Image synthesis device, image synthesis method, and image synthesis program

Abstract

To provide an image synthesizer assisting generation of an image to be displayed in a duplicate region among multiple images.SOLUTION: An image synthesizer 100 comprises: a duplicate region extraction unit 103 for extracting a duplicate region among multiple images from an image group photographing a furnace wall of a coke oven; a duplicate region image generation unit 105 for generating a duplicate region image to be displayed on the duplicate region based on the multiple images; a composite image generation unit 106 using a duplicate region image for the duplicate region when generating a composite image of the image group; and a display control unit 107 for making respective display screen 40 display either the duplicate region image or a composite image.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an image synthesis technique for synthesizing a group of images obtained by photographing a surface to be inspected. [Background technology]

[0002] There is a known technique for using images of the surface to be inspected when inspecting an object to be inspected. The technique disclosed in Patent Document 1 sequentially photographs the wall of a coke oven as the object to be inspected, and provides an image of the entire wall by synthesizing the images. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2011-126988 A Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, when synthesizing the images of the entire furnace wall, the images are superimposed so that the image taken earlier is in the foreground. Therefore, in the overlapping area between multiple images, the image taken earlier is always displayed. For this reason, even if an abnormality is captured in the overlapping area of ​​the image taken later, it will be overlooked.

[0005] The present invention has been made in view of the above circumstances, and has as its object to provide an image synthesis device that supports the generation of an image to be displayed in an overlapping area between multiple images. [Means for solving the problem]

[0006] In order to solve the above problems, an image synthesis device of one embodiment of the present invention includes an overlap area extraction unit that extracts overlap areas between multiple images from a group of images taken of the inspected surface of an object to be inspected, an overlap area image generation unit that generates an overlap area image to be displayed in the overlap area based on the multiple images, a composite image generation unit that uses the overlap area image for the overlap area when generating a composite image of the image group, and a display control unit that displays the overlap area image and the composite image on a display screen, respectively.

[0007] According to this aspect, by displaying the overlapping area image on the display screen in addition to the composite image, the user can visually recognize the overlapping area image and perform modification work, etc., as necessary.

[0008] Another aspect of the present invention is an image synthesis device, which includes an overlap area extraction unit that extracts overlap areas between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection target, an importance determination unit that determines the importance of the plurality of images according to the degree of abnormality of the inspection surface reflected in the overlap area, an overlap area image generation unit that generates an overlap area image to be displayed in the overlap area based on the importance, and a synthetic image generation unit that uses the overlap area image in the overlap area when generating a synthetic image of the image group.

[0009] According to this aspect, since the overlap area image is generated based on the importance corresponding to the degree of abnormality reflected in the overlap area of ​​each image, it is possible to prevent the abnormality from being overlooked.

[0010] Yet another aspect of the present invention is an image synthesis method comprising the steps of: extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an object to be inspected; generating an overlapping area image to be displayed in the overlapping area based on the plurality of images; using the overlapping area image for the overlapping area when generating a synthetic image of the group of images; and displaying the overlapping area image and the synthetic image on a display screen, respectively.

[0011] Yet another aspect of the present invention is also an image synthesis method, which includes the steps of: extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection target object; determining the importance of the plurality of images according to the degree of abnormality of the inspection surface reflected in the overlapping area; generating an overlapping area image to be displayed in the overlapping area based on the importance; and using the overlapping area image for the overlapping area when generating a synthetic image of the image group.

[0012] Any combination of the above components, and any transformation of the present invention into a method, device, system, recording medium, computer program, etc., are also effective as aspects of the present invention. Effect of the Invention

[0013] According to the present invention, it is possible to assist in the generation of an image to be displayed in an overlapping area between multiple images. [Brief description of the drawings]

