Image processing device, image processing method, and program

Abstract

Provided is an image processing device comprising one or more processors, wherein the one or more processors perform importance derivation processing that relates to a plurality of images with an overlapping region and in which the importance of a predetermined division region in the overlapping region is derived, said division region corresponding to an angle formed by radiation emitted from a radiation source or a light beam emitted from a light source in order to obtain the images and a normal line of a detection surface for detecting the radiation or of a light reception surface for receiving the light beam through a subject.

Description

Image processing device, image processing method and program

[0001] This application claims priority to Japanese Patent Application No. 2024-047955, filed March 25, 2024, the entire text of which is incorporated herein by reference. The present disclosure relates to an image processing device, an image processing method, and a program.

[0002] In the past, there was a technique for taking multiple photographs of a subject when the subject was large and it was not possible to obtain an image of the entire subject or an image of the desired range in a single photograph, and then combining the images obtained by the multiple photographs.

[0003] For example, Japanese Patent Application Laid-Open No. 2014-8281 discloses an X-ray imaging device that can combine transmission images detected by a two-dimensional detector at different positions of a sample relative to the two-dimensional detector.

[0004] This X-ray imaging device comprises an X-ray generation unit that irradiates a sample with X-rays that are approximately parallel to the sample, a two-dimensional detector that is arranged on the opposite side of the X-ray generation unit with respect to the sample and has a detection area that detects a transmission image of the sample, a support table on which the sample is placed, a stage that mounts the support table and is capable of moving the support table in-plane along the plane of the detection area of ​​the two-dimensional detector, and a control unit that generates composite transmission image data based on a plurality of transmission images of the sample detected by the two-dimensional detector, and is characterized in that the control unit generates composite transmission image data by stitching together transmission images of the sample at a plurality of different positions.

[0005] However, while the technology disclosed in JP 2014-8281 A can generate a composite transparent image by pasting together multiple transparent images that have overlapping areas, it only determines the pasting position by taking into account the amount of overlap in the overlapping areas of adjacent transparent images in the composite transparent image, and does not necessarily make it possible to suppress the visual unnaturalness of the composite transparent image.

[0006] This is not limited to transmission images obtained by radiography using X-rays or other radiation, but can also occur in reflection images obtained by radiography using a normal optical camera.

[0007] The present disclosure has been made in consideration of the above circumstances, and provides an image processing device, an image processing method, and a program that can suppress the visual unnaturalness of a composite image obtained by overlapping and combining multiple images that have overlapping areas with each other in the overlapping areas.

[0008] An image processing device of a first aspect of the present disclosure includes at least one processor, and the processor performs an importance derivation process on a plurality of images having overlapping regions with each other, in which the importance of a predetermined divided region in the overlapping region is derived according to the angle between the light ray emitted from the light source or the radiation emitted from the radiation source to obtain the image and the normal of the light receiving surface that receives the light ray through the subject or the normal of the detection surface that detects the radiation.

[0009] An image processing device according to a second aspect of the present disclosure is the image processing device according to the first aspect, wherein the normal is obtained at a position where a ray of light or radiation lands on the light receiving surface or the detection surface.

[0010] An image processing device according to a third aspect of the present disclosure is the image processing device according to the first aspect, wherein the normal is obtained on at least one representative surface that represents the light receiving surface or the detection surface.

[0011] An image processing device of a fourth aspect of the present disclosure is an image processing device of the third aspect, wherein the representative surface is any one of the following surfaces on the light receiving surface or detection surface: a surface located at the center, a surface that is the shortest distance from the light source or radiation source, a surface perpendicular to the light ray or radiation, a surface on which the light ray or radiation that has passed through the center or center of gravity of the subject lands, and a surface indicated by the user.

[0012] An image processing device according to a fifth aspect of the present disclosure is the image processing device according to the first or second aspect, wherein the processor assigns a lower importance to an image as the angle increases.

[0013] An image processing device of a sixth aspect of the present disclosure is an image processing device of the first or second aspect, in which the processor further performs a synthesis process to create a composite image by overlapping multiple images in overlapping areas depending on their importance.

[0014] An image processing device of a seventh aspect of the present disclosure is an image processing device of the sixth aspect, in which, when the processor displays the created composite image and an overlapping area in the displayed composite image is specified by the user, it further performs partial image display processing to display the image of higher importance among the images corresponding to the overlapping area.

[0015] An image processing device of an eighth aspect of the present disclosure is an image processing device of the sixth aspect, in which the processor performs the compositing process by moving and overlapping at least one of the multiple images, and when the processor determines the amount of movement to actually apply from the multiple amounts of movement using the degree of similarity of the overlapping areas in multiple composite images created by performing the compositing process individually using multiple candidate amounts of movement, the processor determines the contribution of the divided area to the degree of similarity according to its importance.

[0016] An image processing device of a ninth aspect of the present disclosure is an image processing device of the sixth aspect, in which the processor performs a synthesis process by deforming and overlapping at least one of a plurality of images, and when the processor determines the amount of deformation to actually apply from the plurality of deformation amounts using the degree of similarity of the overlapping areas in a plurality of synthesized images created by performing the synthesis process individually using a plurality of candidate deformation amounts, the processor determines the contribution of the divided area to the degree of similarity according to its importance.

[0017] An image processing device of a tenth aspect of the present disclosure is the image processing device of the sixth aspect, in which the processor determines the image to be adopted from a plurality of corresponding images as the image of the overlapping area in the composite image based on importance.

[0018] An image processing device of an eleventh aspect of the present disclosure is an image processing device of the tenth aspect, in which the processor determines the image to be adopted as an image obtained by weighted averaging images of corresponding divided areas in multiple images, with the corresponding importance used as a weighting coefficient.

[0019] An image processing device of a twelfth aspect of the present disclosure is an image processing device of the tenth aspect, in which the processor determines the image to be used as the image with the higher importance among the images of the corresponding partition area in the multiple images.

[0020] An image processing device according to a thirteenth aspect of the present disclosure is the image processing device according to the tenth aspect, wherein the processor determines the image to be adopted to be the image having the highest importance among the plurality of images.

[0021] An image processing device of a fourteenth aspect of the present disclosure is an image processing device of the first or second aspect, in which a processor receives placement information indicating the placement relationship between a light source or radiation source and a light receiving surface or a detection surface, and derives an angle using the placement information.

