Automated image consolidation in radiographic imaging for non-destructive inspection

Abstract

Data characterizing, a first set of radiographic images of a region of interest and a second set of radiographic images of a reference region, are received. The first set of radiographic images is captured at multiple circumferential sectors of a cylinder. Each radiographic image of the second set correlates to a respective radiographic image of the first set. Each radiographic image of the second set is subtracted from the respective radiographic image of the first set to produce a third set of radiographic images of a feature region. Data characterizing one or more consolidated radiographic images of the feature region is then provided.

Description

AUTOMATED IMAGE CONSOLIDATION IN RADIOGRAPHIC IMAGING FOR NONDESTRUCTIVE INSPECTIONTECHNICAL FIELD

[0001] The subject matter described herein relates to radiographic image acquisition, processing, and consolidation.BACKGROUND

[0002] Radiographic imaging provides detailed internal views of objects without causing damage to the objects. Radiographic imaging, such as X-ray imaging, is widely used across industries for assessing the structural integrity of objects in non-destructive testing and inspection of objects (e.g., cylinders, pipes, and other geometries requiring circumferential coverage). Currently, X-ray inspection of circumferential welds on pipes is performed using X-ray films, computed radiography plates, or flat panel detectors. Observing the full view of the inspection covering the whole circumference of the object is desired to ensure complete coverage and facilitate thorough analysis during inspection. However, individual radiographic images captured by existing systems are typically confined to specific sectors of the object, making it challenging to obtain a comprehensive view of the entire circumference.SUMMARY

[0003] This disclosure relates to automated image consolidation in radiographic imaging for non-destructive inspection.

[0004] An example implementation of the subject matter described within this disclosure is a method with the following features. Data characterizing, a first set of radiographic images of a region of interest, and a second set of radiographic images of a reference region, are received. The first set of radiographic images are captured at multiple circumferential sectors of a cylinder. Each radiographic image of the second set correlates to a respective radiographic image of the first set. Each radiographic image of the second set is subtracted from the respective radiographic image of the first set. A third set of radiographic images of a feature region is thereby produced.Data characterizing one or more consolidated radiographic images of the feature region is then provided.

[0005] The disclosed method can be implemented in a variety of ways. For example, within a system that includes at least one data processor and a non-transitory memory storing instructions for the processor to perform aspects of the method. Alternatively or in addition, the method can be in included non-transitory computer readable memory storing the method as instructions which, when executed by at least one data processor forming part of at least one computing system, causes the at least one data processor to perform operations of the method.

[0006] Aspects of the example method, that can be combined with the example method alone or in combination with other aspects, can include the following. Data characterizing physical characteristics of the cylinder is received. The second set of radiographic images of the reference region is rendered based on the physical characteristics of the cylinder.

[0007] Aspects of the example method, that can be combined with the example method alone or in combination with other aspects, can include the following. A range of pixel intensity values across each radiographic image of the third set is reduced. In other words, an intensity curve of each radiographic image of the third set is flattened. Each radiographic image of the third set has a higher contrast compared to each radiographic image of the first set. Each radiographic image of the third set has an improved signal-to-noise ratio (SNR) compared to each radiographic image of the first set.

[0008] Aspects of the example method, that can be combined with the example method alone or in combination with other aspects, can include the following. Providing the consolidated radiographic image includes following steps. A dynamic range of each radiographic image of the third set is increased. At least an alignment feature identified in overlapping regions of adjacent radiographic images of the third set. Transformation parameters are determined for each radiographic image of the third set based on the at least an alignment feature. Additionally, each radiographic image of the third set is transformed according to the transformation parameters. The adjacent radiographic images of the third set are aligned based on the at least an alignment feature to produce a single consolidated radiographic image. In some implementations, the at least an alignment feature includes an identifiable marker adjacent to the region of interest.

[0009] Aspects of the example method, that can be combined with the example method alone or in combination with other aspects, can include the following.