[0014] [Figure 1] FIG. 2 is a side view showing a schematic diagram of a coke oven interior observation device. [Diagram 2] FIG. 2 is a diagram showing a schematic view of the inside of a coke oven. [Diagram 3] 1 is a functional block diagram of an image synthesis device according to an embodiment. [Figure 4] 2A to 2C are diagrams illustrating image selection, overlapping area extraction, and importance determination processes performed by the image synthesis device. [Diagram 5] 11A and 11B are diagrams illustrating examples of display on a display screen by a display control unit. [Figure 6] 4 is a flowchart showing a process of the image synthesis device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, the embodiments for carrying out the present invention will be described in detail with reference to the drawings. In the description and drawings, the same or equivalent components, members, and processes are given the same reference numerals, and duplicated descriptions are omitted as appropriate. The scale and shape of each part shown in the drawings are set for convenience in order to facilitate the description, and are not to be interpreted as being limiting unless otherwise specified. The embodiments are illustrative and do not limit the scope of the present invention in any way. All features and combinations thereof described in the embodiments are not necessarily essential to the invention.

[0016] The image synthesis device of the present invention can be used to inspect any object to be inspected. Therefore, the object to be inspected is not particularly limited, but in this embodiment, the wall of a coke oven similar to that of Patent Document 1 will be described as an example. Other examples of the object to be inspected will be described later.

[0017] Fig. 1 is a side view showing a typical furnace interior observation device. This furnace interior observation device is used to observe the interior of the carbonization chamber of a coke oven (hereinafter, also simply referred to as a coke oven). Fig. 2 is a diagram showing a typical interior of a coke oven.

[0018] The coke oven 10 is a narrow oven with a pair of brick oven walls 11 facing each other. Each oven wall 11 extends from an oven inlet 12 on one side of the coke oven 10 to an oven outlet 13 on the other side, with a total length of, for example, several tens of meters. The distance between the opposing oven walls 11 is, for example, several tens of centimeters. The height from the bottom 15 to the ceiling 14 of the coke oven 10 is, for example, several meters.

[0019] The pusher 20 shown in FIG. 1 repeatedly moves back and forth within the coke oven 10. On the way thereto, the pusher 20 is inserted into the coke oven 10 from the oven entrance 12, and pushes out the coke C generated by carbonization in the coke oven 10 to the oven exit 13. On the way back, the pusher 20 returns from the oven exit 13 to the oven entrance 12 within the coke oven 10. The pusher 20 includes a pusher plate 21 and a beam 22, and the beam 22 connects the pusher plate 21 to a driving device (not shown). This driving device allows the pusher plate 21 to move freely between the oven entrance 12 and the oven exit 13 of the coke oven 10. Since the pusher plate 21 has the same shape as the cross section of the coke oven 10, the coke C can be pushed out by the movement of the pusher plate 21.

[0020] The camera 30 continuously photographs the oven wall 11 while moving between the oven inlet 12 and the oven outlet 13 in the coke oven 10 together with the pushing device 20. The camera 30 may be a still camera that continuously photographs still images, or a video camera that photographs moving images. The camera 30 is attached to a support base installed on the back of the push plate 21 or behind the push plate 21. The camera 30 includes two cameras that are attached facing the left and right oven walls 11, respectively, and can photograph front-view images of the oven walls 11 on both the left and right sides. In order to photograph the entire left and right oven walls 11, the two cameras may be photographed while changing the angle somewhat in the vertical direction. Note that the camera 30 may be attached so as to face in the opposite direction (to the right in FIG. 1) to the extrusion direction of the coke C by the pushing device 20 so that the view is not obstructed by the push plate 21 or the coke C. In that case, the camera 30 is installed directly facing the oven inlet 12, and can photograph the oven walls 11 on both the left and right sides as oblique images. In order to protect the camera 30 from the high-temperature environment (eg, 1000° C. or higher) inside the coke oven 10, thermal measures are taken, such as housing the camera in a heat-resistant housing or a cooling box.

[0021] 3 is a functional block diagram of the image synthesis device 100 according to the embodiment. The image synthesis device 100 includes an image processing unit 101, an image selection unit 102, an overlapping area extraction unit 103, an importance determination unit 104, an overlapping area image generation unit 105, a synthesis image generation unit 106, a display control unit 107, and an overlapping area image change unit 108. The camera 30 and the image memory 31 constitute an image input unit that inputs a group of images of the furnace wall 11 as the inspected surface of the inspection object to the image synthesis device 100. The display screen 40 displays the processing contents of the image synthesis device 100. The operation unit 50 is composed of an input device such as a touch panel integrated with the display screen 40 or a keyboard or mouse separate from the display screen 40, and generates various control information for the image synthesis device 100 based on the user's operation.