[0022] An image processing device according to a fifteenth aspect of the present disclosure is the image processing device according to the first or second aspect, wherein the partitioned regions are regions for each pixel in a plurality of images.

[0023] An image processing device according to a sixteenth aspect of the present disclosure is the image processing device according to the first or second aspect, wherein the plurality of images are transparent images.

[0024] A program of a seventeenth aspect of the present disclosure causes a computer to execute processing relating to a plurality of images having overlapping regions, performing importance derivation processing to derive the importance of predetermined divided regions in the overlapping regions according to the angle between the light rays emitted from a light source or the radiation emitted from a radiation source to obtain the image and the normal of the light receiving surface that receives the light rays or the normal of the detection surface that detects the radiation through the subject.

[0025] The method of the eighteenth aspect of the present disclosure is an image processing method executed by a computer, which processes multiple images having overlapping areas with each other, and performs importance derivation processing to derive the importance of predetermined divided areas in the overlapping areas according to the angle between the light rays emitted from a light source or the radiation emitted from a radiation source to obtain the images and the normal of the light receiving surface that receives the light rays through a subject or the normal of the detection surface that detects the radiation.

[0026] According to the present disclosure, it is possible to suppress the visual unnaturalness of a composite image obtained by combining a plurality of images having overlapping regions by overlapping the overlapping regions.

[0027] 9 is a block diagram showing a schematic configuration of a radiographic image capturing device according to an embodiment. FIG. 10 is a block diagram showing an example of a hardware configuration of an image processing device according to an embodiment. FIG. 11 is a diagram provided for explaining the related art, in which the left diagram is a side view showing a state of radiation irradiating an object to be inspected, the middle diagram is a transmission image when the radiation irradiation position is on the left side of the left diagram, and the right diagram is a transmission image when the radiation irradiation position is on the right side of the left diagram. FIG. 12 is a diagram provided for explaining the related art, and is a side view showing various variations of imaging. FIG. 13 is a block diagram showing an example of a functional configuration of an image processing device according to an embodiment. FIG. 14 is a side view (graph showing a partial importance) provided for explaining importance according to an embodiment. FIG. 15 is a diagram showing an example of importance according to an embodiment. FIG. 16 is a diagram showing an example of a method for determining a synthesis boundary according to an embodiment. FIG. 17 is a diagram showing an example of an image (partial image) before synthesis according to an embodiment. FIG. 18 is a diagram showing an example of importance in the image shown in FIG. 9. FIG. 19 is a diagram showing an example of a result of synthesis processing of the images shown in FIG. 10. FIG. 11 is a schematic diagram showing an example of a configuration of an image information database according to an embodiment. FIG. 12 is a schematic diagram showing an example of a configuration of a placement information database according to an embodiment. FIG. 13 is a flowchart showing an example of image processing according to an embodiment. FIG. 14 is a schematic diagram showing a flow up to creating a synthetic image in image processing by an image processing device according to an embodiment. 1A and 1B are side views showing an example of an arrangement of a radiation source, an inspection object, and a non-planar detector when the radiation detector is non-planar;

[0028] Hereinafter, with reference to the drawings, an example of an embodiment for implementing the technology of the present disclosure will be described in detail. Note that in this embodiment, a radiographic image, which is a transmission image, is applied as the image related to the technology of the present disclosure, and a case will be described in which the technology of the present disclosure is applied to a radiographic imaging device that performs non-destructive testing of an object, such as a metal part, from a radiographic image of the object. Note that the technology of the present disclosure can also be applied to an image acquired using light rays emitted from a light source and received on a light-receiving surface.

[0029] First, the configuration of a radiographic image capturing apparatus 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing a schematic configuration of the radiographic image capturing apparatus 1 according to this embodiment.

[0030] 1 , the radiographic imaging device 1 includes an image processing device 10, a radiation source 12, and a radiation detector 14. The image processing device 10, the radiation source 12, and the radiation detector 14 are connected to each other so as to be able to communicate with each other. The image processing device 10 is, for example, a computer such as a personal computer or a server computer.

[0031] The radiation source 12 irradiates radiation R, such as X-rays, onto an inspection object O serving as a subject. The radiation source 12 according to this embodiment irradiates the inspection object O with cone-beam radiation R. Hereinafter, the direction from the radiation source 12 to a point on the radiation detector 14 at which the radiation R, having passed through the inspection object O, reaches will be referred to as the "irradiation direction D."

[0032] The radiation detector 14 includes a scintillator as an example of a light-emitting layer that emits light when irradiated with radiation R, and a TFT (Thin Film Transistor) substrate. The scintillator and TFT substrate are laminated. The TFT substrate has a plurality of pixels arranged two-dimensionally, and each pixel has a sensor unit and a field-effect thin-film transistor as an example of a conversion element that generates an increasing amount of charge as the amount of radiation irradiated increases. The sensor unit absorbs light emitted by the scintillator to generate charge and accumulates the generated charge. The field-effect thin-film transistor converts the charge accumulated in the sensor unit into an electrical signal and outputs it. With the above configuration, the radiation detector 14 generates a two-dimensional radiographic image corresponding to the radiation R irradiated from the radiation source 12 onto the inspection object O, and outputs the generated radiographic image to the image processing device 10.

[0033] In this manner, in the radiographic image capturing device 1 , a radiographic image captured by irradiating the object O to be inspected with radiation R from the radiation source 12 along the irradiation direction D is stored in the image processing device 10 .

[0034] Next, the hardware configuration of the image processing device 10 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the hardware configuration of the image processing device according to this embodiment.

[0035] 2 , the image processing device 10 includes a CPU (Central Processing Unit) 20, a memory 21 serving as a temporary storage area, and a non-volatile storage unit 22. The image processing device 10 also includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and a mouse, and a network I / F (Interface) 25 connected to a network. The image processing device 10 also includes an external I / F 26 to which the radiation source 12 and the radiation detector 14 are connected. The CPU 20, the memory 21, the storage unit 22, the display 23, the input device 24, the network I / F 25, and the external I / F 26 are connected to a bus 27. The CPU 20 is an example of a processor according to the disclosed technology.

[0036] The storage unit 22 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 22 serves as a storage medium and stores an image processing program 30. The CPU 20 reads the image processing program 30 from the storage unit 22, loads it into the memory 21, and executes the loaded image processing program 30.

