Image-processing device, image-processing method, and image-processing program

Abstract

An acquisition unit 36 acquires an input image showing a chart for evaluating images, the input image being input from a radiation image photographing device to a control device. A detection unit 38 detects, from the acquired input image, the chart in the input image by using chart pattern information determined in advance. An evaluation unit 40 evaluates the input image by using the result of detecting the chart.

Description

Image processing device, image processing method, and image processing program

[0001] The present disclosure relates to an image processing device, an image processing method, and an image processing program.

[0002] JP 2024-28042 A discloses an information processing device that performs processing to correct defective pixels in a radiographic image obtained by radiographing a physical phantom on which a test pattern is formed, the information processing device including a processor, wherein the processor inputs an image based on the radiographic image into a first machine-learned model to detect an area including the test pattern, determines the edge direction of the test pattern within the area, treats defective pixels within the area as pixels to be corrected, and corrects the pixels to be corrected using normal pixels within the area that are present in the edge direction from the pixels to be corrected, other than the defective pixels.

[0003] Japanese Patent Application Laid-Open No. 2004-150908 discloses a non-destructive inspection method that eliminates cumbersome manual operations by capturing an image of an inspection object and an image quality confirmation pattern and automating the image quality confirmation process.

[0004] Japanese Patent Publication No. 2004-81331 discloses a sharpness measuring method for measuring the sharpness of a radiographic apparatus by photographing a chart and analyzing the chart image.

[0005] During medical or non-destructive X-ray imaging, a chart is photographed and the image is analyzed to evaluate the image, such as its resolution and / or contrast, in order to perform a proper diagnosis and / or examination.

[0006] Furthermore, the captured image is corrected and / or the photographing device is adjusted based on the evaluation result of the captured image.

[0007] However, when evaluating a photographed image based on a chart, it is necessary to take the time to specify the chart itself and / or each part of the chart to be evaluated in the photographed image, and in particular, when the position of the chart is not fixed, it is necessary to take the time to find the position of the chart in the photographed image.

[0008] The present disclosure has been made in consideration of the above facts, and provides an image processing device, an image processing method, and an image processing program that can easily evaluate an input image containing a chart without the need to specify the chart itself and / or the part of the chart that is to be evaluated in the input image.

[0009] In order to achieve the above object, an image processing device according to a first aspect of the present disclosure includes a processor, which detects a chart in an input image containing a chart for evaluating the image using predetermined pattern information of the chart, and performs processing to evaluate the input image using the chart detection results.

[0010] 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 processor evaluates the input image further using the input image and evaluation information required for evaluating the chart.

[0011] 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 input image is an X-ray transmission image.

[0012] An image processing device according to a fourth aspect of the present disclosure is the image processing device according to the first aspect, wherein the processor receives a range in the input image in which to detect a chart, and detects the chart from the received range.

[0013] An image processing device according to a fifth aspect of the present disclosure is the image processing device according to the second aspect, wherein the processor identifies relative position information of at least some of the patterns obtained from the evaluation information based on the state of the chart identified from the detected chart, and evaluates the input image based on the identification result.

[0014] An image processing device according to a sixth aspect of the present disclosure is an image processing device according to the first aspect, wherein the pattern information is information on a portion of the chart that includes at least one of a clear portion, a portion with little individual variation, and a portion with little distortion, information on a portion of the chart that does not include text, or information that includes machine learning parameters.

[0015] An image processing device according to a seventh aspect of the present disclosure is the image processing device according to the second aspect, wherein the evaluation information includes information of a portion different from the pattern information of the chart, or information obtained from the pattern information of the chart.

[0016] An image processing device according to an eighth aspect of the present disclosure is an image acquisition processing device according to the first aspect, in which the processor evaluates at least one of the presence or absence, number, type, position, angle, scale, and shape of a chart, and at least one of the contrast of the chart.

[0017] An image processing device according to a ninth aspect of the present disclosure is the image processing device according to the first aspect, wherein the processor further performs processing to display at least one of the presence or absence, number, type, position, angle, scale, and shape of the detected chart.

[0018] An image processing device according to a tenth aspect of the present disclosure is the image processing device according to the third aspect, wherein the chart is a multi-linear image quality meter.

[0019] An image processing device according to an eleventh aspect of the present disclosure is the image processing device according to the tenth aspect, wherein the pattern information is information about a pattern including at least one of the first to sixth line pairs of the multi-linear image quality meter.

[0020] An image processing device according to a twelfth aspect of the present disclosure is the image processing device according to the tenth aspect, wherein the processor evaluates the input image further using the input image and evaluation information including information of at least one line pair of the multi-linear image quality meter as information necessary for evaluating the chart.

[0021] An image processing device according to a thirteenth aspect of the present disclosure is the image processing device according to the twelfth aspect, wherein the evaluation information includes information on line pairs that are not included in the chart pattern.

[0022] An image processing device according to a fourteenth aspect of the present disclosure is the image processing device according to the twelfth aspect, wherein the processor evaluates the contrast of at least one line pair.

[0023] An image processing device according to a fifteenth aspect of the present disclosure is the image processing device according to the twelfth aspect, wherein the processor evaluates the input image by calculating a one-dimensional density profile.

[0024] An image processing device according to a sixteenth aspect of the present disclosure is the image processing device according to the tenth aspect, in which the processor evaluates the input image further using the input image and evaluation information including information on the start and end points of the line pairs as information necessary for evaluating the chart.

[0025] An image processing device according to a seventeenth aspect of the present disclosure is an image processing device according to the tenth aspect, wherein the processor evaluates at least one of whether the angle of the multi-linear image quality meter is within a predetermined range, whether the number of multi-linear image quality meter is within a predetermined range, whether the angles between the multi-linear image quality meter and the multi-linear image quality meter are within a predetermined range if there are two, and the scale.

[0026] An image processing device according to an eighteenth aspect of the present disclosure is the image processing device according to the tenth aspect, wherein the processor detects at least one line pair of the multi-linear image quality meter to evaluate the input image.

[0027] An image processing device according to a 19th aspect of the present disclosure is the image processing device according to the 10th aspect, wherein the processor further performs processing to display the start and end points of the multi-linear image quality meter, the evaluation result of at least one line pair, and at least one of the one-dimensional density profiles.

[0028] An image processing device according to a twentieth aspect of the present disclosure is the image processing device according to the third aspect, wherein the chart is a perforated penetrometer.

[0029] An image processing device according to a twenty-first aspect of the present disclosure is the image processing device according to the twentieth aspect, wherein the pattern information includes information of a pattern including characters.

[0030] An image processing device according to a 22nd aspect of the present disclosure is the image processing device according to the 20th aspect, wherein the processor evaluates the input image further using the input image and evaluation information including information of at least one hole as information necessary for evaluating the chart.

[0031] An image processing device according to a twenty-third aspect of the present disclosure is the image processing device according to the twenty-second aspect, wherein the processor evaluates the contrast of at least one hole.

[0032] An image processing device according to a twenty-fourth aspect of the present disclosure is the image processing device according to the twenty-second aspect, wherein the processor evaluates the input image by detecting at least one hole in the perforated penetrometer.

