JP6846003B2 - Modeled object inspection device, modeled object inspection control device and modeled object inspection method - Google Patents

Description

The present disclosure relates to a modeled object inspection device, a modeled object inspection control device, and a modeled object inspection method for inspecting a modeled object produced by a 3D printer.

Conventionally, quality inspection of a three-dimensional object has often focused on indicators such as the height and surface shape of the three-dimensional object. For example, Patent Document 1 describes a technique for inspecting a three-dimensional object based on an image obtained by capturing the three-dimensional object from the direction in which the side surface is projected. In this technique, the height information of a three-dimensional object is extracted and the three-dimensional object is inspected.

Japanese Unexamined Patent Publication No. 2005-274309

Recently, a 3D printer that can easily produce a three-dimensional model has been attracting attention. A 3D printer is for manufacturing a three-dimensional model of an arbitrary shape by laminating thin resin layers, and while an expensive mold is not required, whether or not even a fine shape can be manufactured as designed is a question. It depends on the performance of the 3D printer. In many cases, the more expensive a 3D printer is, the more faithfully it is possible to produce a three-dimensional model with a finer shape, but the reality is that a method for inspecting the outer shape of a three-dimensional model produced by a 3D printer has not been established. ..

An object to be solved by the present disclosure is to provide a modeled object inspection device, a modeled object inspection control device, and a modeled object inspection method capable of accurately inspecting a modeled object produced by a 3D printer.

In order to solve the above problems, in one aspect of the present disclosure, a first aspect of generating two-dimensional design data in which three-dimensional design data used for producing a modeled object by a 3D printer is projected onto a two-dimensional plane. Generator and
An imaging unit that images the modeled object produced by the 3D printer, and
A second generation unit that generates two-dimensional real data including two-dimensional outline contour information based on the imaging data captured by the imaging unit, and a second generation unit.
A comparison unit that compares the two-dimensional design data and the two-dimensional real data in the corresponding angular directions, and
A modeled object inspection device including an inspection unit for inspecting the outer shape of the modeled object based on the comparison result of the comparison unit is provided.

A plurality of the two-dimensional design data and a plurality of the two-dimensional real data may be acquired from a plurality of angular directions, and the comparison unit may compare the corresponding angular directions with each other.

It may be provided with a turntable for rotating the modeled object produced by the 3D printer around one axis.
The imaging unit generates moving image data obtained by capturing the modeled object from one direction while rotating the modeled object on the turntable.
The second generation unit may generate the plurality of two-dimensional real data based on the plurality of imaging data included in the moving image data.

The comparison unit compares the plurality of two-dimensional design data and the plurality of two-dimensional real data in the corresponding angular directions, detects the degree of agreement between the corresponding two-dimensional design data and the imaging data, and detects the degree of coincidence between the corresponding two-dimensional design data and the imaging data.
The inspection unit may inspect the outer shape of the modeled object based on the degree of coincidence.

When the degree of coincidence is lower than a predetermined threshold value, the inspection unit may determine that the outer shape of the modeled object is defective.

In the comparison unit, the first value representing the degree of coincidence when the plurality of two-dimensional design data and the plurality of two-dimensional real data are compared with each other in the corresponding angular directions, and the angular direction shifted by a predetermined angle. The difference between the second value representing the degree of coincidence when compared with each other is detected, and the difference is detected.
The inspection unit may inspect the outer shape of the modeled object based on the first value and the difference.

The two-dimensional design data is binarized digital data including external contour information obtained by projecting the three-dimensional design data onto a two-dimensional plane.
The two-dimensional real data may be binarized digital data including external contour information obtained by capturing the modeled object from directions corresponding to the plurality of angular directions.

In order to solve the above problems, the two-dimensional design data used to create a modeled object with a 3D printer is projected onto a two-dimensional plane, and the two-dimensional design data
A comparison unit that compares two-dimensional real data including external contour information generated based on imaging data obtained by imaging the modeled object produced by the 3D printer in the corresponding angular directions.
A model inspection device is provided.

The comparison unit compares the two-dimensional design data with the two-dimensional real data generated by imaging the two-dimensional design data in the same direction as the angle of the projected two-dimensional plane.