[0037] The storage unit 22 also stores an image information database 32 and a layout information database 34. These databases will be described in detail later.

[0038] However, there are cases where the object to be inspected O is relatively large and a radiographic image of the entire area to be inspected cannot be obtained by a single image capture by the radiation detector 14, or where it is desired to get close to the object to be inspected O and capture the image in order to perform precise non-destructive inspection of the object to be inspected O.

[0039] In these cases, the user divides the inspection object O into a plurality of partial regions and captures an image of each partial region to obtain a plurality of radiographic images (hereinafter referred to as "partial images"). The radiographic image capturing device 1 according to this embodiment then performs a process of combining the obtained plurality of partial images (hereinafter referred to as "combining process") in the image processing, the details of which will be described later. This combining process is performed because, when inspecting an inspection object using captured images, if the images obtained in a single capture are handled individually, it is not possible to correctly grasp the entire inspection object, which leads to inefficiency in the inspection work and a decrease in the quality of the inspection results.

[0040] When capturing these multiple partial images, the user captures adjacent partial images so that overlapping areas are provided at their edges, and in the compositing process according to this embodiment, the multiple partial images are overlapped at their overlapping areas to create a composite image (hereinafter referred to as a "composite image"). The overlapping areas are provided in order to reliably reproduce radiographic images for the entire area to be captured in the composite image obtained by the compositing process.

[0041] The above-described image synthesis is generally called mosaicking or stitching. Mosaicking simply translates partial images, while stitching transforms and moves the partial images, and then performs image processing so that the boundaries between the synthesized partial images are visually natural. The synthesis process according to this embodiment can be applied to either mosaicking or stitching.

[0042] In general, when combining images, it is required that the combined image allows the user to easily grasp the overall image of the object, and therefore it is required to achieve more natural visibility of overlapping areas in adjacent partial images.

[0043] To achieve this, image synthesis processing generally involves the following two processes: "deforming and moving partial images" and "determining the boundaries in the overlapping areas between partial images (hereinafter referred to as "synthesis boundaries")."

[0044] First process: "Transforming and moving partial images" determines the optimal amount of transformation and movement based on the degree of similarity of the images in the overlapping areas between the partial images. Examples of "similarity" include pixel-by-pixel correlation (e.g., SAD (Sum of Absolute Difference), SSD (Sum of Squared Difference), NCC (Normalized Cross-Correlation), etc.) and the degree of similarity of feature points in the target images whose positions have been detected in advance. This process also includes a process of correcting distortions caused by photography for each partial image in advance.

[0045] - Second process: "Determining the synthesis boundary" determines the optimal boundary based on the naturalness of the overlapping area between the partial images. "Naturalness" here means that the boundary line is difficult to see. Methods for determining the synthesis boundary include, for example, simply determining which partial image is to be in front, calculating an adaptive boundary line, blending pixels using a weighted average (so-called alpha blending), and smoothing the boundary through image processing.

[0046] However, for inspection purposes, distortion correction and deformation of partial images in the first process, and pixel blending and boundary smoothing in the second process, may be considered inappropriate because these processes may be considered to be falsification of the photographic information.

[0047] Furthermore, even when using existing methods, overlapping regions between partial images may not match. For example, as shown in FIG. 3 , when capturing a transmission image of an inspection object O having a three-dimensional structure, radiation R radially irradiated from a radiation source 12 is captured by the detection surface of a radiation detector 14 and imaged. For this reason, transmission images 50 obtained by capturing multiple images with the radiation source 12 positioned at different times may not match. Note that FIG. 3 is a diagram used to explain the problems of the conventional technology, with the left diagram being a side view showing the irradiation state of radiation R on the inspection object O, the middle diagram showing a transmission image 50 when the irradiation position of radiation R is on the left side of the left diagram, and the right diagram showing a transmission image 50 when the irradiation position of radiation R is on the right side of the left diagram.

[0048] In the example shown in Figure 3, a protrusion p exists on the rear surface of the inspection object O, and a protrusion q exists on the front surface of the inspection object O. In this case, when the radiation source 12 is located on the left side in the left diagram of Figure 3, the protrusion p and the protrusion q appear to overlap at approximately the same position in the images. In contrast, when the radiation source 12 is located on the right side in the left diagram of Figure 3, the protrusion p and the protrusion q appear to be spaced apart and at different positions in the images. Therefore, in this case, when the image portions of the protrusion p and the protrusion q are located in overlapping regions of the partial images, the images of the overlapping regions do not match.

[0049] This problem can arise when a composite image is obtained by capturing multiple images of an object having a three-dimensional structure, such as in the transmission photography shown in the upper left of Fig. 4 or the reflection photography (photography using an optical camera) shown in the upper right of Fig. 4. In other words, in these cases, distortions can occur, in which the partial images do not match, depending on the relative positions of the radiation source 12 or light source, the object, and the detection surface or light-receiving surface of the radiation detector 14. Note that Fig. 4 is a side view illustrating various variations in photography, provided for explanation of the prior art.

[0050] On the other hand, this problem does not arise when only the surface of the object is of interest, as in the reflected image shown on the left in the lower part of Fig. 4, or when it is assumed that radiation R is irradiated from infinity, as in the transmitted image shown on the right in the lower part of Fig. 4. This is because in the former case, if the prior distortion correction is based on the imaging system, it is not considered to be tampering, and in the latter case, no distortion occurs and the partial images match.

[0051] The image processing device 10 according to this embodiment performs image processing to solve the above problems. Next, the functional configuration of the image processing device 10 according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing an example of the functional configuration of the image processing device 10 according to this embodiment.

[0052] 5, the image processing device 10 includes an importance derivation unit 20A, a synthesis processing unit 20B, a partial image display processing unit 20C, and a placement information receiving unit 20D. The CPU 20 executes the image processing program 30 to function as the importance derivation unit 20A, the synthesis processing unit 20B, the partial image display processing unit 20C, and the placement information receiving unit 20D.