[0033] An image processing device according to a twenty-fifth aspect of the present disclosure is the image processing device according to the twentieth aspect, wherein the processor further performs processing to display an evaluation result of at least one hole of the perforated penetrometer.

[0034] An image processing device according to a twenty-sixth aspect of the present disclosure is the image processing device according to the second aspect, wherein at least one of the chart pattern information and the chart evaluation information is registered by a user.

[0035] An image processing method according to a 27th aspect of the present disclosure performs processing that includes detecting a chart in an input image containing a chart for evaluating the image using predetermined pattern information of the chart, and evaluating the input image using the chart detection results.

[0036] An image processing program according to a twenty-eighth aspect of the present disclosure is an image processing program for causing a computer to execute processing including detecting a chart in an input image showing a chart for evaluating the image using predetermined pattern information of the chart, and evaluating the input image using the chart detection result.

[0037] According to the present disclosure, it is possible to provide an image processing device, an image processing method, and an image processing program that can easily evaluate an input image that includes a chart without having to specify the chart itself and / or the part of the chart that is to be evaluated in the input image.

[0038] 1 is a block diagram showing an example of the configuration of a main part of a control device, which is a block diagram showing an example of the overall configuration of a radiographic image capturing system according to the present embodiment; FIG. 2 is a functional block diagram showing the functional configuration of a control unit in the control unit of the radiographic image capturing system according to the present embodiment; FIG. 3 is a flowchart showing an example of the flow of processing performed by the control unit in the control unit of the radiographic image capturing system according to the present embodiment; FIG. 4 is a diagram showing an example of chart pattern information used when detecting a chart in an input image using chart pattern information; FIG. 5 is a diagram showing an example of an input image in which a chart is captured; FIG. 6 is a diagram showing an example of a result of chart detection; FIG. 7 is a diagram showing an example of a pattern when the chart is a Duplex type IQI chart; FIG. 8 is a diagram for explaining an example of chart evaluation information when the chart is a Duplex type IQI chart; FIG. 9 is a diagram showing another first example of chart pattern information; FIG. 10 is a diagram showing another second example of chart pattern information; FIG. 11 is a diagram for explaining an example of chart evaluation information; FIG. 12 is a diagram showing an example of a display of evaluation results; FIG. 13 is a diagram showing an example of a Hole type IQI chart; FIG. 14 is a diagram showing an example of a Wire type IQI chart.

[0039] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings, but the present invention is not limited to the embodiment.

[0040] In this embodiment, a radiographic image capturing system including a control device as an example of an image processing device will be described as an example. Fig. 1 is a block diagram showing an example of the overall configuration of a radiographic image capturing system according to this embodiment.

[0041] As shown in FIG. 1, the radiation image capturing system 10 includes a radiation irradiation device 12, a radiation image capturing device 16, and a control device 18.

[0042] The radiation irradiator 12 according to this embodiment includes a radiation source 14 that irradiates a subject W, which is an example of an imaging target, with radiation R, such as X-rays (X-rays). The method of instructing the radiation irradiator 12 to irradiate radiation R is not particularly limited. For example, if the radiation irradiator 12 includes an irradiation button or the like, a user such as a radiologist may issue an instruction to irradiate radiation R using the irradiation button, thereby irradiating radiation R from the radiation irradiator 12. Alternatively, for example, a user such as a radiologist may issue an instruction to irradiate radiation R by operating the control device 18, thereby irradiating radiation R from the radiation irradiator 12.

[0043] When the radiation irradiating device 12 receives an instruction to irradiate radiation R, it irradiates radiation R from the radiation source 14 in accordance with irradiation conditions such as set tube voltage, tube current, and irradiation period. Note that, hereinafter, the dose of radiation R will be referred to as the "radiation dose."

[0044] The radiographic imaging device 16 according to this embodiment includes a radiation detector 20 that detects radiation R that is irradiated from the radiation irradiation device 12 and passes through the subject W. The radiographic imaging device 16 uses the radiation detector 20 to capture a radiographic image of the subject W.

[0045] 2, the control device 18 includes a control unit 22, a display unit 32, an operation unit 34, and a communication I / F (interface) unit 35. FIG. 2 is a block diagram showing an example of the configuration of the main parts of the control device 18.

[0046] The main part of the control unit 22 is configured as a general computer, and controls the overall operation of the control device 18 .

[0047] The control unit includes a CPU 24, a ROM 26, and a RAM 28. The ROM 26 pre-stores various programs 30 executed by the CPU 24, such as an image capture processing program and / or a display processing program executed when controlling image capture. The RAM 28 temporarily stores various data.

[0048] The display unit 32 displays a screen for operating the radiation irradiating device 12 and / or the radiation image capturing device 16, captured radiation images, etc. The display unit 32 is, for example, a direct-view electronic display.

[0049] The operation unit 34 is used by the user to input instructions and / or various information related to photography, etc. The operation unit 34 is not particularly limited, and examples thereof include various switches, a touch panel, a touch pen, and a mouse.

[0050] The communication I / F unit 35 communicates captured images such as radiographic images and various information between the radiation irradiating device 12 and the radiographic image capturing device 16 via wireless communication or wired communication.

[0051] During radiography for medical or non-destructive testing, a chart is captured to perform proper diagnosis and / or testing, and the captured image is analyzed to determine resolution and / or contrast, thereby evaluating the captured radiographic image. Based on the evaluation results, the radiographic image is corrected and / or the radiographic imaging device 16 is adjusted. For example, during radiography for non-destructive testing, an Image Quality Indicator (IQI) is used as a chart for evaluating the image. Types of IQI include a duplex type (multi-linear image quality meter), a hole type (hole type penetrometer), and a wire type (wire type penetrometer).

[0052] However, when evaluating a radiographic image based on a chart, it is time-consuming to specify the chart itself and / or each part of the chart to be evaluated in the radiographic image, and particularly when the position of the chart is not fixed, it is time-consuming to find the position.

[0053] Furthermore, checking whether or not charts are present in the captured radiographic image, as well as their number and type, requires time and effort and / or errors. Specifically, a duplex-type IQI (multi-linear image quality meter) requires one or two charts to be placed in the captured image, and a hole-type IQI (perforated transmittance meter) requires a specific type of chart depending on the subject being imaged. However, checking the presence, number and type of these charts requires time and effort, leading to oversights and / or errors in judgment.

[0054] Furthermore, it is difficult to evaluate the installation conditions, such as the angle and / or scale of the chart in the captured radiographic image. For example, the IQI Duplex type requires the chart to be tilted at an angle of 2 to 5 degrees relative to the rows or columns of pixels in the image, but evaluating the angle is difficult.

[0055] Furthermore, unclear parts of the chart in the captured radiographic image are difficult to evaluate because their position, size, angle, etc. cannot be identified. For example, in the case of the IQI Duplex type, the thin line pair cannot be identified clearly, in the case of the Hole type, the small hole cannot be identified clearly, and in the case of the Wire type (wire-type penetrameter), the thin wire cannot be identified clearly, making it difficult to evaluate contrast.

[0056] Therefore, in this embodiment, the control device 18 detects a chart in an input image that shows a chart for evaluating the image using predetermined pattern information of the chart, and performs a process of evaluating the input image using the chart detection results.