[0022] The image memory 31 stores a group of images of the oven wall 11 continuously photographed by the camera 30. The image memory 31 may be a built-in memory of the camera 30 or a general-purpose removable medium such as a memory card. It may also be a storage outside the coke oven 10 that can communicate with the camera 30 by wire or wirelessly. The image synthesis device 100 executes each process described later on the group of images stored in the image memory 31. Here, if the camera 30 and the image synthesis device 100 can communicate by wire or wirelessly and the image synthesis device 100 can acquire and process the images photographed by the camera 30 in real time, it is not necessary to store all images in the image memory 31, and the image memory 31 can be unnecessary or can have a small capacity. The image memory 31 may also store a front view image of the oven wall surface photographed by the camera 30 and other images.

[0023] The image processing unit 101 calculates position information based on two-dimensional coordinates on the inspection surface of each front view image of the oven wall 11 provided from the camera 30 or the image memory 31. The position of the camera 30 along the extrusion direction (left and right direction in FIG. 1) when the camera 30 captures a series of front view images of the oven wall 11 and the tilt angle of the camera 30 in the up and down direction are measured by a sensor (not shown), and the two-dimensional coordinates of each front view image can be calculated based on the measurement information. The sensor that measures the position of the camera 30 may be a position sensor that directly measures the position of the camera 30 along the extrusion direction in the coke oven 10, or an encoder that measures the extrusion amount of the extrusion device 20. When the image of the oven wall 11 provided from the camera 30 or the image memory 31 is an oblique image, the image processing unit 101 may convert the viewpoint of the oblique image to generate a front view image of the oven wall 11 as the inspection surface. Based on the measurement information of each of the above sensors, the oblique image can be converted into a front view image using existing technology.

[0024] The image selection unit 102 selects an image pair from the front view image group to be used in each process of the overlap area extraction unit 103, the importance determination unit 104, and the overlap area image generation unit 105, which will be described later. As shown on the left side of FIG. 4, while the extrusion device 20 moves between the furnace entrance 12 and the furnace exit 13, the camera 30 captures an image group 32 consisting of N images 321 to 32N (N is any natural number equal to or greater than 2) (t1 to tN represent the respective capture times). The image selection unit 102 selects an arbitrary image pair from the N images 321 to 32N. Since the main purpose of this selection process is to extract the overlap area, which will be described later, it is preferable to preferentially select an image pair captured at close capture times, which is likely to have overlapping capture locations. In the following, an example will be described in which an image 32i captured at capture time ti and an image 32i+1 captured at capture time ti+1 are selected. The image selection unit 102 may select an image pair based on the user's operation of the operation unit 50. Alternatively, a total of NC2 image pairs may be selected in sequence in a round-robin manner.

[0025] The overlapping area extraction unit 103 extracts the overlapping area of ​​the image pair selected by the image selection unit 102. As shown in the center of FIG. 4, if the position coordinates of the center of the i-th image 32i are expressed as (Xi, Yi) and the position coordinates of the center of the i+1-th image 32i+1 are expressed as (Xi+1, Yi+1), when the absolute value of the difference in the X coordinates of both images is smaller than a certain image width w and the absolute value of the difference in the Y coordinates of both images is smaller than a certain image height h, both images have an overlapping area D. Conversely, if there is no overlapping area D in the selected image pair, the process returns to the process of the image selection unit 102 and another image pair is selected. Note that, if the position information of the camera 30 in the coke oven 10 cannot be obtained and the position coordinates of each image are unknown, the overlapping image areas may be extracted by extracting feature points of each image using a corner detection method or the like and matching them.