[0053] 6 as an example, the importance derivation unit 20A according to this embodiment performs an importance derivation process on a plurality of images (corresponding to the above-mentioned "partial images") having overlapping regions, deriving the importance of a predetermined divided region (in this embodiment, a region for each pixel) in the overlapping region of the partial images in accordance with the angle A formed between the radiation R emitted from the radiation source 12 to obtain the partial image and the normal N to the detection surface of the radiation detector 14 that detects the radiation R via the inspection object O. Note that FIG. 6 is a side view (a graph showing a portion of the importance) for explaining the importance according to this embodiment.

[0054] In this embodiment, the normal N is obtained from at least one representative surface that represents the detection surface of the radiation detector 14. Although the representative surface in this embodiment is a surface located at the center of the detection surface of the radiation detector 14, the present invention is not limited to this. For example, the representative surface may be any one of the following: a surface on the detection surface of each radiation detector 14 that is closest to the radiation source 12; a surface perpendicular to the radiation R; a surface on which the radiation R lands after passing through the center or center of gravity of the subject; and a surface designated by the user. Note that the "center" and "center of gravity" referred to here refer to both the "center" and "center of gravity" when the subject is viewed in a two-dimensional view, and the "center" and "center of gravity" when viewed three-dimensionally.

[0055] Here, in the importance derivation process according to this embodiment, the importance decreases as the angle A increases. However, this is not limited to this embodiment, and for example, the importance may be constant for some sections of the angle A, such as a section near 90 degrees (for example, a section from 80 degrees to 90 degrees) or a section near 0 (zero) degrees (for example, a section from 0 degrees to 5 degrees). Furthermore, in the importance derivation process according to this embodiment, the importance decreases linearly in proportion to the angle A as the angle A increases, but this is not limited to this embodiment. For example, the importance may decrease nonlinearly by decreasing the amount of decrease as the angle A increases.

[0056] In this way, in the importance derivation process according to this embodiment, the importance is derived according to the angle A. In other words, the importance is derived according to the distance from the position of the radiation source 12 when projected onto the detection surface of the radiation detector 14. In other words, the importance is defined according to the distance and the angle A because the importance is given to image regions with smaller distortion due to imaging.

[0057] Therefore, in cases where the position of the radiation source 12 projected onto the detection surface of the radiation detector 14 is known but the distance between the detection surface and the radiation source 12 is unknown, the importance may be derived based only on the distance from the position.

[0058] In this embodiment, the importance level is set for each of the above-described divided regions of the partial image. The setting state of the importance levels 40 in this case may be, for example, concentrically spread as shown in the left diagram of Fig. 7 , or may be biased depending on the position of the radiation source 12, the emission angle of the radiation R, etc., as shown in the center diagram of Fig. 7 . Furthermore, as shown in the right diagram of Fig. 7 , the change in the importance level may not be constant. Fig. 7 shows an example of the importance levels 40 according to this embodiment.

[0059] Then, the synthesis processing unit 20B according to this embodiment performs synthesis processing to create a synthetic image by overlapping the plurality of partial images in overlapping regions according to the importance.

[0060] In addition, when the partial image display processing unit 20C according to this embodiment displays the created composite image, and when an overlapping area in the displayed composite image is specified by the user by hovering or clicking the mouse, etc., it performs partial image display processing to display the image of higher importance among the images corresponding to the overlapping area.

[0061] Here, when the synthesis processing unit 20B according to this embodiment deforms the partial images in the above-described first process, the synthesis processing is performed by deforming at least one of the multiple partial images to overlap them. In this case, the synthesis processing unit 20B according to this embodiment determines the transformation amount to actually apply from the multiple transformation amounts using the degree of coincidence of the overlapping areas in multiple synthesized images created by performing synthesis processing individually using multiple candidate transformation amounts.

[0062] In this case, the synthesis processing unit 20B according to the present embodiment determines the contribution of the segmented region to the degree of matching (hereinafter referred to as "deformation contribution") according to the importance.

[0063] Furthermore, when moving partial images in the first process, the compositing processing unit 20B according to this embodiment performs the compositing process by moving at least one of the multiple partial images to overlap them. In this case, the compositing processing unit 20B according to this embodiment determines the amount of movement to actually apply from the multiple amounts of movement using the degree of coincidence of overlapping areas in multiple composite images created by performing the compositing process individually using multiple candidate amounts of movement.

[0064] In the synthesis processing unit 20B according to this embodiment, the contribution of the segmented region to the degree of coincidence (hereinafter referred to as "movement contribution") is also determined according to the importance.

[0065] Specifically, for both the deformation contribution and the movement contribution, the contribution is increased for each segmented area with higher importance. For example, when the correlation between overlapping areas of partial images is used as the degree of match, the average value of values ​​obtained by weighting the average with the importance of each segmented area as a weighting factor is used as the degree of match. Also, when the degree of match between feature points is used as the degree of match, the average value of values ​​obtained by weighting the average with the importance of each segmented area as a weighting factor is used as the degree of match. Note that in this case, the weighted average may not use the value of the segmented area with the lowest importance.

[0066] On the other hand, the "determination of the synthesis boundary" in the second process described above is, more specifically, determining the value of the divided area in the overlapping area, and the synthesis processing unit 20B in this embodiment determines the partial image to be adopted from the corresponding multiple partial images as the image of the overlapping area in the synthesized image, based on its importance.

[0067] In the synthesis processing unit 20B according to this embodiment, the partial image to be adopted is determined to be the image with the higher importance among the images of corresponding partitioned regions in the plurality of partial images, as shown in Fig. 8 as an example. Fig. 8 is a diagram showing an example of a synthesis boundary determination method according to this embodiment, in which the left diagram shows an example of the importance 40 of adjacent partial images 42, the middle diagram shows the selection result of the image with the higher importance 40 in the left diagram, and the right diagram shows the determination result of a synthesis boundary 44 according to the selection result.

[0068] More specific examples of this embodiment are shown in Figures 9 to 11. Figure 9 is a diagram showing an example of a partial image 42 (here, an image of a metal pipe) before compositing, and Figure 10 is a diagram showing an example of the importance 40 for the partial image 42 shown in Figure 9. Note that Figures 9 and 10 illustrate an example in which the translation of each partial image 42 has been completed. And Figure 11 is a diagram showing an example of the result of compositing processing using the importance 40 shown in Figure 10 for the partial image 42 shown in Figure 9. Note that the left diagram in Figure 11 is a diagram showing a compositing boundary 44, and the right diagram in Figure 11 is a diagram showing the finally obtained composite image 46.