[0057] Specifically, the CPU 24 executes a program 30 stored in the ROM 26 of the control unit 22 to provide the functions shown in Fig. 3. Fig. 3 is a functional block diagram showing the functional configuration of the control unit 22 in the control device 18 of the radiation image capturing system 10 according to this embodiment.

[0058] That is, the control unit 22 has the functions of an acquisition unit 36, a detection unit 38, and an evaluation unit 40, as shown in FIG.

[0059] The acquisition unit 36 ​​acquires an input image by inputting a radiographic image showing a chart for evaluating an image from the radiographic image capturing device 16 to the control device 18 as an input image.

[0060] The detection unit 38 detects a chart in the input image acquired by the acquisition unit 36 ​​using predetermined pattern information of the chart. In the above configuration, the chart pattern in the input image may have unclear portions, distortion, or individual differences. To enable chart detection even in such cases, in this embodiment, the chart may be detected using pattern information of a portion of the chart that includes at least one of a clear portion of the chart, a portion with little individual difference, and a portion with little distortion, rather than the entire chart. Note that an example of the detection result of the detection unit 38 may be the result of detecting at least one of the presence or absence, number, type, position, angle, scale, and shape of a chart.

[0061] The evaluation unit 40 evaluates the input image using the chart detection results. The evaluation unit 40 may evaluate the input image using the input image and evaluation information necessary for evaluating the chart. The evaluation unit 40 evaluates, for example, at least one of the presence / absence, number, type, position, angle, scale, and shape of the chart, and at least one of the contrast of the chart. The evaluation information includes information on a portion of the chart that is different from the pattern information of the chart, or information obtained from the pattern information of the chart. An example of the evaluation information may be information on each portion of the chart that is the subject of evaluation. Furthermore, if the chart is a Duplex type IQI chart, the evaluation information may include information on line pairs that are not included in the chart pattern.

[0062] 4 is a flowchart showing an example of the flow of processing performed by the control unit 22 in the control device 18 of the radiographic imaging system 10 according to this embodiment. The processing in FIG. 4 starts, for example, when an instruction to evaluate a radiographic image is given.

[0063] In step 100, the CPU 24 inputs an image and proceeds to step 102. That is, the acquisition unit 36 ​​acquires an input image by inputting an input image showing a chart for evaluating the image from the radiographic image capturing device to the control device 18.

[0064] In step 102, the CPU 24 detects the chart in the input image using the chart pattern information, and the process proceeds to step 104. That is, the detection unit 38 detects the chart in the input image acquired by the acquisition unit 36 ​​using predetermined pattern information of the chart.

[0065] In step 104, the CPU 24 evaluates the input image using the input image, the chart detection results, and the chart evaluation information, and then proceeds to step 106. That is, the evaluation unit 40 evaluates the input image using the input image, the chart detection results, and the chart evaluation information. Note that the evaluation unit 40 may also evaluate the input image using the chart detection results. Alternatively, the evaluation unit 40 may identify relative position information of at least some of the patterns obtained from the evaluation information based on the chart state identified from the detected chart, and evaluate the input image based on the identification results.

[0066] In step 106, the CPU 24 displays the evaluation result of the input image on the display unit 32, and then the series of processes ends.

[0067] With the above configuration, this embodiment first detects the chart in the input image using the chart's pattern information, eliminating the need to find and specify the chart. It also enables the evaluation of the presence, number, type, and installation conditions of the chart. For example, if the chart is a duplex-type IQI, it can be evaluated whether the IQI is tilted 2 to 5 degrees relative to the pixel rows or columns of the image. Next, based on the chart detection results and the evaluation information required for chart evaluation, the position, size, and angle of each part of the chart, including unclear parts, can be identified, enabling accurate evaluation. For example, accurate contrast evaluation can be performed on thin line pairs in the case of a duplex-type IQI chart, small holes in the case of a hole-type IQI chart, and thin wires in the case of a wire-type IQI chart.

[0068] In the following, a specific example will be described in which the input image is an X-ray transmission image and the chart is an IQI (Image Quality Indicator), but the above-described problem is common even if the chart is not an IQI or the image is not an X-ray transmission image, when "capturing a chart, analyzing that image, and evaluating an input image," and the above-described solution is effective in such cases (for example, a QC phantom, etc.). In other words, in the present disclosure, the input image is not limited to an X-ray transmission image, and the chart is not limited to an IQI.

[0069] (Specific Example 1) A specific example of chart pattern information used by the detection unit 38 when detecting a chart in an input image using the chart pattern information in step 102 will be described. An example of the pattern information is shown in a white frame in FIG. 5.

[0070] In the case of a duplex type IQI, the characters on the chart 50 vary from one chart to another. Furthermore, the 14th and 15th line pairs included in the chart 50 may or may not be present. Furthermore, in an X-ray transmission image, the shape of the chart 50 may be distorted depending on the positional relationship between the radiation source 14 and the chart 50, and the inclination of the chart 50 relative to the radiation detector 20. In other words, the spacing between each line pair on the chart 50 may be distorted. Furthermore, depending on the input image, thin line pairs may be unclear.

[0071] Therefore, as shown by the white frame 52 in FIG. 5, only the first to third line pairs, which are thick and clear without individual differences and are less affected by distortion, are used as the pattern information of the chart 50.

[0072] The chart 50 is detected, for example, by inputting the image of FIG. 6 and searching for a pattern similar to the pattern shown in the white frame 52 in FIG. 5 using a pattern matching technique. An example of the search results is shown in FIG. 7. The color of each pixel in FIG. 7 indicates the degree of similarity between the pattern of the rectangular area with each pixel at its upper left corner and the pattern shown in the white frame 52 in FIG. 5, with the whiter the pixel color, the greater the similarity. It can be seen that the similarity is greater at the position of the chart 50 in FIG. 6. The chart 50 can be detected by extracting only those areas where the similarity is equal to or greater than a predetermined threshold.

[0073] Note that the pattern information for the chart 50 may be a pattern including at least one of the first to sixth line pairs, which are thick, clear, and less affected by distortion. There are various known methods for detecting a pattern similar to the pattern of the chart 50 in an input image. A common method is to compare the pattern of the chart 50 with a pattern in the input image on a pixel-by-pixel basis to derive similarity. The normalized correlation coefficient is often used to measure similarity, but other methods such as the normalized squared difference are also used. Another method involves extracting feature points, such as corners and / or corners, from the pattern of the chart 50, extracting feature points in the input image in the same way, and evaluating the similarity based on the positional relationship of the feature points. Another method involves extracting and vectorizing the outline features of the pattern of the chart 50, and similarly vectorizing the outline features in the input image to evaluate the similarity of the vectors (known as an outline search or geometric shape search, etc.). The chart 50 may be detected using any of these known methods, or other methods.