[0010] Aspects of the example method, that can be combined with the example method alone or in combination with other methods, can include the following. Data characterizing a three-dimensional (3D) cylinder model is further received. A transform of the one or more consolidated radiographic images is determined based on the physical characteristics of the cylinder. The transform includes positional alignments of the one or more consolidated radiographic images to overlay the images onto the 3D cylinder model for visualizing the feature region.BRIEF DESCRIPTION OF DRAWINGS

[0011] These and other features will be more readily understood from the following detailed description taken in conjunction with the accompanying drawings.

[0012] FIG. 1 is an example flexible detector that can be used to scan a cylinder;

[0013] FIG. 2 A is an example radiographic image from the first set of radiographic images captured by the flexible detector as illustrated in FIG. 1;

[0014] FIG. 2B is an example radiographic image from the third set of radiographic images;

[0015] FIG. 2C is the example radiographic image from the third set of radiographic images as illustrated in FIG. 2B subjective to an image enhancement process;

[0016] FIG. 3 is an example of a consolidated radiographic image;

[0017] FIG. 4 is a flowchart of an example method that can be used with aspects of this disclosure;

[0018] FIG. 5 is a block diagram of an example controller that can be used with aspects of this disclosure.DETAILED DESCRIPTION

[0019] Certain implementations will now be described to provide an overall understanding of the principles of the structure, function, manufacture, and use of the devicesand methods disclosed herein. One or more examples of these implementations are illustrated in the accompanying drawings. Those skilled in the art will understand that the devices and methods specifically described herein and illustrated in the accompanying drawings are nonlimiting implementations and that the scope of the present invention is defined solely by the claims. The features illustrated or described in connection with one implementation may be combined with the features of other implementations. Such modifications and variations are intended to be included within the scope of the present invention.

[0020] Further, in the present disclosure, like-named components of the implementations generally have similar features, and thus within a particular implementation each feature of each like-named component is not necessarily fully elaborated upon. Additionally, to the extent that linear or circular dimensions are used in the description of the disclosed systems, devices, and methods, such dimensions are not intended to limit the types of shapes that can be used in conjunction with such systems, devices, and methods. A person skilled in the art will recognize that an equivalent to such linear and circular dimensions can easily be determined for any geometric shape. Sizes and shapes of the systems and devices, and the components thereof, can depend at least on the anatomy of the subject in which the systems and devices will be used, the size and shape of components with which the systems and devices will be used, and the methods and procedures in which the systems and devices will be used.

[0021] Radiographic imaging is typically conducted in non-destructive testing and inspection operations by providing detail internal views of objects without causing damage. When inspecting cylindrical structures, such as a pipe, radiographic imaging is conducted in multiple circumferential sectors. However, conventional methods face challenges in obtaining consolidated images that cover the entire region of interest e.g., pipe welds or similar features. This limitation can hinder the ability to accurately detect and analyze defects.

[0022] The method and system described herein focus on the automated stitching of radiographic images of cylindrical objects. Data characterizing, a first set of radiographic images of a region of interest and a second set of radiographic images of a reference region, are received. The first set of radiographic images is captured at various circumferential sectors or a cylinder. A third set of radiographic images is produced by subtracting each radiographic image of the second set from the respective radiographic image of the first set. Each radiographic imageof the third set highlights only the feature region. The third set of radiographic images is then consolidated into one or more consolidated radiographic images.

[0023] FIG. 4 illustrates a flowchart of an example method 400 that can be used with aspects of this disclosure. The method 400 can be applied to cylindrical objects using a flexible detector 100. In some implementations, the automated stitching is coupled with a flexible detector. For example. FIG. 1 illustrates an example flexible detector 100 mounted on a cylinder 102. In some implementations, the cylinder 102 includes a pipe, saft, or other rotationally symmetric structures. In some implementations, the cylinder 102 need not be rotationally symmetric. Objects of other shapes can be similarly scanned without departing from this disclosure.