[0026] The importance determination unit 104 determines the importance based on a comparison of the overlapping areas of each image constituting the image pair. Specifically, the importance determination unit 104 determines the importance according to the degree of abnormality of the inspected surface reflected in each overlapping area and the sharpness of each overlapping area. As shown on the right side of FIG. 4, the degree of abnormality and the sharpness of the overlapping area image Di included in the i-th image 32i and the overlapping area image Di+1 included in the i+1-th image 32i+1 are compared. Note that the images 32i and 32i+1 are images taken consecutively in time, and ideally the degree of abnormality and the sharpness do not change between the two images. However, the brightness and temperature inside the coke oven 10, which is in a red-hot environment, are prone to sudden changes, and unexpected noise is also likely to occur, so a large difference may occur even between images that are consecutive in time.

[0027] Examples of types of abnormalities or damage occurring in the oven wall 11 of the coke oven 10 as the surface to be inspected include spalling, which is the destruction of the oven wall 11 due to distortion caused by rapid heating or cooling, adhesion of carbon derived from coal, which is the raw material of coke, to the oven wall 11, and deterioration of the joints of the bricks that make up the oven wall 11. The importance determination unit 104, which has previously machine-learned these types of abnormalities, accurately detects abnormalities reflected in each overlap area image Di, Di+1, and scores the degree of abnormality based on a predetermined algorithm. Then, a high importance is assigned to the overlap area image (Di or Di+1) with a high abnormality score. Note that the algorithm for calculating the abnormality score can be appropriately designed according to the purpose, but it is preferable to take into account the ratio (area ratio) of the abnormal area in the overlap area. In addition, it is also possible to design it so that a weight is assigned to a specific type of abnormality (e.g. spalling) with a high priority, and a high score is assigned when the abnormality is present.

[0028] In determining the sharpness of the overlap region images Di and Di+1, it is preferable to use an image quality evaluation method that takes into account the characteristics of the human eye so that a high importance is given to an image with high sharpness for a human user of the image synthesis device 100. For example, an existing image quality evaluation method such as NIQE (Natural Image Quality Evaluator) can be used.

[0029] The overlap area image generating unit 105 generates an overlap area image to be displayed in the overlap area D based on the importance determined by the importance determining unit 104 for the overlap area images Di and Di+1. When it is acceptable to use either of the images Di and Di+1, for example, when the importance of both images is equal to or greater than a predetermined upper threshold or equal to or less than a predetermined lower threshold, the average value of the images Di and Di+1 for each pixel is used as the overlap area image. Alternatively, either of the images Di and Di+1 may be arbitrarily selected as the overlap area image. Also, when the importance of at least one of the images Di and Di+1 is greater than the lower threshold and less than the upper threshold, the image with the higher importance (Di or Di+1) is used as the overlap area image. As described above, the overlap area image is generated based on an image with a higher importance, that is, an image with a severe abnormality on the inspection surface or an image with high clarity, so that the user's visual inspection can be effectively supported.

[0030] As a modified example of the overlap region image generating unit 105, the overlap region image may be obtained by taking a weighted average of each pixel value based on the importance of each image Di and Di+1 without using the upper and lower thresholds as described above. That is, when the importance of image Di is Wi, the importance of image Di+1 is Wi+1, each pixel value of image Di is Pi, and each pixel value of image Di+1 is Pi+1, each pixel value P of the overlap region image can be expressed as Wi×Pi+Wi+1×Pi+1. In this case, the importance is normalized so that Wi+Wi+1=1. In addition, although the overlap region image is generated in units of each image Di and Di+1 in the above, importance determination and overlap region image generation may be performed in units of partial images obtained by dividing each image Di and Di+1. For example, if each of images Di and Di+1 is divided into partial image 1 and partial image 2, the importance of image Di will be higher in partial image 1, and the importance of image Di+1 will be higher in partial image 2, so that an overlapping area image can be generated using image Di as partial image 1 and image Di+1 as partial image 2.

[0031] The composite image generating unit 106 generates a composite image of a series of image pairs processed by the image selecting unit 102, the overlapping area extracting unit 103, the importance determining unit 104, and the overlapping area image generating unit 105. An example of the composite image is shown in the composite image display unit 41 in the upper part of FIG. 5. This composite image is obtained by combining the image group 32 shown in FIG. 4 into an entire image of the furnace wall 11. There are overlapping areas between the images constituting the composite image, and the overlapping area image generated by the overlapping area image generating unit 105 is used for these overlapping areas. As shown in the figure, the overlapping areas are displayed in a manner different from the other non-overlapping areas in order to draw the attention of the user who views them.