[0074] Furthermore, the angle of the chart in the input image is unknown and varies. The distance of the chart 50 from the radiation detector 20 also varies, meaning that the scale (size, reduction) of the chart 50 is unknown. Therefore, the pattern of the chart 50 in FIG. 5 is rotated from 0 to 360 degrees, and the scale is also changed to search for similar locations. Here, the input image and the pattern of the chart 50 may be reduced to shorten the search processing time. Alternatively, the angle and scale may be first searched roughly to extract candidate locations with high similarity, and then the angle and scale at which each candidate has the highest similarity may be searched for and detected in detail. Alternatively, the input image and the pattern of the chart 50 may be reduced to multiple sizes by varying the reduction ratio, and candidates with high similarity may be extracted using an image with the highest reduction ratio (smallest image size), and then the candidates may be sequentially narrowed down and detected using images with smaller reduction ratios (larger image sizes). By searching while varying the angle and scale of the chart 50, it is possible to detect the chart 50 in the input image and simultaneously identify the angle and scale of the chart 50.

[0075] When extracting a location where the similarity is greater than or equal to a predetermined threshold, multiple locations may be extracted. If there are multiple charts 50 in the input image, multiple locations are extracted. For example, if there are two charts 50, both locations are extracted. Here, whether there is one chart 50 or multiple charts 50, each chart 50 location will have multiple pixels with similarity greater than or equal to the predetermined threshold. Therefore, the charts 50 are arranged in descending order of similarity using the angle and scale detected for each pixel. If the overlap with an already arranged chart 50 is greater than or equal to a predetermined value (for example, if the ratio of the overlapping area is 0.2 or 0.4 or greater, assuming that the area when all charts 50 overlap is 1.0), the pixel is removed from the candidates. In this way, only the pixel with the highest similarity for each chart 50 remains as a candidate for detection. When searching for a location similar to the chart 50, the relationship between the pattern of the chart 50 and the overall shape of the chart 50 is known. For example: The overall shape of the Duplex type IQI shown in Fig. 5 is shown by a white frame 54 in Fig. 8. The relationship between the pattern of the chart 50 (Duplex type IQI) shown in Fig. 5 and the overall shape of the chart 50 shown in Fig. 8 is known. Therefore, the overall shape of the chart 50 can be arranged using the angle and scale detected for each pixel in the input image.

[0076] Next, a specific example of the chart evaluation information used by the evaluation unit 40 when evaluating the input image using the input image, the detection result, and the chart evaluation information in step 104 will be described. As an example of the evaluation information, Fig. 9 shows an example of the chart evaluation information when the chart 50 is a Duplex type IQI.

[0077] In the case of a duplex-type IQI, the density profile of each line pair is first derived. A one-dimensional density profile is then derived, averaging 21 or more lines, including the center line of the IQI. The contrast of each line pair is then evaluated from the one-dimensional density profile. Alternatively, the contrast of at least one line pair may be evaluated from the profile.

[0078] Specifically, the dip values ​​for the two peaks in the profile of each line pair are calculated, starting with the thickest line pair, and the first line pair with a dip value of less than 20% is identified. Finally, the iSRb value (meaning the interpolated SRb value) with a dip value of 20% is calculated by interpolation from the SRb values ​​of neighboring line pairs, including the line pair with a dip value of less than 20%. The SRb value represents the basic spatial resolution and is defined for each line pair.

[0079] In the above procedure, a line must first be defined perpendicular to each line pair to properly derive the profile. This line must include the thickest line pair, no characters, and the thinnest line pair. Furthermore, the width of at least 21 lines, including this line, must fall within the IQI range. To properly define the profile lines, information other than pattern information, such as the start and end points of the lines, is required as chart evaluation information. Figure 9 shows the center line of the IQI and the range of at least 21 lines including this line, indicated by a white frame 56. The start and end points of the center line are indicated by an upturned triangle (▲) below the IQI, respectively.

[0080] Next, to derive the dip value of each line pair from the profile, information on the position of each line pair is required as evaluation information for chart 50. In FIG. 9, the position of each line pair is indicated by a ▼ (downward-facing triangle mark) above the IQI. Furthermore, to derive the dip value of each line pair, information on the wire diameter and distance of the two wires in each line pair may be used as evaluation information for chart 50. Furthermore, to derive the iSRb value, information on the SRb value of each line pair is required as evaluation information for the chart.

[0081] Since the relationship between the pattern of the chart 50 and the start and end points of the chart 50, as well as the position of each line pair, is known, it is possible to identify the start and end points of the chart 50 in the input image and the relative position information of each line pair from the state of the chart 50, such as information on the position, angle, and scale, detected in the input image as a pattern similar to the pattern of the chart 50, and it is possible to derive the iSRb value. In other words, it is possible to evaluate the input image.

[0082] Note that the end point in the evaluation information for the chart 50 is the end point when the chart 50 has 15 pairs, and when the chart 50 in the input image has 13 pairs, the end point is specified at a position that is longer than the thinnest line, the 13th. However, this is not a problem because the number of the first line pair where the dip value is less than 20% in the evaluation of the input image is smaller than the 13th.

[0083] Furthermore, in the case of Duplex type IQI, the input image is not limited to being evaluated by detecting each line pair, but may be evaluated by detecting at least one line pair.

[0084] Specific Example 2 In specific example 2, another example of the pattern information of the chart 50 will be described. FIG. 10 is a diagram showing another example of the pattern information of the chart 50.

[0085] If the distortion of the shape of the chart 50 in the input image is small, the patterns of the first to thirteenth line pairs may be used as the pattern information of the chart 50, as shown in the white frame 58 in Fig. 10. Characters vary from one to another, and the fourteenth and fifteenth line pairs may or may not be present, so they are excluded from the pattern.

[0086] The pattern information for the chart 50 may also be set as shown in FIG. 11 . That is, after detecting the chart in the input image using the pattern shown by the solid white frame 60 in FIG. 11 , distortion may be detected using the pattern shown by the dotted white frame 62 in the middle of FIG. 11 . The presence or absence of the 14th and 15th line pairs may then be detected using the pattern shown by the dotted white frame 64 on the right side of FIG. 11 . First, the position, angle, and scale of the chart 50 in the input image are identified as a result of detection using the pattern shown by the solid white frame 60 in FIG. 11 . Next, the aspect ratio of the pattern shown by the dotted white frame 62 in the middle of FIG. 11 is changed within a predetermined range, and the similarity between the pattern and the chart pattern of the identified position, angle, and scale in the input image is calculated, and the aspect ratio that maximizes the similarity is identified. Finally, the similarity between the pattern of the dotted white frame 64 on the right in Fig. 11 and the pattern of the chart 50 in the input image with the specified position, angle, scale, and aspect ratio is calculated, and if the similarity is equal to or greater than a predetermined threshold, it is determined that the 14th and 15th line pairs are present, and if it is less than the threshold, it is determined that they are absent. Because the positional relationship between the pattern of the solid white frame 60 in Fig. 11 and the patterns of the dotted white frames 62 and 64 in the middle and right in Fig. 11 is known, after detecting the position, angle, and scale of the chart in the input image as described above, it is also possible to detect the aspect ratio and / or the presence or absence of the 14th and 15th line pairs.