[0024] As shown in FIG. 1, the flexible detector 100 can conform to the geometry of the cylinder 102, capturing radiographic images with reduced distortion. The flexible detector 100 includes a detector 104, a radiation source 106, and a controller 108 communicatively coupled to both the detector 104 and the radiation source 106. In some implementations, the detector 104 is positioned along a portion of the circumference of the cylinder 102. In some instances, the detector 104 is an X-ray detector constructed from a pliable material that allows it to conform to the cylindrical outer surface and be in close contact with cylinder 102. The radiation source 106 is positioned opposite the detector 104. The controller 108 can manage the operation of the radiation source 106. For example, radiation source 106 emits radiation beams 110, such as X-rays, towards the detector 104 upon instructed by the controller 108. In this example, the intensity and duration of the radiation beams 110 are controlled by the controller 108. The radiation beams 110 passes through the cylinder 102. In some cases, variations in material density within the cylinder 102 attenuate the radiation beams 110. The radiation beams 110 are captured by the detector 104 and converted into radiographic images received by the controller 108. Details on the controller are discussed throughout this disclosure.

[0025] Returning to FIG. 4, at 402, data characterizing a first set of radiographic images of a region of interest 112 and a second set of radiographic images of a reference region 114, are received, for example, by the controller 108. The first set of radiographic images is captured at multiple circumferential sectors of the cylinder 102. Each radiographic image of the second set correlates to a respective radiographic image of the first set. The first set of radiographic imagesof a region of interest 112 can, in some implementations, be received from the flexible detector 100. The region of interest 112 refers to an area within the cylinder 102 that is targeted for radiographic imaging and analysis. The region of interest 112 can include various internal or external features of the cylinder 102 and their surrounding areas, such as joints, structural inconsistencies, or specific material characteristics. For example, the region of interest 112 includes pipe welds. The region of interest 112 is determined based on the inspection requirements. The region of interest 112 may vary in size, shape, and orientation and can be distributed throughout the volume or surface of the cylinder 102. For example, the region of interest 112 cover a continuous circumferential band around the cylinder 102, a localized section, or a distributed pattern spanning multiple circumferential sectors of the cylinder 102.

[0026] FIG. 2A is an example radiographic image 200a from the first set of radiographic images captured by the flexible detector 100. The radiographic image 200a contains information pertaining to the region of interest. It should be noted that the region of interest 112 encompass both a reference region 114 and a feature region 116. The reference region 114 refers to a portion of the cylinder 102 that excludes specific features of the region of interest 112. In some instances, the reference region 114 represent the background material of the cylinder, typically the base structure or body of the cylinder 102. The feature region 116, on the other hand, refers to a portion of the cylinder 102 that contains one or more structural or functional features targeted for inspection. The feature region 116 includes areas such as welds, joints, or other points of material discontinuity that are of interest for the inspection.

[0027] As shown in FIG. 2A, the feature region 116 is difficult to discern in its raw form due to interference from the reference region 114. The reference region 114 can obscure the visibility of the feature region 116 by introducing overlapping information and reducing the clarity of the feature in the radiographic image 200a. As a result, background subtraction algorithm is employed to isolate the reference region 114 from the region of interest 112 thereby increasing the contrast the remaining feature region 116, making the feature of interest (e.g., the weld) more prominent. This provides a more accurate representation of the feature region 116 for precise inspections.

[0028] Returning to FIG. 4, at 404, each radiographic image of the second set is subtracted from the respective radiographic image of the first set. A third set of radiographicimages of a feature region 116 is produced. Inputs to background subtraction algorithm includes radiographic images of the reference region 114. For example, the controller 108 receives second set of radiographic images that exclusively capture the reference region 114. In some implementations, data characterizing physical characteristics of the cylinder 102, such as, inner diameter, thickness, and material composition are received. The controller is configured to render, for each radiographic image of the first set, a correlating radiographic image of the reference region 114 by simulating how the radiation beams 110 would interact with the background material of the cylinder 102. The rendering process may involve recreating the reference region 114 and synthesize a correlating radiographic image. Data characterizing physical characteristics of the cylinder 102 may be received as outputs from upstream tasks or devices e.g„ defect detection processes or dimensional scanners. Alternatively, an inspector may manually input parameters related to the geometry, material properties, or dimensions of the cylinder 102. The third set of radiographic images that exclusively capture the feature region 116 is provided as outputs of the background subtraction algorithm.