[0032] The display control unit 107 displays the processing contents of the image synthesis device 100 on the display screen 40. Fig. 5 shows an example of display on the display screen 40 by the display control unit 107. The above-mentioned synthetic image display unit 41 is provided in the upper part of Fig. 5. The lower part of Fig. 5 is provided, in order from the left, with a contrast image display unit 42, an individual synthetic image display unit 43, and an overlap area image editing unit 44.

[0033] The contrast image display unit 42, the individual composite image display unit 43, and the overlapping area image editing unit 44 display the image pair selected by the image selection unit 102 based on the user's operation of the operation unit 50 from among the whole image in different modes, and the overlapping area image thereof. There are two methods for selecting an image pair by the operation unit 50. In the first method, when the user selects an arbitrary area of ​​the composite image display unit 41 by a touch operation, a pointer, or the like, the image pair closest thereto, or the image pair including the closest overlapping area thereto, is selected. In the second method, when the user presses the image switching unit 45 indicated by a pair of arrows in opposite directions by a touch operation, a pointer, or the like, the image pair is switched to a temporally or spatially adjacent image pair. Specifically, when the rightward arrow, meaning "forward," is pressed, the image pair is switched to the image pair one step later in time or the image pair adjacent to the right in space, and when the leftward arrow, meaning "back," the image pair is switched to the image pair one step earlier in time or the image pair adjacent to the left in space. As described below, the contrast image display unit 42, the individual composite image display unit 43, and the overlap area image editing unit 44 all display the overlap area image to be displayed in the overlap area. Therefore, the display control unit 107 causes the composite image display unit 41 to display the composite image, and at the same time causes the contrast image display unit 42, the individual composite image display unit 43, and the overlap area image editing unit 44 to display the overlap area image.

[0034] The contrast image display unit 42 displays a contrast image for comparing the selected image pair. The contrast image displays the images constituting the image pair side by side, as in the right side of Fig. 4, and highlights overlapping areas in a different manner from non-overlapping areas. This draws the user's attention to the overlapping areas, allowing them to visually compare and examine them.

[0035] The individual composite image display unit 43 displays an individual composite image obtained by individually compositing the selected image pairs. For the overlapping areas in the individual composite images, the overlapping area images generated by the overlapping area image generation unit 105 are used. As with the comparison images, the overlapping areas are highlighted in a manner different from the non-overlapping areas. This draws the user's attention to the overlapping areas, enabling the user to closely examine the composition results in the overlapping areas.

[0036] The overlap area image editing unit 44 enlarges and displays the overlap area image of the selected image pair, and edits it based on the user's operation of the operation unit 50. In the functional block diagram of FIG. 3, the overlap area image changing unit 108 realizes the function, changes the overlap area image based on the user's operation of the operation unit 50, and overwrites the overlap area image generated by the overlap area image generating unit 105. After the editing is completed, when the user presses the update button 46 of FIG. 5 based on the operation of the operation unit 50, the editing content is reflected in the overall composite image of the composite image display unit 41 and the individual composite image of the individual composite image display unit 43. The editing content by the overlap area image editing unit 44 is not particularly limited, and may be, for example, various image filters for emphasizing an abnormality on the inspection surface, or may be able to adjust the brightness, saturation, and hue of all or part of the overlap area image, or may be able to be directly drawn on the overlap area image by the user. In addition, by pressing the load button 47 in FIG. 5, an overlap area image that has been edited outside the image synthesis device 100 can be loaded, and by pressing the save button 48, the overlap area image can be saved for editing outside the image synthesis device 100.

[0037] FIG. 6 is a flowchart showing the processing of the image synthesis device 100 described above. In this figure, "S" means step. In S1, the camera 30 and the image memory 31 input a group of images of the inspected surface of the inspection object to the image synthesis device 100. In S2, the image processing unit 101 calculates position information of each input front view image by two-dimensional coordinates on the inspected surface. Also, when the input image is an oblique image, the image processing unit 101 converts the viewpoint of each oblique image to generate each front view image and calculates its position information.