[0087] When searching using the patterns of the dotted white frames 62 and 64 in the center and right of FIG. 11 , not only the aspect ratio but also the amount of positional misalignment may be considered, and the search may be performed while changing the amount of positional misalignment. This type of search allows for detection of distortions that include not only the aspect ratio but also the positional misalignment. Similarly, the amount of angular misalignment may also be considered, and the search may be performed while changing the amount of angular misalignment, and the search may be performed while changing the angle of the pattern, and the angle at which the similarity is greatest may be determined. This type of search allows for detection of distortions that include angular misalignment due to the position of the line pairs in the chart pattern in the input image. If at least one of the determined aspect ratio, positional misalignment, and angular misalignment is greater than a predetermined threshold, the chart in the input image is deemed distorted and unreliable for the purpose of evaluating the input image, and evaluation may not be performed. Furthermore, when searching using the pattern of the dotted white frame 62 in the middle of FIG. 11 , not only the aspect ratio but also the scale may be determined again. Specifically, the aspect ratio and scale of the pattern of the dotted white frame 62 in the middle of FIG. 11 may be varied within a predetermined range to calculate the similarity with the chart pattern in the input image, and the aspect ratio and scale that maximize the similarity may be determined. By searching both the aspect ratio and scale, both the aspect ratio and scale can be accurately determined. Because at least the position of the chart in the input image is determined using the pattern of the solid white frame 60 in FIG. 11 , search and identification may be performed using the pattern of the dotted white frame 62 in the middle of FIG. 11 while varying not only the aspect ratio but also multiple parameters related to the angle, scale, and shape of the chart in the input image. Furthermore, a pattern including the solid white frame 60 may be used as the pattern of the dotted white frame 62 in the center of FIG.

[0088] Furthermore, when detecting the presence or absence of the 14th and 15th line pairs, the evaluation information for the chart 50 also includes information on the end point of the center line 66 when the chart 50 has 13 pairs (no 14th or 15th pairs), as shown in Fig. 12. In Fig. 12, the start point and end point when the chart 50 has 13 pairs, and the start point and end point when the chart 50 has 15 pairs, are indicated by an upturned triangle mark (▲) on the bottom of the chart 50 (the start point is the same for both 13 pairs and 15 pairs).

[0089] When evaluating the input image, the start and end points of chart 50 in the input image and the positions of each line pair can be accurately identified from information on the position, angle, scale, aspect ratio, positional deviation, angular deviation, and the presence or absence of the 14th and 15th patterns detected in the input image as patterns similar to the pattern of chart 50, and the iSRb value can be accurately derived.

[0090] If there is no need to consider individual differences in the characters on the chart, it is preferable to detect the chart 50 in the input image using the pattern of the chart 50 including the characters.

[0091] For example, if there are no individual differences in the characters on the chart 50, or even if there are individual differences, if it is acceptable to detect each type of chart using the pattern of each type of chart 50 (which has individual differences), it is preferable to detect the characters as well.

[0092] (Specific Example 3) In specific example 3, charts are detected in detail when the input image is evaluated in step 104 described above.

[0093] As mentioned above, the chart in the input image may be distorted, meaning that the position of each line pair in the chart in the input image may differ from the position of each line pair in the chart information.

[0094] Therefore, when evaluating the input image in step 104, the position of each line pair in the chart in the input image may first be tentatively determined based on the chart evaluation information, and then the positions of the two peaks and dips of the line pair near that position may be searched for and detected. The peak positions can be detected by searching for the positions of two downwardly convex peaks where the density is minimum near the tentative line pair positions. The position where the density between the two peaks is maximum can also be detected as the dip position. When detecting the two peaks and dips, information on the diameter and distance of the two lines may be used in addition to the positions of each line pair. Furthermore, when detecting the two peaks and dips of each line pair, the angle of the line perpendicular to each line pair may be varied within a predetermined range based on the angle determined in step 102 above to derive a density profile, and the angle at which the contrast between the two peaks and dip is maximized may be searched for and identified. Because the chart in the input image may be distorted, the angle of each line pair may deviate from the angle determined in step 102 above. Therefore, by changing the line angle relative to each line pair and performing a search as described above, the two peaks and dips of each line pair can be accurately detected. The angle of the line perpendicular to each line pair can be searched and identified individually, or it can be identified for multiple line pairs collectively. When identifying multiple line pairs, a single line perpendicular to the multiple line pairs is selected to derive a density profile, and the angle at which the contrast between the two peaks and dips of the thinnest line pair is maximized can be identified. Note that if the angle of each line pair (the angle of the line perpendicular to each line pair) differs significantly by more than a predetermined threshold, the chart in the input image is distorted and is deemed unreliable for the purpose of evaluating the input image, and evaluation may not be performed.

[0095] (Specific Example 4) In specific example 4, the display of the evaluation results of the input image in step 106 will be specifically described.

[0096] An example of the displayed content is at least one of the start point, end point, evaluation result of at least one line pair, and one-dimensional density profile.

[0097] For example, the evaluation results may be displayed as at least one of the lines, frames, start and end points of the chart 50, the one-dimensional concentration profile, the dip value, and the iSRb value. Fig. 13 shows an example of displaying the evaluation results.

[0098] In the upper diagram of Figure 13, the center line of the chart 50 in the input image is indicated by a white line, and the range of 21 lines or more including the center line is indicated by a dotted white frame 68. The start and end points of the lines, as well as line pairs with dip values ​​of less than 20%, are also indicated by text or white lines. The largest number with a dip value of 20% or more and the iSRb value are also displayed around the periphery of the chart 50. The largest number with a dip value of 20% or more and / or the iSRb value may also be displayed on the graph in the lower diagram of Figure 13.

[0099] The lower diagram in Figure 13 shows the profile of each line pair between the start point and the end point, as well as the number and dip value of each line pair. It can be seen that the dip value of the 10th line pair is less than 20%. The lower and upper limits of the density profile and the dip position of the highest-numbered line pair with a dip value of 20% or more are also shown with white lines.

[0100] The evaluation results to be displayed are not limited to those described above, and may include, for example, at least one of the presence or absence, number, type, position, angle, scale, and shape of the detected charts 50 .

[0101] For example, if the chart 50 is a Duplex type IQI, the results of evaluating at least one of whether the angle is within a predetermined range, whether the number is within a predetermined range, whether the angles between the two are within a predetermined range if there are two, and the scale may be displayed.

[0102] Specifically, when the chart 50 is a Duplex type IQI, it is required to be tilted at an angle of 2 to 5 degrees relative to the row or column of pixels of the input image, so the color and / or font of the characters may be changed depending on whether the angle is within the range of 2 to 5 degrees or outside the range.

[0103] Furthermore, if there are two charts 50 of Duplex type IQI, when one chart 50 is arranged in a row (or column), the other chart 50 must be arranged in a column (or row), so it may be possible to display whether the relationship between the two arrangements is appropriate.

[0104] Furthermore, in an X-ray transmission image, if the distance from the radiation source 14 to the radiation detector 20 is known, the distance between the radiation detector 20 and the chart 50 can be derived from the scale of the chart 50. The scale of the chart 50 and / or the distance between the radiation detector 20 and the chart 50 derived from the scale may be displayed.

[0105] Furthermore, if the chart 50 is a duplex type IQI, the type of IQI may be displayed as 13 pairs or 15 pairs. Note that the installation conditions such as the angle and scale of the chart and / or the type can be obtained simultaneously with the chart detection in step 102, and evaluation of the input image in step 104 is not necessary.

