then set to localize area to be targeted on the substrate. The imaging device is further adjusted to optimize optical zoom level in order to capture a clear image. The first image of the substrate in the initial inspection is then captured, wherein the first image comprises a plurality of pixels. In accordance to an embodiment of the present invention, the imaging device is, but not limited to, a digital imaging device. The digital imaging device may be an electronic camera or a scanner.

In accordance to an embodiment of the present invention, the first image of the substrate is acquired (121 a) by imaging a fresh substrate as a control or standard sample, in which substrate does not have major defect or damage.

Upon acquiring the first image of the substrate (121 a), a copy of the first image is stored in memory, such as a computer memory device including a plurality of default data such as date taken and zoom level. Following that, the first image is processed according to a parameter (121 b) to obtain the shadow image, wherein the parameter comprises colour value of a pixel. More particular, the first image is processed (121 b) by converting image background to transparent according to the parameter to produce a first processed image, wherein the colour value of each pixel is defined as 0. The shadow image is then derived from the first processed image by displaying the first processed image with adjustable transparency level as an alignment template for subsequent inspection imaging of the same substrate or a different substrate with a similar outline and dimension. A copy of the shadow image is then stored as alignment template in memory with a plurality of default data including pre-test imaging zoom level.

In accordance to an embodiment of the present invention, the colour value of each pixel is preferably comprised of a set of colour values including a set of red, blue and green (RGB) colour values. In a further embodiment of the present invention, the colour value is preferably comprised of alpha value, whereby the alpha value indicating transparency.

In accordance to another embodiment of the present invention, the first image may be further processed from a colour image into a grayscale image for any substrate which comprises metal surfaces.

Figure 3 is a flow diagram showing the process of acquiring a subsequent image of the substrate (122b) by overlaying and aligning the substrate on the shadow image (122a) at a time interval and processing the image according to the parameter (122c) in accordance to a preferred embodiment of the present invention.

Upon obtaining the shadow image, the substrate is configured to undergo a corrosion testing and the substrate is inspected for corrosion appearance detection at a time interval by taking images of the substrate surface. During each inspection interval, the shadow image is firstly de-compressed and loaded from memory to be displayed as alignment template inside the box studio, which may be projected through an opening of the box studio. At the same time, the substrate is arranged in the box studio and the zoom level of the imaging device is adjusted to the same imaging zoom level when acquiring the first image. The substrate is positioned to overlay and align with outline of the shadow image (122a), followed by acquiring a second image of the substrate (122b) using the imaging device, wherein the second image comprises a plurality of pixels. Next, the second image is processed by converting image background to transparent according to the parameter (122c) to obtain a second processed image, wherein the parameter comprises colour value of a pixel which is defined as 0. A copy of the second processed image is then stored into memory for further analysis, for instance, corrosion determination. The process of acquiring and processing image of the substrate is repeated at subsequent inspection interval.

In accordance to another embodiment of the present invention, the plurality of processed images may be further processed from a plurality of colour images into a plurality of grayscale images for any substrate which comprises metal surfaces. Figures 4 shows the step of selecting and comparing at least two processed images, pixel by pixel, according to the rule (140), followed by the step of copying pixel that meets the rule to the blank image (160) in accordance to a preferred embodiment of the present invention. A plurality of processed images of the substrate from each time interval are acquired (120) to proceed with pixel comparison process in order to identify and determine colour changes in the plurality of processed images of the substrate.

At least two processed images are selected and compared for corrosion determination, in which one of the exemplary is shown in Fig. 6. A new blank image is created for comparing the two processed images, pixel by pixel, according to the rule (140), wherein the rule is defined as difference in colour value between each pixel of the at least two processed images exceeds a threshold value, preferably the colour value is comprised of, but not limited to the RGB colour values. If the difference in colour value between each pixel of the two selected processed images exceeds the threshold value, that pixel is selected and copied to another new blank image (160) with same position as the current processed image. A test image is formed upon completing the step of copying all pixels that meet the rule to the blank image (160). In accordance to an embodiment of the present invention, the processed images may comprise an active area which is used for pixel comparison, wherein the active area is defined as the area of the substrate in the processed image which was not highlighted during image processing process. In accordance to an embodiment of the present invention, the threshold value may be a variable threshold value, which is configured based on a plurality of factors, including set-up condition, lighting intensity and types of substrate. Preferably, the threshold value is 10% of maximum RGB colour values, in which the maximum RGB colour values are 255. The preferred threshold value may be further adjusted based on the plurality of factors.

Figures 5 is a flow diagram showing the process of conducting a corrosion determination (180) using the test image formed by copying pixels that meet the rule to the blank image (160) in accordance to a preferred embodiment of the present invention. The blank image that filled with a plurality of copied pixels forms the test image for corrosion determination (180) upon copying the plurality of pixels which meet the rule to the blank image (160).

In accordance to an embodiment of the present invention, the corrosion determination is conducted by comparing colour value of every pixel to a set of predetermined range, preferably comparing the RGB colour values of every pixel. Any pixel that does not fall within the set of predetermined range is removed from the test image; while the remaining pixels are compared to the total pixels of first image for corrosion percentage calculation. In accordance to an embodiment of the present invention, a pixel that falls within the set of predetermined range is identified as sign of corrosion, wherein the set of predetermined range includes a first range for red colour value ranging from 145 to 221 ; a second range for blue colour value ranging from 10 to 20; and a third range for green colour value ranging from 56 to 74. The predetermined range may be defined in reference to the natural RGB colour values for red rust, as per theoretical and experimental data. Fine adjustment on the predetermined range is required if necessary based on visual evaluation when performing corrosion determination.

In another embodiment of the present invention, a grayscale image may have a different predetermined range as compared to the colour image. Preferably, the predetermined range of the grayscale image is defined as RGB colour values of a pixel less than 100.

There are few examples of corrosion determination as shown in Figure 6, including analysis of time effect on corrosion appearance, analysis on corrosion growth and analysis on substrate-to-substrate comparison. The analysis of time effect on corrosion appearance can be conducted by comparing a plurality of processed image of the substrate to the first processed image acquired from initial inspection, wherein the plurality of processed image are acquired at a different time interval; while the analysis on corrosion growth is conducted by comparing a plurality of processed images of the substrate at a plurality of different time intervals. Further, in the analysis on substrate-to-substrate comparison, a plurality of processed images that acquired from different substrates at a time interval is selected for corrosion comparison analysis of the different substrates.

Figure 7(a) illustrates an example embodiment of the shadow image created from the first image which has been processed (121 b), wherein the background of the first image was converted to transparent; while figure 7(b) illustrates an example embodiment of an image of a substrate aligned with the shadow image acquired at the inspection interval (122a). The alignment of the substrate with the shadow image allows consistency in imaging parameters, thereby improving the quality of corrosion inspection results. The above-mentioned system and method overcomes the problems and shortcomings of the existing system and provides a number of advantages over them. It is therefore an advantage of the present invention of having an alignment template cloned from initial inspection image for ensuring a consistent image quality during image acquisition process of a substrate at every time interval. Also, the process of forming the alignment template is configured to be applicable for various sizes and outlines of different substrates.

Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the embodiments shown along with the accompanying drawings but is to be providing broadest scope of consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claim.