[0038] In S3, the image selection unit 102 selects an image pair to be used in each process of the overlap region extraction unit 103, the importance determination unit 104, and the overlap region image generation unit 105. In S4, the overlap region extraction unit 103 extracts the overlap region of the image pair selected in S3. If an overlap region is not extracted in S4, the process skips the following S5 and S6 and proceeds to S7, and if there are unprocessed images, the process returns to S3 again to select another unprocessed image pair. If an overlap region is extracted in S4, the process proceeds to S5, and the importance determination unit 104 determines the importance based on a comparison of the overlap regions of each image constituting the image pair. In S6, the overlap region image generation unit 105 generates an overlap region image to be displayed in the overlap region based on the importance determined in S5. In S7, it is determined whether there are unprocessed images. If there are unprocessed images, the process returns to S3 to select another unprocessed image pair, and the processes of S3 to S7 are repeated until there are no more unprocessed images.

[0039] In S8, the composite image generating unit 106 generates a composite image of the series of image pairs processed in S3 to S6. Specifically, an overall composite image to be displayed on the composite image display unit 41 in FIG. 5 and an individual composite image to be displayed on the individual composite image display unit 43 are generated. In S9, the display control unit 107 causes the display screen 40 to display the processing contents of the image synthesis device 100. Specifically, the composite image display unit 41 displays the overall composite image, the contrast image display unit 42 displays the contrast image, the individual composite image display unit 43 displays the individual composite image, and the overlapping area image editing unit 44 displays the overlapping area image. Note that the image pair to be displayed first on the contrast image display unit 42, the individual composite image display unit 43, and the overlapping area image editing unit 44 can be set arbitrarily. For example, the image pair at the left end of the overall composite image is displayed first. The selection of this image pair can be changed by the image selection unit 102 based on the user's operation of the operation unit 50 in S10, and the display can be updated in S11. In addition, if the overlap area image change unit 108 changes the overlap area image based on the user's operation of the operation unit 50 in S10, the overlap area image generated in S6 is overwritten, and the display is updated in S11 by pressing the update button 46.

[0040] The present invention has been described above based on the embodiments. The embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of each component and each treatment process, and that such modifications are also within the scope of the present invention.

[0041] In the embodiment, the coke oven 10 has been described as an example of the object to be inspected by the image synthesis device 100, but the object to be inspected is not limited to this. For example, the object to be inspected may be various industrial machines (including coke ovens) such as boilers and construction machines, social infrastructure such as bridges, various industrial structures such as environmental plants and water treatment facilities, or other industrial facilities, and the surface to be inspected may be an internal or external surface of such industrial facilities. In addition, a camera that captures the image group of these surfaces to be inspected may be attached to a mobile body of any configuration that can move along the surface to be inspected. For example, the camera may be attached to an aircraft such as a so-called drone.

[0042] The functional configuration of each device described in the embodiment can be realized by hardware resources, software resources, or by the cooperation of hardware resources and software resources. A processor, ROM, RAM, and other LSIs can be used as hardware resources. An operating system, an application, and other programs can be used as software resources. [Explanation of symbols]

[0043] 10 Coke oven, 11 Oven wall, 20 Pushing device, 30 Camera, 32 Image group, 40 Display screen, 41 Composite image display unit, 42 Contrast image display unit, 43 Individual composite image display unit, 44 Overlap area image editing unit, 45 Image switching unit, 50 Operation unit, 100 Image synthesis device, 101 Image processing unit, 102 Image selection unit, 103 Overlap area extraction unit, 104 Importance determination unit, 105 Overlap area image generation unit, 106 Composite image generation unit, 107 Display control unit, 108 Overlap area image change unit.

Claims

1. an overlapping area extracting unit that extracts overlapping areas between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; an importance determination unit that determines an importance based on a comparison of the overlapping regions of the plurality of images; an overlap area image generating unit that generates an overlap area image to be displayed in the overlap area based on the plurality of images and the importance of each of the images; a composite image generating unit that uses the overlapping area image for the overlapping area when generating a composite image of the image group; a display control unit that displays the overlapping area image and the composite image on a display screen; Equipped with the importance determination unit scores the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigns a high importance to an image having a high abnormality score; The overlapping area image generating unit generates the overlapping area image based on at least the image having the highest abnormality score among the plurality of images. Image synthesis device.