The comparison unit prepares a plurality of the two-dimensional design data and the two-dimensional real data in the vicinity of the angle of the two-dimensional plane on which the two-dimensional design data is projected, and prepares the two-dimensional design data and the two-dimensional real object, respectively. Compare the data.

In another aspect of the present disclosure, two-dimensional design data is generated by projecting the three-dimensional design data used for producing a modeled object with a 3D printer onto a two-dimensional plane.
An image of the modeled object produced by the 3D printer was taken.
Based on the captured image data, two-dimensional real data including two-dimensional outline contour information is generated.
The two-dimensional design data and the two-dimensional real data are compared with each other in the corresponding angular directions.
Based on the result of the comparison, a modeled object inspection method for inspecting the outer shape of the modeled object is provided.

According to the present disclosure, it is possible to accurately inspect a modeled object produced by a 3D printer.

The figure which shows the modeled object inspection apparatus by this embodiment. The flowchart which shows the modeled object inspection method by this embodiment. The figure which shows an example of the 2D real data generated based on the image pickup data which image | imaged the model | object of FIG. 1 from a predetermined direction. The figure which shows an example of the 2D design data which projected the 3D design data on the 2D plane in a predetermined angle direction. The figure which shows how the feature point of 2D real data and 2D design data is associated with each other.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. FIG. 1 is a diagram showing a modeled object inspection device 1 according to the present embodiment. The modeled object inspection device of FIG. 1 inspects the outer shape of a modeled object produced by a 3D printer (not shown). More specifically, the modeled object inspection device of FIG. 1 inspects whether or not the external shape of the modeled object produced by the 3D printer is the shape as designed, and in some cases, the external shape of the modeled object. Evaluate how faithfully the is made compared to the design.

The modeled object inspection device 1 shown in FIG. 1 includes a first generation unit 2, a camera (imaging unit) 3, a second generation unit 4, a comparison unit 5, and an inspection unit 6. Of these, the first generation unit 2, the second generation unit 4, the comparison unit 5, and the inspection unit 6 constitute a modeled object inspection control device 10.

The first generation unit 2 generates a plurality of two-dimensional design data by projecting the three-dimensional design data used for producing the modeled object 7 with a 3D printer onto two-dimensional planes in a plurality of angular directions. The angular direction is a direction corresponding to an angle with respect to the three-dimensional design data. The two-dimensional plane is a plane whose normal direction is the angular direction, that is, a plane orthogonal to the angular direction. The three-dimensional design data may be STL (Standard Triangulated Language) data generally used in various 3D printers, or data in other data formats. The three-dimensional design data is monochrome three-dimensional data that does not have color information or gradation information, and is, for example, data of an aggregate of triangular polygons. The plurality of angular directions are, for example, 90 degree intervals, and the first generation unit 2 generates four two-dimensional design data projected in four directions of the front surface, the left side surface, the back surface, and the right side surface of the modeled object 7. May be good. Alternatively, the first generation unit 2 may generate a plurality of two-dimensional design data by changing the angle in units finer than 90 degrees. Each two-dimensional design data generated by the first generation unit 2 is binarized digital data including external contour information projected in the corresponding angle direction.

The first generation unit 2 projects not only an angle range passing through the front surface, the back surface, and the side surface of the model object 7, but also a plurality of projections in a plurality of angular directions within an arbitrary angle range with respect to the height direction of the model object 7. Two-dimensional design data may be generated. Thereby, for example, it is possible to generate two-dimensional design data corresponding to the case where the modeled object 7 is viewed from above or diagonally above.

The camera 3 takes an image of the modeled object 7 produced by the 3D printer from directions corresponding to a plurality of angular directions. The camera 3 may be a still camera that captures a still image, or a video camera that captures a moving image. As will be described later, when the camera 3 takes an image while rotating the model 7, even if the camera 3 always takes an image in one direction, the image data obtained by capturing the image 7 from a plurality of angular directions can be obtained. Can be done. Imaging may be performed while moving the camera 3 around the model 7 without rotating the model 7. Alternatively, different still cameras may be installed in advance in a plurality of angular directions, and each still camera may take an image of the modeled object 7 as viewed from the corresponding angular directions. In the following, an example of capturing a moving image with a video camera will be mainly described. A video camera generates moving image data by repeating imaging of several tens of frames per second. Since the moving image data can be regarded as containing a plurality of still image data, for example, by rotating the modeled object 7 during imaging by a video camera, a plurality of still image data (plural images captured data) from a plurality of angular directions can be obtained. ) Can be substantially obtained. Moreover, if the rotation speed of the modeled object 7 is slowed down, it is possible to obtain a plurality of imaging data in a large number of angular directions in which the angles are changed little by little.