[0029] For example, as shown in FIG. 2B, a radiographic image 200b from the third set of radiographic images is characterized by improved contrast and signal-to-noise ratio (SNR) compared to the radiographic image 200a from the first set of radiographic images, as the subtraction eliminates the background information associated with the region of interest 112. In some implementations, the range of pixel intensity values across each radiographic image of the third set is reduced. The background subtraction algorithm focuses on flattening the intensity profile of each radiographic image of the first set in order to achieve a uniform intensity distribution in the produced third set of radiographic images. In some instances, each radiographic image of the third set has an increased contrast level. Each radiographic image of the third set has an improved SNR.

[0030] Referring back to FIG. 4, at 406, data characterizing one or more consolidated radiographic images of the feature region is provided. The third set of radiographic images is processed to produce one or more consolidated radiographic images. A consolidated radiographic image represents a unified depiction of the feature region 116 among all radiographic images captured by the flexible detector 100. The consolidated radiographic image encompasses the entire circumferential area or length of the cylinder 102. In some implementations, the consolidated radiographic images are generated by aligning and stitching(or merging) individual radiographic images from the third set, integrating data across different circumferential sectors of the cylinder 102 into a single, high-resolution view of the feature region 116.

[0031] In some cases, each radiographic image of the third set undergoes one or more processes implemented to enhance the quality and visibility of the feature region 116 and one or more alignment features used to compute transformations of radiographic images of the third set. For example, and as show in FIG. 2C, the dynamic range of each radiographic image 200b of the third set is increased from 10-bit to 16-bit prior to the consolidation. It should be noted that other enhancement processes, such as contrast adjustment and noise reduction may be applied prior or after the consolidation to provide a clear view of feature region 116 so that at least an alignment feature 202, such as an identifiable marker (e.g., a lead letters) can be easily identified from the radiographic image 200b.

[0032] FIG. 3 is an example consolidated radiographic image 300. In some implementations, the consolidated radiographic image 300 is provided by identifying an alignment feature 202 in overlapping regions 302a-b of adjacent radiographic images 304a-b of the third set. As illustrated in FIG. 3, the first radiographic image 304a is defined by the region A to B, and the second radiographic image 304b is defined by the region C to D. At least an alignment feature 202 is identified by comparing pixel values from an estimate or average pixel value via template matching. Alternatively or in addition, feature extraction algorithms can be employed to detect edges, comers, or distinctive patterns in both radiographic images 304a-b. In cases where the image parameters are different, radiographic images 304a-b can be normalized. The boundary x (i.e., stitching point) can then be calculated as a function of the spatial extent of the at least an alignment features 202.

[0033] One or more transformation parameters can then be determined based on the identified alignment feature 202 and the boundary x. Example transformation parameters include translation (to shift the images so that the alignment feature 202 matches at boundary x), scaling (to adjust the relative size of the images if necessary), or rotation (to correct any angular misalignment between images). In some implementations, transformations according to these parameters are applied to each radiographic image of the third set to algin them at their respective boundary / overlapping regions, thereby producing a single consolidated radiographicimage 300. Alternatively or in addition, manual stitching capabilities, including tools for adjusting transparency, cropping, as well as window leveling are implemented thereto. The consolidated radiographic image 300 can be further provided to a downstream device, such as a computing device or a visualization tool, in a digital format suitable for overlaying onto a three-dimensional (3D) model of the cylinder 102. The two-dimension (2D) image data can be mapped onto the corresponding spatial regions of 3D model, providing an intuitive representation of the feature region 116.