[0069] The method for determining the partial image to be adopted is not limited to the above. For example, the partial image to be adopted may be determined to be an image obtained by a weighted average of images of corresponding divided regions in a plurality of partial images, with the corresponding importance as a weighting factor. Furthermore, for example, the partial image to be adopted may be determined to be the partial image with the highest importance among the plurality of partial images.

[0070] Furthermore, the arrangement information receiving unit 20D according to this embodiment receives arrangement information indicating the arrangement relationship between the radiation source 12 and the detection surface of the radiation detector 14. Then, the importance derivation unit 20A according to this embodiment derives the angle A using the arrangement information received by the arrangement information receiving unit 20D.

[0071] In this embodiment, radiographic images, which are transmitted images, are used as the plurality of partial images, but the present invention is not limited to this. For example, reflected images obtained by photographing with an optical camera may be used as the plurality of partial images.

[0072] Next, the image information database 32 according to this embodiment will be described with reference to Fig. 12. Fig. 12 is a schematic diagram showing an example of the configuration of the image information database 32 according to this embodiment.

[0073] The image information database 32 according to this embodiment is a database in which information indicating the partial images described above is registered. As shown in Fig. 12, the image information database 32 according to this embodiment stores information such as object IDs (Identifications) and image information.

[0074] The object ID is information assigned in advance to each of the inspection objects O in order to individually identify the inspection objects O that are compatible with the radiographic imaging device 1. The image information is information that indicates the image information itself that indicates the partial image.

[0075] Next, the placement information database 34 according to this embodiment will be described with reference to Fig. 13. Fig. 13 is a schematic diagram showing an example of the configuration of the placement information database 34 according to this embodiment.

[0076] The arrangement information database 34 according to this embodiment is a database in which the above-described arrangement information is registered. As shown in Fig. 13 , the arrangement information database 34 according to this embodiment stores information on the object ID, the partial image, the radiation source position, and the detector.

[0077] The object ID is the same information as the object ID in the image information database 32. The partial image is information indicating the type of the corresponding partial image of the inspection object O, and the radiation source position is information indicating the position of the radiation source 12 when the corresponding partial image was captured by the radiographic imaging device 1. The detector is information indicating the position of the radiation detector 14 and the effective imaging size of the radiation detector 14 used when capturing the corresponding partial image.

[0078] In the radiographic imaging device 1 according to this embodiment, predetermined positions (in this embodiment, central positions) of the radiation source 12 and the radiation detector 14 are expressed in a predetermined common three-dimensional coordinate system. Furthermore, in the radiographic imaging device 1 according to this embodiment, the effective imaging size of the radiation detector 14 is determined by the vertical and horizontal dimensions of the imaging area of ​​the radiation detector 14 when viewed from the radiation R incident side.

[0079] The importance derivation unit 20A according to this embodiment uses the positions of the radiation source 12 and the radiation detector 14 to derive, for each partial image, an angle A for each divided area (in this embodiment, an area for each pixel) in the entire area of ​​the radiographic image obtained by imaging using the radiation detector 14, which is defined by the effective imaging size, and derives the importance of each divided area from the derived angle A.

[0080] As described above, the importance derivation unit 20A according to the present embodiment derives the importance using the positions of the radiation source 12 and the radiation detector 14 and the effective imaging size of the radiation detector 14, but is not limited to this. For example, if the radiation detector 14 is flexible and the radiation detector 14 itself is distorted, the importance may be derived taking into account the distortion. Furthermore, if the detection surface of the radiation detector 14 is inclined with respect to the incident direction of the radiation R, the importance may be derived taking into account the angle of the inclination.

[0081] Next, the operation of the image processing device 10 according to this embodiment will be described with reference to Fig. 14. The image processing shown in Fig. 14 is performed by the CPU 20 of the image processing device 10 executing the image processing program 30. The image processing shown in Fig. 14 is performed, for example, when a command to perform the image processing is input by a user of the image processing device 10. Note that, in order to avoid confusion, the following description will be given on the case where the image information database 32 and the arrangement information database 34 have already been constructed. The following description will also be given on the case where the object ID of the inspection object O to be processed has been specified in advance.

[0082] 14, the CPU 20 reads out image information indicating each partial image of the inspection object O (hereinafter referred to as the "processing object") corresponding to a pre-specified object ID from the image information database 32. Also, in step 100, the CPU 20 reads out information on the radiation source position and detector (hereinafter referred to as the "arrangement information") corresponding to the processing object from the arrangement information database 34.

[0083] In step 102, the CPU 20 uses the read-out layout information to derive the angle A for each of the read-out partial images and for each of the segmented areas, as described above. In step 104, the CPU 20 uses the derived angle A to derive the importance for each of the read-out partial images and for each of the segmented areas, as described above.

[0084] In step 106, the CPU 20 performs the synthesis process for synthesizing the read partial images using the derived importance, as described above. In step 108, the CPU 20 controls the display 23 to display the synthesized image obtained by the synthesis process.

[0085] In step 110, if the user specifies an overlapping area in the displayed composite image, the CPU 20 performs the partial image display process described above, which displays the image with the higher importance among the images corresponding to the overlapping area, and then terminates this image processing. Note that if the user specifies that the image processing is to be terminated without specifying an overlapping area in the displayed composite image, this image processing is terminated without executing the partial image display process.

[0086] FIG. 15 is a schematic diagram showing the flow of the above image processing up to the creation of a composite image.

[0087] As shown in FIG. 15, in the image processing according to this embodiment, the target layout information and a plurality of partial images are read out in the processing of step 100, and the importance is derived in the processing of steps 102 and 104.

[0088] In this image processing, a synthesis process for synthesizing partial images is performed in step 106. At this time, in the image processing according to this embodiment, as described above, the following process is performed.

[0089] First, candidates for the amount of deformation and movement for each partial image are derived, and the derived importance is used to derive the degree of matching for each of the candidates with respect to each overlapping area of ​​the partial image.The amount of deformation and movement to be actually applied to each partial image from the candidates is then determined based on the degree of matching.

[0090] Separately from this, the derived importance is used to derive the composite boundary of each of the adjacent partial images as described above, and the partial images are combined using the determined deformation amount and movement amount and the derived composite boundary to create a composite image.