It is desirable that the camera 3 captures images with as high a resolution as possible. This is because the pixels become coarse in the low-resolution imaging data, and the fine shape of the modeled object 7 cannot be inspected. Therefore, when a video camera is used, it is desirable that it has a function of generating moving image data having a resolution of 2K or more, preferably 4K.

The height in the vertical direction can be changed when imaging data captured from a plurality of angular directions within an arbitrary angular range with respect to the height direction of the model 7 as well as the front, back, and side surfaces of the model 7 is required. The camera 3 may be installed on a possible tripod, and the model 7 may be imaged at different height positions while variably adjusting the height of the tripod. Alternatively, the height position of the camera 3 may be fixed, the elevation angle of the camera 3 may be varied, and the model 7 may be imaged at different elevation angles.

The second generation unit 4 generates a plurality of two-dimensional real data, each of which includes two-dimensional outline contour information, based on the plurality of imaged data captured by the camera 3. Each two-dimensional real data is binarized digital data including external contour information captured from the corresponding angular direction of the modeled object 7. That is, each two-dimensional real data is monochrome digital data that does not include color information or gradation information.

The comparison unit 5 compares the plurality of two-dimensional design data and the plurality of two-dimensional real data in the corresponding angular directions. That is, the comparison unit 5 compares the two-dimensional design data projected / imaged in the same angular direction with the two-dimensional actual data. In other words, the comparison unit 5 compares the two-dimensional design data with the two-dimensional real data generated by imaging the two-dimensional design data at an angle of the projected two-dimensional plane, that is, in the same direction as the angle direction. For example, if there are two-dimensional design data and two-dimensional real data in four angular directions, the comparison process of the comparison unit 5 is also performed four times. An example of the comparison process performed by the comparison unit 5 is to detect the degree of coincidence between the two-dimensional design data projected / imaged in the same angular direction and the two-dimensional actual data. The feature points of the two-dimensional design data and the two-dimensional real data are obtained, the positioning is performed using the feature points, and the difference between the aligned two-dimensional design data and the two-dimensional real data is calculated. The degree of coincidence is obtained based on the calculated difference.

The feature point extraction may be performed using, for example, a known feature extraction algorithm such as AKAZE implemented in the OpenCV library developed by Intel, or may be performed using another algorithm. The comparison unit 5 extracts the feature points of the two-dimensional design data projected / imaged in the same angular direction and the two-dimensional real data, and performs image conversion processing such as rotational movement and enlargement / reduction by affine conversion to obtain the feature amount. The two-dimensional design data and the two-dimensional real data are aligned by aligning the feature points with similar characteristics.

More specifically, the comparison unit 5 detects the difference when the plurality of two-dimensional design data and the plurality of two-dimensional real data are aligned with each other by the affine transformation and then compared with each other in the corresponding angular directions. To do.

The inspection unit 6 inspects the outer shape of the modeled object 7 based on the comparison result of the comparison unit 5. For example, the inspection unit 6 compares the degree of matching obtained by the comparison unit 5 with a predetermined threshold value, and depending on whether or not the degree of matching is higher than the threshold value, there is no defect such as chipping in the outer shape of the modeled object 7. Inspect whether or not. Alternatively, the inspection unit 6 may evaluate how faithfully the outer shape of the modeled object 7 is made with respect to the ideal three-dimensional design model based on the comparison result of the comparison unit 5. The evaluation result may be quantified based on the result of comparison with the above-mentioned degree of agreement and the threshold value.