[0106] Furthermore, if the chart 50 is a Duplex type IQI, and if no chart 50 is detected and / or three or more charts are detected as a result of chart detection in step 102, the number of detected charts may be displayed in text without evaluating the input image in step 104, or a message may be displayed indicating that the number of IQIs is outside the range of 1 or 2. Furthermore, if the chart distortion is deemed to be large in the chart detection in step 102 or the evaluation of the input image in step 104, and the input image is not evaluated, a message to that effect is displayed.

[0107] (Specific Example 5) In specific example 5, a case will be described in which Hole type IQI is applied as the chart 50. Fig. 14 is a diagram showing an example of the chart 50 of Hole type IQI.

[0108] When the chart 50 is a hole-type IQI, there are many types (large individual differences), making detection using a common pattern difficult. It is preferable to detect each type of chart 50 using the pattern information of each type of chart 50. Then, information about each hole (e.g., information about the position and size of the hole) for each type of chart 50 can be used as evaluation information for the chart 50. Note that for charts 50 of different types but with the same hole information, the same common information about each hole can be linked as evaluation information for each chart 50.

[0109] First, the position, angle, scale, and aspect ratio of the chart 50 in the input image are detected using the pattern information of the chart 50. Then, since the relationship between the pattern of the chart 50 and the positions of each of the three holes in the chart 50 is known, the position and size of each hole in the chart 50 in the input image can be identified from the information on the position, angle, scale, and aspect ratio detected in the input image, and the contrast of each hole can be evaluated. In other words, the input image can be evaluated. Here, if the chart 50 is a Hole Type IQI, the chart 50 has three holes of different sizes. Each hole is indicated by a white circle in FIG. 14. Particularly small holes are unclear in the input image, but the present disclosure makes it possible to identify the position and size of even unclear holes, allowing for accurate contrast evaluation. The contrast of each hole may then be displayed on the display unit 32 as an evaluation result of the input image.

[0110] Note that if the chart 50 is a hole-type IQI, the positions of the holes and outer frame relative to the IQI characters may shift over time. Therefore, the position, angle, and scale of the chart 50 in the input image are detected using clear characters as pattern information of the chart 50. Next, the holes and outer frame of the chart 50 are used as pattern information of the chart 50, and the position, angle, and scale are changed within a predetermined range around the position, angle, and scale detected for the characters to calculate the similarity with the pattern in the input image, and the position, angle, and scale that maximize the similarity are detected. Here, if the similarity calculated using the holes and outer frame of the chart 50 as pattern information of the chart 50 is smaller than a predetermined threshold, they may be excluded from detection. This can eliminate erroneous detection when only characters are used as pattern information of the chart 50.

[0111] First, the position of each hole in the chart 50 in the input image may be tentatively identified based on the evaluation information of the chart 50, and then the true position of the hole may be searched for and detected near that position. The true position of the hole can be detected by searching for the position of the hole that has the greatest contrast with its surroundings at the identified size near the tentative hole position.

[0112] Furthermore, if the chart 50 is a Hole-type IQI, the type of IQI may be displayed in text. The type of chart 50 is obtained simultaneously with the chart detection in step 102 described above, and evaluation of the input image in step 104 is not required.

[0113] Furthermore, if the chart 50 is a Hole type IQI, when the contrast is displayed on the display unit 32, the contrast of at least one hole may be evaluated and displayed.

[0114] Furthermore, if the chart 50 is a Hole type IQI, the input image may be evaluated by detecting at least one hole.

[0115] When the evaluation results are displayed, the evaluation results of at least one hole may be displayed.

[0116] (Specific Example 6) In specific example 6, a case where a Wire type IQI is applied as a chart will be described. Fig. 15 is a diagram showing an example of a Wire type IQI chart 50.

[0117] If the chart 50 is a wire type IQI, the position, angle, and scale of the chart 50 in the input image may be detected using a pattern including both characters and wires as pattern information for the chart 50. Alternatively, only clear wires with little individual variation and little influence of distortion may be used as pattern information for the chart 50. Then, information on the position or diameter of each wire may be used as evaluation information for the chart 50.

[0118] First, the position, angle, and scale of the chart 50 in the input image are detected using the pattern information of the chart 50. Then, since the relationship between the pattern of the chart 50 and the position of each wire in the chart 50 is known, the position and diameter of each wire in the chart 50 in the input image can be identified from the position, angle, and scale information detected in the input image, and the contrast of each wire can be evaluated. In other words, the input image can be evaluated. Although particularly thin wires are unclear in the input image, the present disclosure makes it possible to identify the position and diameter of the wire, allowing for accurate contrast evaluation. Note that the evaluation results of the contrast of each wire may be displayed on the display unit 32 as the evaluation results of the input image.

[0119] (Specific Example 7) In specific example 7, another example of the evaluation information of the chart 50 will be described.

[0120] The evaluation information for the chart 50 may be information obtained from the pattern information. That is, it may be acquired from the pattern information of the chart 50. For example, if the chart 50 is a Duplex type IQI and information on the start and end points of the chart 50 and the positions of each line pair are required as information on the chart 50, the chart 50 in the input image is detected using a pattern including all line pairs as pattern information for the chart 50. Then, the start and end points and the positions of each line pair may be derived from the pattern of the same chart 50, and the input image may be evaluated based on the derived information, the detection results, and the input image.

[0121] For example, as described above, the input image is evaluated by deriving a profile and / or an iSRb value from the derived information, the detection result, and the input image. The profile, iSRb value, etc. may then be displayed on the display unit 32 as the evaluation result.

[0122] (Eighth Specific Example) In an eighth specific example, a modified example when evaluating an input image will be described.

[0123] In the above-mentioned step 102, when the chart 50 is detected in the input image, the detected range may be cut out, and the input image may be evaluated using the cut-out image, the detection result of the chart 50, and the evaluation information of the chart 50.

[0124] (Specific Example 9) In specific example 9, before detecting the chart 50, the chart 50 is roughly detected in advance at high speed in the input image by a different method.

[0125] For example, a learning model for detecting the chart 50 from an input image may be generated in advance through learning. Then, before detecting the chart 50 in step 102 described above, the generated learning model may be used to roughly detect the chart 50 from the input image at high speed using a machine learning technique.

[0126] Thereafter, each location detected by another method in the input image, including the surrounding area, is searched for using the pattern information of the chart 50, and it is possible to accurately detect the presence or absence, number, type, position, angle, scale, shape, etc. of the chart 50. The user may also specify the chart 50.

[0127] (Specific Example 10) In specific example 10, a method for detecting the chart 50 is to detect the chart from the input image using a machine learning technique.

[0128] For example, a learning model may be generated by learning the pattern characteristics of the chart 50 using a machine learning technique such as a neural network, and the generated learning model may be used to detect the chart 50 in the input image.

[0129] In this embodiment, the pattern information of the chart 50 includes machine learning parameters and / or a learning model that has learned the characteristics of the pattern of the chart 50 .

[0130] (Specific Example 11) In specific example 11, a case will be described in which the detection range of the chart 50 in the input image is limited by the user.

[0131] In step 102 described above, when detecting the chart 50, it takes time to search and detect the chart 50 over the entire input image.