[0091] As described above, the image processing device according to this embodiment performs an importance derivation process on multiple images having overlapping regions, in which the importance of predetermined divided regions in the overlapping regions is derived in accordance with the angle between the light rays emitted from the light source or the radiation emitted from the radiation source (in this embodiment, the radiation emitted from the radiation source) to obtain the image and the normal to the light-receiving surface that receives the light rays or the normal to the detection surface that detects the radiation via the subject. This makes it possible to reduce the visual unnaturalness of a composite image obtained by combining multiple images having overlapping regions by overlapping them at the overlapping regions.

[0092] Furthermore, the image processing device according to this embodiment uses a normal obtained from at least one representative surface that represents the light-receiving or detecting surface, which makes it easier to determine the normal compared to when a normal obtained from the position where the light ray or radiation lands on the light-receiving or detecting surface is used.

[0093] Furthermore, the image processing device according to this embodiment applies, as the representative surface, any one of the following surfaces on the light receiving surface or detection surface: a surface located at the center, a surface that is closest to the light source or radiation source, a surface perpendicular to the light ray or radiation, a surface on which the light ray or radiation that has passed through the center or center of gravity of the subject lands, and a surface designated by the user. Therefore, the normal can be determined based on the applied representative surface.

[0094] Furthermore, according to the image processing device of this embodiment, the larger the angle, the lower the importance level, so that visual unnaturalness in the composite image can be more effectively suppressed.

[0095] Furthermore, the image processing device according to this embodiment further performs a compositing process to create a composite image by overlapping multiple images in overlapping areas according to the importance, thereby making it possible to create a composite image that is visually less unnatural.

[0096] Furthermore, according to the image processing device of this embodiment, when the created composite image is displayed and an overlapping area in the displayed composite image is specified by the user, a partial image display process is further performed to display the image with the higher importance among the images corresponding to the overlapping area, thereby making it possible to display the more important partial image.

[0097] Furthermore, according to the image processing device of this embodiment, when combining images by moving at least one of the images to overlap them, and when determining the amount of movement to actually apply from the multiple amounts of movement using the degree of similarity of the overlapping areas in the multiple combined images created by performing the combining process individually using multiple candidate amounts of movement, the contribution of the segmented areas to the degree of similarity is determined according to their importance. Therefore, it is possible to appropriately determine the amount of movement when creating a combined image by moving and overlapping the images.

[0098] Furthermore, according to the image processing device of this embodiment, when combining images by deforming and overlapping at least one of the images, and when determining the transformation amount to be actually applied from the multiple transformation amounts using the degree of agreement of the overlapping areas in the multiple combined images created by performing the combining process individually using multiple candidate transformation amounts, the contribution of the segmented areas to the degree of agreement is determined according to their importance. Therefore, it is possible to appropriately determine the transformation amount when creating a combined image by deforming and overlapping images.

[0099] Furthermore, according to the image processing device of this embodiment, the image to be used as the image of the overlapping area in the composite image is determined from the multiple corresponding images according to the importance, so that the image to be used as the image of the overlapping area can be appropriately determined.

[0100] Furthermore, the image processing device according to the present embodiment may also adopt a mode in which the image to be adopted is determined to be an image obtained by a weighted average of images in corresponding divided regions of a plurality of images, with the corresponding importance used as a weighting factor. Therefore, the image in the overlapping region can be made into an image in which the two corresponding images are transparent, taking their importance into account (alpha blending image), thereby more effectively suppressing the visual unnaturalness of the composite image.

[0101] Furthermore, the image processing device according to this embodiment determines the image to be adopted as the image with the highest importance among the images in the corresponding segmented area among the multiple images, which makes it easier to determine the image to be adopted than when a weighted average is used to determine the image to be adopted.

[0102] Furthermore, the image processing device according to the present embodiment can also adopt a mode in which the image to be adopted is determined to be the image with the highest importance among multiple images, which makes it easier to determine the image to be adopted compared to when the image to be adopted is determined for each divided area.

[0103] Furthermore, the image processing device according to this embodiment receives positional information indicating the positional relationship between the radiation source and the detection surface of the radiation detector, and derives the angle using the positional information, thereby easily obtaining the angle between the radiation source and the normal to the detection surface of the radiation detector.

[0104] Furthermore, according to the image processing device of this embodiment, the divided regions are regions of each pixel in the multiple images, and therefore, processing related to overlapping of images can be performed on a pixel-by-pixel basis, thereby creating a composite image with reduced visual unnaturalness.

[0105] Furthermore, according to the image processing device of this embodiment, the plurality of images are transparent images, and therefore the effects of the disclosed technology can be enjoyed for transparent images.

[0106] In the above embodiment, the derived importance of each divided region may be presented to the user. By referring to the importance of each divided region, the user can grasp important regions with less distortion on the image, and as a result, can accurately grasp the target of judgment in various examinations.

[0107] In this case, the importance may be displayed for each partial image individually, or may be displayed for the composite image. Furthermore, the importance may be displayed as a map, separate from and parallel to the corresponding image, or semi-transparently superimposed on the corresponding image. Furthermore, the importance value may be displayed at a position designated by the user, for example, by hovering the mouse, or the value may be spoken aloud.

[0108] In the above embodiment, a boundary line indicating the synthesis boundary may be clearly displayed on the synthesized image.

[0109] A specific example of this form is a form in which the boundary line of the composite boundary in pixel units is highlighted. An example of the highlighting in this case is a form in which at least one of the color, thickness, and display state of the boundary line is displayed differently from other lines. This form can help draw attention to the vicinity of the boundary line and eliminate psychological resistance that may be caused by suspicion of tampering.

[0110] In the above embodiment, when a partial image is displayed, an overlapping area may be clearly indicated in the partial image.

[0111] That is, the composite image may be referred to in order to obtain an overview of the entire image, and at this time, the user may be viewing a partial image corresponding to a specific position in the composite image. In this case, information about the overlapping area is lost in the composite image due to the compositing process. In order to provide this correspondence to the user, the overlapping area in the partial image is highlighted. Specific examples of this include graying out the overlapping area in the partial image semi-transparently, or surrounding the overlapping area with a line of a predetermined color.