[0034] Additionally, data characterizing the three-dimensional (3D) cylinder model is received. A transform to align the two-dimensional (2D) consolidated radiographic images 300 with the physical characteristics of the cylinder 102 is determined. For example, the transform includes positional alignments, such as scaling, rotation, and translation, to map (or overlay) the 2D consolidated radiographic image 300 onto the surface of the 3D model, enabling an intuitive and comprehensive visualization of the feature region 116. In some implementations, a Computer Aided Drafting (CAD) system is used to model the 3D model based on the geometry and physical attributes of the cylinder 102, such as dimensions (e.g., diameter and length), material properties, surface curvature, and any other relevant characteristics. In such implementations, the 3D model serves as a spatial framework onto which the consolidated radiographic images will be aligned and displayed.

[0035] In some cases, the overlay process involves mapping the pixel data of the consolidated radiographic images 300 onto the corresponding regions of the 3D model. In some instances, the feature region 116, such as a weld or joint, is visualized directly on the 3D representation of the cylinder 102. This enables inspectors to analyze the feature region 116 in its spatial context and provides a better understanding of the location and orientation of potential defects or anomalies within the cylinder 102. For example, a weld defect identified in the consolidated radiographic image 300 can be pinpointed on the 3D model with circumferential and axial coordinates.

[0036] In some implementations, such determinations can be made and / or produced by the controller 108. An example of the controller 108 is illustrated in FIG. 5. In some implementations, the controller 108 can execute all or part of the method 400. The controller 108 can. among other things, monitor parameters of the flexible detector 100, send signals to actuateand / or adjust various operating parameters of such systems for example, detector 104 and radiation source 106. As shown in FIG. 5, the controller 108 can include one or more processors 550 and non-transitory computer readable memory storage (e.g.. memory 552) containing instructions that cause the processors 550 to perform operations. The processors 550 are coupled to an input / output (RO) interface 554 for sending and receiving communications with components in the system, including, for example, detector 104 and radiation source 106. In certain instances, the controller 108 can additionally communicate status with and send actuation and / or control signals to one or more of the various system components of the system. Other aspects of the method 400 can similarly be performed by the controller with various degrees of autonomy, for example, adjusting one or more processing parameters or variables used herein based on feedback from the evaluations for specified outputs. Alternatively, or in addition, an inspector can interact with the system described herein to manually customize processing parameters or input specific commands for additional processing.

[0037] The system and method as described herein will enable the quality personnel to identify defects on welds much more easily and decisively. Automatic stitching of images showing only the feature region 116 into one consolidated radiographic image enables identification and location of defects, which can also help identify defects and plan repairs. In some cases, the transformations are based on previous manual alignment of radiographic images by default. Once the first set of radiographic images of the region of interest 112 is received, the second set of radiographic images of the reference region 114 is generated, subtracted from each respective radiographic images of the first set, and the transformations are automatically applied. In some cases, the transformations are dynamic in nature. Lead letters or other similar alignment features at the overlap can be automatically identified and used to determine, for example, rotation, scaling, and / or translation to best align the radiographic images. In some implementations, images of the feature region 116 (e.g., weld) on the reference region 114 (e.g., pipe) that are acquired by flexible detector 100 contain the information of feature region 116 superimposed over information of the reference region 114. An algorithm for background subtraction subtracts the reference region information from the image and produces only feature region information. These feature region-only images are aligned and stitched together based on the mapping of the pixel position and circumferential location on the reference region to produce a high-resolution single image. Additionally, user can add or remove radiographic images, adjustimage position or scale, rotate images, or even stitch images at non-overlapping regions via a user interface.

[0038] Certain exemplary implementations will now be described to provide an overall understanding of the principles of the structure, function, manufacture, and use of the systems, devices, and methods disclosed herein. One or more examples of these implementations are illustrated in the accompanying drawings. Those skilled in the art will understand that the systems, devices, and methods specifically described herein and illustrated in the accompanying drawings are non-limiting exemplary implementations and that the scope of the present invention is defined solely by the claims. The features illustrated or described in connection with one exemplary implementation may be combined with the features of other implementations. Such modifications and variations are intended to be included within the scope of the present invention. Further, in the present disclosure, like-named components of the implementations generally have similar features, and thus within a particular implementation each feature of each like-named component is not necessarily fully elaborated upon.