The modeled object inspection device 1 according to the present embodiment may include the turntable 8 shown in FIG. The turntable 8 rotates the modeled object 7 placed on the turntable 8 about one axis. The turntable 8 is connected to a rotation drive device 11 having a built-in motor that rotationally drives the rotation shaft, and rotates by the rotational force of the motor. The model 7 placed on the turntable 8 of FIG. 1 shows an example of a model of a human blood vessel formed of a resin material. The type of the modeled object 7 to be inspected by the modeled object inspection device 1 according to the present embodiment is not particularly limited.

The camera 3 of FIG. 1 is arranged so as to face the model 7 on the turntable 8 in a direction orthogonal to the rotation axis of the turntable 8, and the imaging direction of the camera 3 is fixed. By presetting imaging conditions such as the distance between the turntable 8 and the camera 3 and the focal length of the camera 3, the camera 3 can image the entire modeled object 7 or the entire area requiring inspection.

The camera 3 continuously captures a moving image of the model 7 rotating on the turntable 8 from a certain direction, thereby capturing a moving image of the model 7. The moving image data of the modeled object 7 captured by the camera 3 is supplied to the second generation unit 4.

As shown in FIG. 1, the modeled object inspection device 1 according to the present embodiment may include a screen 9 arranged behind the turntable 8. By setting the screen 9 to a specific color, it becomes easy to extract the external contour position of the modeled object 7 included in the imaging data of the camera 3. The screen 9 may be, for example, blue drawing paper.

FIG. 2 is a flowchart showing a modeled object inspection method according to the present embodiment. This flowchart is executed by the modeled object inspection device 1 of FIG. It is assumed that the model 7 created by using the three-dimensional design data is placed on the turntable 8.

As shown in FIG. 2, first, a moving image of the model 7 is captured by the camera 3 while rotating the model 7 on the turntable 8 (step S1). Next, from the moving image data captured by the camera 3, a plurality of captured data captured from a plurality of predetermined angular directions are extracted (step S2). The plurality of predetermined angular directions are the plurality of angular directions used by the first generation unit 2 to generate the two-dimensional design data. The process of step S2 may be performed inside the camera 3 or may be performed by the second generation unit 4.

Next, the second generation unit 4 generates a plurality of two-dimensional real data, each of which includes two-dimensional outline contour information, based on the plurality of imaging data (step S3). As described above, each two-dimensional real data is binarized digital data including external contour information obtained by capturing the modeled object 7 from the corresponding angular direction.

FIG. 3 is a diagram showing an example of two-dimensional real data 21 generated based on imaging data obtained by photographing the model 7 of FIG. 1 from a predetermined direction with a camera 3. As shown in the figure, the two-dimensional real data 21 is monochrome (binary) digital data without color information or gradation information.

Before and after the processing of steps S1 to S3 described above, the first generation unit 2 projects the three-dimensional design data used for producing the modeled object 7 with the 3D printer onto two-dimensional planes in a plurality of angular directions. A plurality of two-dimensional design data 22 are generated (step S4). The process of step S4 and the process of steps S1 to S3 may be performed in parallel, or either process may be performed first.

FIG. 4 is a diagram showing an example of two-dimensional design data 22 in which three-dimensional design data is projected onto a two-dimensional plane in a predetermined angular direction. The two-dimensional design data 22 of FIG. 4 is data obtained by pseudo-rotating the STL data input to the 3D printer with general-purpose three-dimensional modeling software and capturing the data in a predetermined rotation direction. As shown in the figure, the two-dimensional design data 22 is monochrome (binary) digital data without color information or gradation information, like the two-dimensional real data 21.

Next, the comparison unit 5 compares the two-dimensional real data 21 generated in step S3 with the two-dimensional design data 22 generated in step S4 in the corresponding angular directions (step S5). In step S5, for example, the two-dimensional real data 21 corresponding to the imaging data captured from the front direction (angle 0 degree direction) of the modeled object 7 is compared with the two-dimensional design data 22 projected in the same angle 0 degree direction. ..