[0112] In the above embodiment, a case where an area of ​​each pixel is used as a partitioned area according to the technology of the present disclosure has been described, but the present disclosure is not limited to this. For example, an area of ​​multiple pixels, such as an area of ​​four adjacent pixels, may be used as a partitioned area according to the technology of the present disclosure.

[0113] Furthermore, in the above embodiment, a radiographic image, which is a transmitted image, is described as an image according to the technology of the present disclosure, but this is not limiting. For example, as described above, a reflected image obtained by capturing an image using an optical camera may be used as an image according to the technology of the present disclosure. That is, because the reflected image is captured through the lens of the optical camera, distortion aberration in the lens causes each partial image to become increasingly distorted as it approaches the periphery. Therefore, even in this case, it is possible to create a high-quality composite image by using the importance level according to the technology of the present disclosure.

[0114] In the above embodiment, the case where the placement information is registered in the placement information database 34 has been described, but the present invention is not limited to this. For example, the placement information may be registered in a private tag of an image defined by DICOM (Digital Imaging and Communications in Medicine), a common standard for medical images.

[0115] Furthermore, in the above embodiment, a case has been described in which a planar radiation detector 14 is used as the radiation detector, and the normal line N is obtained from at least one representative surface that represents the detection surface of the radiation detector 14, but this is not limiting. For example, the normal line N may be obtained from the position where the radiation R lands on the detection surface of the radiation detector.

[0116] That is, when the radiation detector is planar, like the radiation detector 14 according to the above embodiment, the angle of the normal line N is the same regardless of the position of the detection surface of the radiation detector. In contrast, when the radiation detector is a non-planar detector (hereinafter referred to as a "non-planar detector"), the angle of the normal line N changes depending on the position of the detection surface of the non-planar detector.

[0117] 16A and 16B show examples of the arrangement of the radiation source 12, the inspection object O, and the non-planar detector 70 according to this embodiment. Fig. 16A shows an example in which the inspection object O is a pipe, and Fig. 16B shows an example in which the inspection object O has three-dimensional distortion. Note that although Figs. 16A and 16B show an example in which the non-planar detector 70 is separated from the inspection object O, there may also be an embodiment in which the non-planar detector 70 is attached to the surface of the inspection object O.

[0118] As shown in Figures 16A and 16B, in these configurations, the non-planar detector 70 is curved along the surface to be inspected of the object O under inspection, and in these cases, the normal N is obtained at the position where the radiation R lands on the detection surface of the non-planar detector 70.

[0119] In this way, the image processing device and program of the disclosed technology can also be applied to such non-planar detectors 70 that are not planar, and in this case, the same effects as those of the above-mentioned embodiments can be obtained.

[0120] Furthermore, in the above embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the importance derivation unit 20A, the synthesis processing unit 20B, the partial image display processing unit 20C, and the placement information receiving unit 20D. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a programmable logic device (PLD) that is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0121] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0122] Examples of configuring multiple processing units with a single processor include: first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server; second, a form in which a processor is used to realize the functions of an entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs); and thus, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0123] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0124] In the above embodiment, the image processing program 30 is pre-stored (installed) in the storage unit 22 of the image processing device 10, but this is not limiting. The image processing program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The image processing program 30 may also be downloaded from an external device via a network.

[0125] From the above description, the invention described in the following appendix can be understood.

[0126] [Supplementary Note 1] An image processing device comprising at least one processor, the processor performing importance derivation processing on a plurality of images having overlapping regions with each other, the processing deriving importance of predetermined divided regions in the overlapping regions according to an angle between a light ray emitted from a light source or a radiation emitted from a radiation source to obtain the images and a normal to a light receiving surface that receives the light ray or a detection surface that detects the radiation via a subject. [Supplementary Note 2] The image processing device according to Supplementary Note 1, wherein the normal is obtained at a position where the light ray or the radiation lands on the light receiving surface or the detection surface. [Supplementary Note 3] The image processing device according to Supplementary Note 1, wherein the normal is obtained on at least one representative surface that represents the light receiving surface or the detection surface. [Supplementary Note 4] The image processing device according to Supplementary Note 3, wherein the representative plane is any one of a plane located at the center of the light receiving surface or the detection surface, a plane that is closest to the light source or the radiation source, a plane perpendicular to the light ray or the radiation, a plane on which the light ray or the radiation that has passed through the center or center of gravity of the subject lands, and a plane designated by a user. [Supplementary Note 5] The image processing device according to any one of Supplementary Notes 1 to 4, wherein the processor decreases the importance as the angle increases. [Supplementary Note 6] The image processing device according to any one of Supplementary Notes 1 to 5, wherein the processor further performs a synthesis process to create a synthetic image by overlapping the multiple images in the overlapping regions according to the importance. [Supplementary Note 7] The image processing device according to Supplementary Note 6, wherein when the created composite image is displayed and the overlapping area in the displayed composite image is specified by a user, the processor further performs a partial image display process to display the image with the higher importance among the images corresponding to the overlapping area.[Supplementary Note 8] The image processing device according to Supplementary Note 6 or Supplementary Note 7, wherein the processor, when performing the compositing process by moving and overlapping at least one of the plurality of images, and when determining an amount of movement to be actually applied from the plurality of movement amounts using degrees of agreement of the overlapping regions in the plurality of composite images created by performing the compositing process individually with a plurality of candidate movement amounts, determines a degree of contribution of the segmented region to the degree of agreement in accordance with the importance. [Supplementary Note 9] The image processing device according to Supplementary Note 6 or Supplementary Note 7, wherein the processor, when performing the compositing process by transforming and overlapping at least one of the plurality of images, and when determining an amount of deformation to be actually applied from the plurality of deformation amounts using degrees of agreement of the overlapping regions in the plurality of composite images created by performing the compositing process individually with a plurality of candidate deformation amounts, determines a degree of contribution of the segmented region to the degree of agreement in accordance with the importance. [Supplementary Note 10] The image processing device according to any one of Supplementary Notes 6 to 9, wherein the processor determines an image to be adopted from the corresponding plurality of images as the image of the overlapping region in the composite image according to the importance. [Supplementary Note 11] The image processing device according to Supplementary Note 10, wherein the processor determines the image to be adopted to be an image obtained by weighted averaging of images of the corresponding segmented region in the plurality of images, with the corresponding importance as a weighting coefficient. [Supplementary Note 12] The image processing device according to Supplementary Note 10, wherein the processor determines the image to be adopted to be the image having the higher importance among images of the corresponding segmented region in the plurality of images. [Supplementary Note 13] The image processing device according to Supplementary Note 10, wherein the processor determines the image to be adopted to be the image having the higher importance among the plurality of images. [Supplementary Note 14] The image processing device according to any one of Supplementary Notes 1 to 13, wherein the processor receives arrangement information indicating a positional relationship between the light source or the radiation source and the light receiving surface or the detection surface, and derives the angle using the arrangement information. [Supplementary Note 15] The image processing device according to any one of Supplementary Notes 1 to 14, wherein the divided regions are regions for each pixel in the plurality of images.[Supplementary Note 16] The image processing device according to any one of Supplementary Notes 1 to 15, wherein the plurality of images are transmission images. [Supplementary Note 17] A program causing a computer to execute processing relating to a plurality of images having overlapping regions, the program comprising: performing importance derivation processing for deriving importance of predetermined segmented regions in the overlapping regions in accordance with an angle formed between light rays emitted from a light source or radiation emitted from a radiation source to obtain the images and a normal to a light-receiving surface that receives the light rays through a subject or a detection surface that detects the radiation. [Supplementary Note 18] An image processing method executed by a computer, the program comprising: performing importance derivation processing for processing a plurality of images having overlapping regions in accordance with an angle formed between light rays emitted from a light source or radiation emitted from a radiation source to obtain the images and a normal to a light-receiving surface that receives the light rays through a subject or a detection surface that detects the radiation.