[0132] Therefore, the range in the input image in which the chart 50 is to be detected and / or the range in which the chart 50 is to be evaluated may be accepted and limited by the user's operation on the operation unit 34 or the like.

[0133] This makes it possible to reduce the time required to detect the chart 50 from the input image in step 102.

[0134] (Specific Example 12) In specific example 12, a specific example of registering information on the chart 50 will be described.

[0135] The pattern information of the chart 50 and the evaluation information of the chart 50 are registered by user settings together with the image of the chart 50, for example, by the user operating the operation unit 34. In other words, at least one of the pattern information of the chart 50 and the evaluation information of the chart 50 may be registered by the user.

[0136] Specifically, the evaluation information of the chart 50, such as the start and end points of the Duplex type IQI, the position of each wire pair, the wire diameter and / or distance of each wire pair, and the corresponding SRb value, or the position and size of each hole of the Hole type IQI, and the position and wire diameter of each wire of the Wire type IQI, is registered according to the user's settings.

[0137] The pattern information of the chart 50 and the evaluation information of the chart 50 are registered for each type of chart 50. For example, multiple types of Duplex type IQI, Hole type IQI, and Wire type IQI are registered for each of them. Note that multiple pieces of pattern information of the chart 50 may exist for the same type. For example, for the same type of Duplex type IQI, the pattern information of the chart 50 may include the patterns of the third thickest line pair and the patterns of the fifth thickest line pair. The pattern information of the chart 50 and the evaluation information of the chart 50 are linked, but the user can register only the pattern information of the chart 50 and the evaluation information of the chart 50, and can also re-register them. Multiple pieces of pattern information of the chart 50 may be registered for the same evaluation information of the chart 50. Furthermore, evaluation information of multiple different types of charts 50 may be linked and registered to a single common evaluation information.

[0138] During radiography for nondestructive testing, a chart is photographed and its length is analyzed to evaluate the actual size of the photographed image. Specifically, a chart such as a Duplex-type IQI chart is photographed, and the actual length per pixel of the photographed image is evaluated based on the relationship between the chart's length (length in pixels) in the photographed image and its actual length. The actual size of the subject in the photographed image is then evaluated based on this length. Even when evaluating the actual size of the photographed image in this way, the time and effort required to specify the chart itself and / or each portion of the chart to be analyzed for its length, as well as the time and effort required to locate the chart, are issues. The image processing device, image processing method, and image processing program provided by the present disclosure can solve these issues. For example, if the chart is a Duplex-type IQI chart, the present disclosure can detect the chart in an input image using chart pattern information, identify each line pair of the chart using chart evaluation information, and evaluate the contrast. Then, two pairs of lines with appropriate contrast are identified and their lengths in pixels are measured, and the actual lengths are derived based on the evaluation information to evaluate the actual length per pixel of the input image. Here, the two pairs of lines with appropriate contrast may be, for example, the thickest pair of lines (the first pair of lines) and the thinnest pair of lines (the pair of lines with the highest number) with a dip value of 20% or more. In this manner, the present disclosure is also effective when evaluating the actual size of a captured image. In other words, in this disclosure, evaluating an input image also includes evaluating the actual size of the input image. Note that even when evaluating the actual size of a captured image, if the chart is significantly distorted in the chart detection in step 102 or the input image evaluation in step 104, the reliability may be deemed low and the evaluation may not be performed.

[0139] In the above embodiment, an example was described in which a radiological image was used as the input image, but the input image is not limited to a radiological image, and may be an image other than a radiological image as long as it contains a chart for evaluating the image.

[0140] Furthermore, the various processes performed by the CPU in the above embodiments by executing software (programs) may be executed by a computer equipped with various processors other than a CPU. Examples of such processors include programmable logic devices (PLDs) (such as field-programmable gate arrays (FPGAs)) whose circuit configuration can be changed after manufacture, and dedicated electrical circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed to execute specific processes. The various processes may be executed by one of these processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0141] In the above embodiment, the various programs are pre-stored (installed) in the ROM 20B, but the present invention is not limited to this. The various programs may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The various programs may also be downloaded from an external information processing device or the like via a network.

[0142] The program of the present disclosure can be provided as a program product. The program product includes any product for providing the program. For example, the program product includes a program provided over a network such as the Internet, and a non-transitory computer-readable recording medium such as a CD-ROM or DVD on which the program is stored.

[0143] Furthermore, the configuration, operation, etc. of the radiation image capturing system 10 described in the above embodiment are merely examples, and it goes without saying that they can be modified according to the circumstances within the scope of the present disclosure.

[0144] The following supplementary note is further disclosed regarding the above embodiment: (Supplementary Note 1) An image processing device including a processor, the processor detecting a chart for evaluating an image from an input image showing the chart using predetermined pattern information of the chart, and performing processing to evaluate the input image using the result of the chart detection.

[0145] (Supplementary Note 2) The image processing device according to Supplementary Note 1, wherein the processor evaluates the input image by further using the input image and evaluation information required for evaluating the chart.

[0146] (Supplementary Note 3) The image processing device according to Supplementary Note 1 or Supplementary Note 2, wherein the input image is an X-ray transmission image.

[0147] (Supplementary Note 4) The image processing device according to any one of Supplementary Note 1 to Supplementary Note 3, wherein the processor receives a range in the input image in which the chart is to be detected, and detects the chart from the received range.

[0148] (Supplementary Note 5) The image processing device according to Supplementary Note 2, wherein the processor identifies relative position information of at least a portion of patterns obtained from the evaluation information based on the state of the chart identified from the detected chart, and evaluates the input image based on the identification result.

[0149] (Supplementary Note 6) The image processing device according to any one of Supplementary Notes 1 to 5, wherein the pattern information is information on a portion of the chart that includes at least one of a clear portion, a portion with little individual variation, and a portion with little distortion, information on a portion of the chart that does not include text, or information that includes machine learning parameters.

[0150] (Supplementary Note 7) The image processing device according to Supplementary Note 2, wherein the evaluation information includes information on a portion of the chart that is different from the pattern information, or information obtained from the pattern information of the chart.

[0151] (Supplementary Note 8) The image processing device according to any one of Supplementary Note 1 to Supplementary Note 7, wherein the processor evaluates at least one of the presence or absence, number, type, position, angle, scale, and shape of the chart, and at least one of the contrast of the chart.

[0152] (Supplementary Note 9) The image processing device according to any one of Supplementary Note 1 to Supplementary Note 8, wherein the processor further performs processing to display at least one of the presence or absence, number, type, position, angle, scale, and shape of the detected chart.

[0153] (Supplementary Note 10) The image processing device according to Supplementary Note 3, wherein the chart is a multi-linear image quality meter.

[0154] (Supplementary Note 11) The image processing device according to Supplementary Note 10, wherein the pattern information is information on a pattern including at least one of the first to sixth line pairs of the multi-linear image quality meter.

[0155] (Supplementary Note 12) An image processing device according to Supplementary Note 10 or Supplementary Note 11, wherein the processor evaluates the input image by further using the input image and evaluation information including information of at least one line pair of the multi-linear image quality meter as information necessary for evaluating the chart.