Here, since the two-dimensional design data 22 is generated by using the image processing technique, there is no possibility that the two-dimensional design data 22 projected in the direction of 0 degrees will be displaced in the angular direction. On the other hand, since the two-dimensional real data 21 is generated based on the imaged data captured by the camera 3 while rotating the turntable 8, there is a possibility that a slight angle deviation may occur. Therefore, when comparing the two-dimensional design data 22 and the two-dimensional real data 21, it is generated based on a plurality of imaging data belonging to a predetermined angle width centered on the projection angle of the two-dimensional design data 22. A plurality of two-dimensional real data 21 are prepared, these two-dimensional real data 21 are compared with the two-dimensional design data 22 in order, and the two-dimensional real data 21 having the highest degree of matching is referred to the two-dimensional design data 22. It may be selected as a comparison target. That is, the comparison unit 5 prepares a plurality of two-dimensional design data and two-dimensional real data at the angle of the two-dimensional plane on which the two-dimensional design data is projected, that is, in the vicinity of the angular direction, respectively, and the two-dimensional design data and the two-dimensional real data. May be compared.

The degree of coincidence between the two-dimensional real data 21 and the two-dimensional design data 22 is obtained from the difference between the two-dimensional real data 21 and the two-dimensional design data 22. First, each feature point and the feature amount of the feature point are obtained from the two-dimensional real data 21 and the two-dimensional design data 22. The feature amount of the two-dimensional real data 21 and the feature amount of the two-dimensional design data 22 are compared, and the feature points having the closest feature amount are associated with each other. The affine transformation amount (rotation angle, variable magnification, movement amount) is calculated from the correspondence between the feature points, and the two-dimensional real data 21 or the two-dimensional design data 22 is subjected to the affine transformation, and the two-dimensional real data 21 and 2 are performed. The dimension design data 22 is aligned. The degree of coincidence is calculated by taking the difference between the aligned two-dimensional real data 21 and the two-dimensional design data 22.

FIG. 5 is a diagram showing how the feature points of the two-dimensional real data 21 and the two-dimensional design data 22 are associated with each other. In FIG. 5, feature points having similar feature amounts are connected by a straight line. For example, when a part of the modeled object 7 is chipped, the feature points of the chipped portion are present in the two-dimensional design data 22 and not in the two-dimensional actual data 21, but are the closest features. The feature points with quantity correspond to each other.

Next, the inspection unit 6 inspects the outer shape of the modeled object 7 based on the comparison result by the comparison unit 5 (step S6). For example, the inspection unit 6 compares the degree of matching detected in step S5 with a predetermined threshold value, and if the degree of matching is larger than the threshold value, determines that there is no problem with the outer shape of the modeled object 7, and the degree of matching is determined. If it is equal to or less than the threshold value, it may be determined that there is some defect in the outer shape of the modeled object 7.

In step S5, since the degree of coincidence between the two-dimensional real data 21 and the two-dimensional design data 22 is detected in each of the plurality of angular directions, a plurality of degrees of coincidence corresponding to the plurality of angular directions can be obtained. Therefore, the inspection unit 6 compares the degree of coincidence with the threshold value in each angular direction, and if the degree of coincidence is equal to or less than the threshold value in at least one angular direction, it may determine that the modeled object 7 is defective. Good. Alternatively, the modeled object 7 produced by the 3D printer may be evaluated by comprehensively judging the comparison result between the degree of coincidence in the plurality of angular directions and the threshold value.

If there is any defect in the modeled object 7, the value of the degree of agreement between the two-dimensional real data 21 and the two-dimensional design data 22 in a certain angle direction and both in the direction in which the relative angle between the two data is slightly shifted. The difference from the data match value is often larger than in the absence of defects. Therefore, the degree of coincidence when the two-dimensional design data 22 projected in each angular direction is compared with the two-dimensional real data 21 photographed from this angular direction, and the two-dimensional real data 21 photographed slightly deviated from this angular direction. A difference from the degree of agreement in the case of comparison may be detected, and if this difference is equal to or less than a predetermined threshold value, it may be determined that the model 7 has some defect.

Since the size and type of defects that are allowed differ depending on the modeled object 7, it is desirable to set the size of the threshold value to be compared with the degree of coincidence according to the type of modeled object 7.