[0039] The subject matter described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structural means disclosed in this specification and structural equivalents thereof, or in combinations of them. The subject matter described herein can be implemented as one or more computer program products, such as one or more computer programs tangibly embodied in an information carrier (e.g., in a machine-readable storage device), or embodied in a propagated signal, for execution by, or to control the operation of. data processing apparatus (e.g., a programmable processor, a computer, or multiple computers). A computer program (also known as a program, software, software application, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file. A program can be stored in a portion of a file that holds other programs or data, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

[0040] The processes and logic flows described in this specification, including the method steps of the subject matter described herein, can be performed by one or more programmable processors executing one or more computer programs to perform functions of the subject matter described herein by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus of the subject matter described herein can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0041] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processor of any kind of digital computer. Generally, a processor will receive instructions and data from a Read-Only Memory or a Random Access Memory or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g.. magnetic, magneto-optical disks, or optical disks. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks, (e.g., internal hard disks or removable disks); magneto-optical disks; and optical disks (e.g., CD and DVD disks). The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0042] To provide for interaction with a user, the subject matter described herein can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well. For example, feedback provided to the user can be any form of sensory feedback, (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0043] The techniques described herein can be implemented using one or more modules. As used herein, the term “module” refers to computing software, firmware, hardware, and / orvarious combinations thereof. At a minimum, however, modules are not to be interpreted as software that is not implemented on hardware, firmware, or recorded on a non-transitory processor readable recordable storage medium (i.e.. modules are not software per se). Indeed “module” is to be interpreted to always include at least some physical, non-transitory hardware such as a part of a processor or computer. Two different modules can share the same physical hardware (e.g.. two different modules can use the same processor and network interface). The modules described herein can be combined, integrated, separated, and / or duplicated to support various applications. Also, a function described herein as being performed at a particular module can be performed at one or more other modules and / or by one or more other devices instead of or in addition to the function performed at the particular module. Further, the modules can be implemented across multiple devices and / or other components local or remote to one another. Additionally, the modules can be moved from one device and added to another device, and / or can be included in both devices.

[0044] The subject matter described herein can be implemented in a computing system that includes a back-end component (e.g., a data server), a middleware component (e.g.. an application server), or a front-end component (e.g., a client computer having a graphical user interface or a web interface through which a user can interact with an implementation of the subject matter described herein), or any combination of such back-end, middleware, and front-end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.

[0045] Approximating language, as used herein throughout the specification and claims, may be applied to modify any quantitative representation that could permissibly vary without resulting in a change in the basic function to which it is related. Accordingly, a value modified by a term or terms, such as “about” and “substantially,” are not to be limited to the precise value specified. In at least some instances, the approximating language may correspond to the precision of an instrument for measuring the value. Here and throughout the specification and claims, range limitations may be combined and / or interchanged, such ranges are identified and include all the sub-ranges contained therein unless context or language indicates otherwise.

Claims

What is claimed is:

1. A method comprising:receiving data characterizing a first set of radiographic images of a region of interest, the first set of radiographic images being captured at a plurality of circumferential sector of a cylinder, and a second set of radiographic images of a reference region, each radiographic image of the second set correlating to a respective radiographic image of the first set;subtracting each radiographic image of the second set from the respective radiographic image of the first set to produce a third set of radiographic images of a feature region; and providing data characterizing one or more consolidated radiographic images of the feature region.

2. The method of claim 1, wherein receiving the second set of radiographic images of the reference region comprises:receiving data characterizing physical characteristics of the cylinder; andrendering, based on the physical characteristics of the cylinder, the second set of radiographic images of the reference region.

3. The method of claim 1, wherein a range of pixel intensity values across each radiographic image of the third set is reduced, and wherein an intensity curve of each radiographic image of the third set is flattened.