[0156] (Supplementary Note 13) The image processing device according to Supplementary Note 12, wherein the evaluation information includes information on line pairs that are not included in the pattern of the chart.

[0157] (Supplementary Note 14) The image processing device of Supplementary Note 12 or Supplementary Note 13, wherein the processor evaluates contrast of at least one line pair.

[0158] (Supplementary Note 15) The image processing device according to any one of Supplementary Note 12 to Supplementary Note 14, wherein the processor evaluates the input image by calculating a one-dimensional density profile.

[0159] (Supplementary Note 16) The image processing device according to Supplementary Note 10, wherein the processor evaluates the input image by further using the input image and evaluation information including information on start points and end points of line pairs as information necessary for evaluating the chart.

[0160] (Appendix 17) An image processing device described in any one of Appendices 10 to 16, wherein the processor evaluates at least one of whether the angle of the multi-linear image quality meter is within a predetermined range, whether the number of the multi-linear image quality meter is within a predetermined range, whether the angle between the multi-linear image quality meter and the multi-linear image quality meter is within a predetermined range if there are two, and the scale.

[0161] (Supplementary Note 18) The image processing device according to any one of Supplementary Notes 10 to 17, wherein the processor detects at least one line pair of a multi-linear image quality meter to evaluate the input image.

[0162] (Supplementary Note 19) An image processing device according to any one of Supplementary Notes 10 to 18, wherein the processor further performs processing to display the start and end points of the multi-linear image quality meter, the evaluation result of at least one line pair, and at least one one-dimensional density profile.

[0163] (Supplementary Note 20) The image processing device according to Supplementary Note 3, wherein the chart is a perforated penetrameter.

[0164] (Supplementary Note 21) The image processing device according to Supplementary Note 20, wherein the pattern information includes information on a pattern including a character.

[0165] (Supplementary Note 22) The image processing device according to Supplementary Note 20 or Supplementary Note 21, wherein the processor evaluates the input image by further using the input image and evaluation information including information of at least one hole as information necessary for evaluating the chart.

[0166] (Supplementary Note 23) The image processing device of Supplementary Note 22, wherein the processor evaluates the contrast of at least one hole.

[0167] (Supplementary Note 24) The image processing device of Supplementary Note 22 or Supplementary Note 23, wherein the processor evaluates the input image by detecting at least one hole in the perforated penetrometer.

[0168] (Supplementary Note 25) The image processing device according to any one of Supplementary Note 20 to Supplementary Note 24, wherein the processor further performs processing to display an evaluation result of at least one hole of the perforated penetrometer.

[0169] (Supplementary Note 26) The image processing device according to Supplementary Note 2, wherein at least one of the pattern information of the chart and the evaluation information of the chart is registered by a user.

[0170] (Supplementary Note 27) An image processing method that performs processing including: detecting a chart for evaluating an image in an input image showing the chart using predetermined pattern information of the chart; and evaluating the input image using the detection result of the chart.

[0171] (Supplementary Note 28) An image processing program for causing a computer to execute processing including: detecting a chart for evaluating an image in an input image showing the chart using predetermined pattern information of the chart; and evaluating the input image using the result of the detection of the chart.

[0172] In the above, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

Claims

1. An image processing device comprising a processor, which detects a chart for evaluating an image from an input image showing the chart using predetermined pattern information of the chart, and performs processing to evaluate the input image using the detection result of the chart.

2. The image processing device according to claim 1, wherein the processor evaluates the input image by further using the input image and evaluation information required for evaluating the chart.

3. The image processing device according to claim 1, wherein the input image is an X-ray transmission image.

4. The image processing device according to claim 1, wherein the processor receives a range in the input image in which the chart is to be detected, and detects the chart from the received range.

5. The image processing device according to claim 2, wherein the processor determines relative position information of at least a portion of the patterns obtained from the evaluation information based on the state of the chart determined from the detected chart, and evaluates the input image based on the determination result.

6. The image processing device according to claim 1, wherein the pattern information is information on a portion of the chart that includes at least one of a clear portion, a portion with little individual variation, and a portion with little distortion, information on a portion of the chart that does not include text, or information that includes machine learning parameters.

7. The image processing device according to claim 2, wherein the evaluation information includes information on a portion of the chart that is different from the pattern information, or information obtained from the pattern information of the chart.

8. The image processing device according to claim 1, wherein the processor evaluates at least one of the presence or absence, number, type, position, angle, scale, and shape of the chart, and at least one of the contrast of the chart.

9. The image processing device according to claim 1, wherein the processor further performs processing to display at least one of the presence or absence, number, type, position, angle, scale, and shape of the detected chart.

10. The image processing device according to claim 3, wherein the chart is a multi-linear image quality chart.

11. An image processing device according to claim 10, wherein the pattern information is information on a pattern including at least one of the first to sixth line pairs of the multi-linear image quality meter.

12. The image processing device according to claim 10, wherein the processor evaluates the input image using the input image and evaluation information including information of at least one line pair of the multi-linear image quality meter as information necessary for evaluating the chart.

13. The image processing device according to claim 12, wherein the evaluation information includes information on line pairs that are not included in the chart pattern.

14. The image processing apparatus of claim 12, wherein the processor evaluates the contrast of at least one line pair.

15. The image processing apparatus of claim 12, wherein the processor evaluates the input image by calculating a one-dimensional intensity profile.

16. The image processing device according to claim 10, wherein the processor evaluates the input image by further using the input image and evaluation information including information on the start and end points of line pairs as information necessary for evaluating the chart.

17. The image processing device of claim 10, wherein the processor evaluates at least one of whether the angle of the multi-linear image quality meter is within a predetermined range, whether the number of the multi-linear image quality meter is within a predetermined range, whether the angle between the two multi-linear image quality meter is within a predetermined range if there are two, and the scale.

18. The image processing apparatus of claim 10, wherein the processor evaluates the input image by detecting at least one line pair of a multi-linear image quality sensor.

19. The image processing device according to claim 10, wherein the processor further performs processing to display at least one of the start and end points of the multi-linear image quality meter, the evaluation result of at least one line pair, and a one-dimensional density profile.

20. The image processing device according to claim 3, wherein the chart is a perforated penetrometer.

21. The image processing device according to claim 20, wherein the pattern information includes information on a pattern including characters.

22. The image processing device according to claim 20, wherein the processor evaluates the input image using the input image and evaluation information including information about at least one hole as information necessary for evaluating the chart.

23. The image processing device of claim 22, wherein the processor evaluates the contrast of at least one hole.

24. The image processing apparatus of claim 22, wherein the processor evaluates the input image by detecting at least one hole in the perforated penetrometer.

25. The image processing device according to claim 20, wherein the processor further performs processing to display the evaluation result of at least one hole of the perforated penetrometer.

26. The image processing device according to claim 2, wherein at least one of the pattern information of the chart and the evaluation information of the chart is registered by a user.

27. An image processing method that performs processing including: detecting a chart for evaluating an image in an input image that includes the chart using predetermined pattern information of the chart; and evaluating the input image using the results of the chart detection.

28. An image processing program for causing a computer to execute processing including: detecting a chart for evaluating an image in an input image showing the chart using predetermined pattern information of the chart; and evaluating the input image using the results of the chart detection.

Images