2. an overlapping area image changing unit that changes the overlapping area image on the display screen based on a user operation; The composite image generating unit uses the modified overlap area image for the overlap area. The image synthesis device according to claim 1 .

3. the display control unit causes a comparison image for comparing the plurality of images to be displayed on the display screen; In the comparison image, the overlapping area is displayed in a manner different from the other areas.

3. The image synthesis device according to claim 1.

4. the display control unit causes the display screen to display an individual composite image obtained by individually combining the plurality of images; The overlapping area image is used for the overlapping area in the individual composite image.

4. The image synthesis device according to claim 1.

5. an image selection unit that selects the plurality of images for which the overlapping area image is to be displayed on the display screen based on a user operation; 5. The image synthesis device according to claim 1.

6. The image selection unit selects a plurality of images that are closest to a position selected based on a user operation in the composite image.

6. The image synthesis device according to claim 5.

7. The image selection unit switches between a plurality of images that are adjacent in time or space based on a user operation.

7. The image synthesis device according to claim 5.

8. an overlapping area extracting unit that extracts overlapping areas between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; an importance determining unit that determines an importance of the plurality of images according to a degree of abnormality of the inspection surface reflected in the overlapping area; an overlap area image generating unit that generates an overlap area image to be displayed in the overlap area based on the importance; a composite image generating unit that uses the overlapping area image for the overlapping area when generating a composite image of the image group; Equipped with the importance determination unit scores the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigns a high importance to an image having a high abnormality score; The overlapping area image generating unit generates the overlapping area image based on at least the image having the highest abnormality score among the plurality of images. Image synthesis device.

9. The importance determining unit determines the importance of the plurality of images according to the clarity of the overlapping areas. The image synthesis device according to claim 8.

10. Extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; determining an importance based on a comparison of the overlapping regions of the plurality of images; generating an overlap region image to be displayed in the overlap region based on the plurality of images and the importance of each of the images; using the overlap region image for the overlap region when generating a composite image of the images; displaying the overlapping area image and the composite image on a display screen; Equipped with The step of determining the importance includes scoring the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigning a high importance to an image having a high abnormality score; The step of generating an overlapping region image includes generating the overlapping region image based on at least the image having the highest anomaly score among the plurality of images. Image synthesis method.

11. Extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; determining a level of importance of the plurality of images according to a degree of abnormality of the inspection surface reflected in the overlapping area; generating an overlap area image to be displayed in the overlap area based on the importance; using the overlap region image for the overlap region when generating a composite image of the images; Equipped with The step of determining the importance includes scoring the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigning a high importance to an image having a high abnormality score; The step of generating an overlapping region image includes generating the overlapping region image based on at least the image having the highest anomaly score among the plurality of images. Image synthesis method.

12. Extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; determining an importance based on a comparison of the overlapping regions of the plurality of images; generating an overlap region image to be displayed in the overlap region based on the plurality of images and the importance of each of the images; using the overlap region image for the overlap region when generating a composite image of the images; displaying the overlapping area image and the composite image on a display screen; Run the following on your computer: The step of determining the importance includes scoring the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigning a high importance to an image having a high abnormality score; The step of generating an overlapping region image includes generating the overlapping region image based on at least the image having the highest anomaly score among the plurality of images. Image compositing program.

13. Extracting an overlapping area between a plurality of images from a group of images obtained by photographing an inspection surface of an inspection object; determining a level of importance of the plurality of images according to a degree of abnormality of the inspection surface reflected in the overlapping area; generating an overlap area image to be displayed in the overlap area based on the importance; using the overlap region image for the overlap region when generating a composite image of the images; Run the following on your computer: The step of determining the importance includes scoring the degree of abnormality of the inspection surface reflected in the overlapping area for the plurality of images, and assigning a high importance to an image having a high abnormality score; The step of generating an overlapping region image includes generating the overlapping region image based on at least the image having the highest anomaly score among the plurality of images. Image compositing program.

Images