4. The method of claim 1, wherein each radiographic image of the third set has a higher contrast compared to each radiographic image of the first set.

5. The method of claim 1, wherein each radiographic image of the third set has an improved signal-to-noise ratio (SNR) compared to each radiographic image of the first set.

6. The method of claim 1, wherein providing the data characterizing one or more consolidated radiographic image comprises:increasing a dynamic range of each radiographic image of the third set.

7. The method of claim 1, wherein providing the data characterizing one or more consolidated radiographic images comprises:identifying at least an alignment feature in overlapping regions of adjacent radiographic images of the third set; anddetermining transformation parameters for each radiographic image of the third set based on the alignment feature.

8. The method of claim 7, wherein the at least an alignment feature comprises an identifiable marker adjacent to the region of interest.

9. The method of claim 7, wherein providing the consolidated radiographic image further comprises:transforming each radiographic image of the third set according to the transformation parameters; andaligning the adjacent radiographic images of the third set based on the at least an alignment feature to produce a single consolidated radiographic image.

10. The method of claim 2, further comprising:receiving data characterizing a three-dimensional (3D) cylinder model; and determining a transform of the one or more consolidated radiographic images based on the physical characteristics of the cylinder, wherein the transform includes positional alignments of the one or more consolidated radiographic images to overlay the images onto the 3D cylinder model for visualizing the feature region.

11. A system comprising:at least one data processor; andnon-transitory memory storing instructions, which, when executed by the at least one data processor causes the at least one data processor to perform operations comprising:receiving data characterizing a first set of radiographic images of a region of interest, the first set of radiographic images being captured at a plurality of circumferential sector of a cylinder, and a second set of radiographic images of a reference region, each radiographic image of the second set correlating to a respective radiographic image of the first set;subtracting each radiographic image of the second set from the respective radiographic image of the first set to produce a third set of radiographic images of a feature region; andproviding data characterizing one or more consolidated radiographic images of the feature region.

12. The system of claim 11, wherein receiving the second set of radiographic images of the reference region comprises:receiving data characterizing physical characteristics of the cylinder; and rendering, based on the physical characteristics of the cylinder, the second set of radiographic images of the reference region.

13. The system of claim 11, wherein a range of pixel intensity values across each radiographic image of the third set is reduced, and wherein an intensity curve of each radiographic image of the third set is flattened.

14. The system of claim 11, wherein each radiographic image of the third set has a higher contrast compared to each radiographic image of the first set.

15. The system of claim 11, wherein each radiographic image of the third set has an improved signal-to-noise ratio (SNR) compared to each radiographic image of the first set.

16. The system of claim 11 , wherein providing the consolidated radiographic image comprises:increasing a dynamic range of each radiographic image of the third set.

17. The system of claim 11, wherein providing the data characterizing one or more consolidated radiographic images comprises:identifying at least an alignment feature in overlapping regions of adjacent radiographic images of the third set; anddetermining transformation parameters for each radiographic image of the third set based on the alignment feature.

18. The system of claim 17, wherein the at least an alignment feature comprises an identifiable marker adjacent to the region of interest.

19. The system of claim 17, wherein providing the consolidated radiographic image further comprises:transforming each radiographic image of the third set according to the transformation parameters; andaligning the adjacent radiographic images of the third set based on the at least an alignment feature to produce a single consolidated radiographic image.

20. A non-transitory computer readable memory storing instructions which, when executed by at least one data processor forming part of at least one computing system, causes the at least one data processor to perform operations comprising:receiving data characterizing a first set of radiographic images of a region of interest, the first set of radiographic images being captured at a plurality of circumferential sector of a cylinder, and a second set of radiographic images of a reference region, each radiographic image of the second set correlating to a respective radiographic image of the first set;subtracting each radiographic image of the second set from the respective radiographic image of the first set to produce a third set of radiographic images of a feature region; and providing data characterizing one or more consolidated radiographic images of the feature region.

Images