[0127] REFERENCE SIGNS LIST 1 Radiation image capturing device 10 Image processing device 12 Radiation source 14 Radiation detector 20 CPU 20A Importance derivation unit 20B Combining processing unit 20C Partial image display processing unit 20D Arrangement information receiving unit 21 Memory 22 Storage unit 23 Display 24 Input device 25 Network I / F 26 External I / F 27 Bus 30 Image processing program 32 Image information database 34 Arrangement information database 40 Importance 42 Partial image 44 Combining boundary 46 Combining image 50 Transmission image 70 Non-planar detector A Angle D Irradiation direction N Normal O Inspection object R Radiation p Protrusion q Protrusion

Claims

1. An image processing device comprising at least one processor, the at least one processor performing importance derivation processing on a plurality of images having overlapping regions, the importance of a predetermined divided region in the overlapping region being determined in accordance with the angle between a light ray emitted from a light source or a radiation emitted from a radiation source to obtain the images, and a normal to a light receiving surface that receives the light ray or a detection surface that detects the radiation via a subject.

2. The image processing device according to claim 1, wherein the normal is obtained at a position where the light ray or the radiation lands on the light receiving surface or the detection surface.

3. The image processing device according to claim 1, wherein the normal is obtained on at least one representative surface that represents the light receiving surface or the detection surface.

4. The image processing device according to claim 3, wherein the representative surface is one of the following surfaces on the light receiving surface or the detection surface: a surface located at the center, a surface that is the shortest distance from the light source or the radiation source, a surface perpendicular to the light ray or the radiation, a surface on which the light ray or the radiation that passes through the center or center of gravity of the subject lands, and a surface indicated by a user.

5. The image processing device according to claim 1 or 2, wherein the at least one processor reduces the importance as the angle increases.

6. The image processing device according to claim 1 or claim 2, wherein the at least one processor further performs a synthesis process to create a synthetic image by overlapping the plurality of images in the overlapping area according to the importance.

7. The image processing device according to claim 6, wherein the at least one processor, when displaying the created composite image and when the overlapping area in the displayed composite image is specified by the user, further performs partial image display processing to display the image with the higher importance among the images corresponding to the overlapping area.

8. The image processing device described in claim 6, wherein, when the synthesis process is performed by moving and overlapping at least one of the multiple images, and when the amount of movement to actually be applied is determined from the multiple amounts of movement using the degree of similarity of the overlapping areas in the multiple synthesized images created by performing the synthesis process individually using multiple candidate amounts of movement, the at least one processor determines the contribution of the divided area to the degree of similarity in accordance with the importance.

9. The image processing device according to claim 6, wherein, when the synthesis process is performed by deforming and overlapping at least one of the plurality of images, and when the amount of deformation to be actually applied is determined from the plurality of deformation amounts using the degree of agreement of the overlapping areas in the plurality of synthesis images created by performing the synthesis process individually using a plurality of candidate deformation amounts, the at least one processor determines the contribution of the segmented area to the degree of agreement in accordance with the importance.

10. The image processing device according to claim 6, wherein the at least one processor determines an image to be adopted from the plurality of corresponding images as the image of the overlapping region in the composite image according to the importance.

11. The image processing device according to claim 10, wherein the at least one processor determines the image to be adopted as an image obtained by weighting the images of the corresponding divided regions in the plurality of images using the corresponding importance as a weighting coefficient.

12. The image processing device according to claim 10, wherein the at least one processor determines the image to be adopted to be the image having the higher importance among the images of the corresponding divided area in the plurality of images.

13. The image processing device according to claim 10, wherein the at least one processor determines the image to be adopted to be the image having the higher importance among the plurality of images.

14. The image processing device according to claim 1 or 2, wherein the at least one processor receives arrangement information indicating a positional relationship between the light source or the radiation source and the light receiving surface or the detection surface, and derives the angle using the arrangement information.

15. An image processing device according to claim 1 or claim 2, wherein the divided regions are regions for each pixel in the plurality of images.

16. The image processing device according to claim 1 or 2, wherein the plurality of images are transparent images.

17. A program that causes a computer to execute processing relating to multiple images having overlapping regions, performing importance derivation processing to derive the importance of predetermined divided regions in the overlapping regions in accordance with the angle between the light rays emitted from a light source or the radiation emitted from a radiation source to obtain the images and the normal to the light receiving surface that receives the light rays or the normal to the detection surface that detects the radiation via the subject.

18. A computer-implemented image processing method for processing a plurality of images having overlapping regions, the method including performing importance derivation processing to derive the importance of predetermined divided regions in the overlapping regions in accordance with the angle between the light rays emitted from a light source or the radiation emitted from a radiation source to obtain the images and the normal to the light receiving surface that receives the light rays or the normal to the detection surface that detects the radiation via the subject.

Images