In the flowchart of FIG. 2, an example in which the modeled object 7 is rotated on the turntable 8 and the two-dimensional actual data 21 and the two-dimensional design data 22 in a plurality of angular directions orthogonal to the rotation axis of the turntable 8 are compared. However, the two-dimensional real data 21 and the two-dimensional design data 22 in a plurality of angular directions within an arbitrary angular range with respect to the height direction of the modeled object 7 may be compared. In this case as well, the difference between the two-dimensional real data 21 and the two-dimensional design data 22 may be extracted and the degree of coincidence may be detected by the same processing procedure as in FIG.

In the above description, the first generation unit 2 has generated a plurality of two-dimensional design data obtained by projecting the three-dimensional design data onto two-dimensional planes in a plurality of angular directions. In addition, the second generation unit 4 generates a plurality of two-dimensional real data based on a plurality of imaging data from a plurality of angular directions imaged by the camera 3. Then, the comparison unit 5 compares the plurality of two-dimensional design data and the plurality of two-dimensional real data in the corresponding angular directions. The present embodiment is not limited to such an embodiment. For example, the first generation unit 2 generates a single two-dimensional design data by projecting the three-dimensional design data onto a two-dimensional plane in a single angular direction, and the second generation unit 4 simply captures the image with the camera 3. A single two-dimensional real data may be generated based on a single imaging data from one angular direction. Then, the comparison unit 5 may compare the single two-dimensional design data with the single two-dimensional real data.

As described above, according to the present embodiment, the two-dimensional real data 21 and the two-dimensional design data 22 in the corresponding angular directions are compared, and the two-dimensional design data 22 is produced by a 3D printer based on the comparison result. Since the outer shape of the model 7 is inspected, even if there is any defect in the outer shape of the model 7, the defect can be automatically detected without omission. According to the present embodiment, since the outer shape of the model 7 can be inspected without visual inspection by humans, it is possible to quickly perform a highly reliable inspection even if the model 7 has a complicated outer shape. it can. As a result, the quality of the modeled object 7 produced by the 3D printer can be improved. Further, the inspection method of the present embodiment can be applied regardless of the type of the 3D printer and the type of the modeled object 7, and the utility value is extremely high.

At least a part of the modeled object inspection device 1 described in the above-described embodiment may be configured by hardware or software. When configured by software, a program that realizes at least a part of the functions of the model inspection device 1 may be stored in a recording medium such as a flexible disk or a CD-ROM, read by a computer, and executed. The recording medium is not limited to a removable one such as a magnetic disk or an optical disk, and may be a fixed recording medium such as a hard disk device or a memory.

Further, a program that realizes at least a part of the functions of the model inspection device 1 may be distributed via a communication line (including wireless communication) such as the Internet. Further, the program may be encrypted, modulated, compressed, and distributed via a wired line or wireless line such as the Internet, or stored in a recording medium.

The aspects of the present disclosure are not limited to the individual embodiments described above, but also include various modifications that can be conceived by those skilled in the art, and the effects of the present disclosure are not limited to the contents described above. That is, various additions, changes and partial deletions are possible without departing from the conceptual idea and purpose of the present disclosure derived from the contents defined in the claims and their equivalents.

1 Modeled object inspection device, 2 1st generation unit, 3 camera, 4 2nd generation unit, 5 comparison unit, 6 inspection unit, 7 modeled object, 8 turntable, 9 screen, 11 rotation drive device, 21 2D real data , 22 2D design data

Claims (6)

A first generator that generates 2D design data that projects 3D design data used to create a modeled object with a 3D printer onto a 2D plane.
An imaging unit that images the modeled object produced by the 3D printer, and
A second generation unit that generates two-dimensional real data including two-dimensional outline contour information based on the imaging data captured by the imaging unit, and a second generation unit.
A comparison unit that compares the two-dimensional design data and the two-dimensional real data in the corresponding angular directions, and
An inspection unit for inspecting the outer shape of the modeled object based on the comparison result of the comparison unit is provided .
The comparison unit compares the plurality of the two-dimensional design data acquired from the plurality of angular directions with the plurality of the two-dimensional real data in the corresponding angular directions, and the corresponding two-dimensional design data and the imaging data. Detects the degree of agreement with
The inspection unit inspects the outer shape of the modeled object based on the degree of matching, and if the degree of matching is lower than a predetermined threshold value, determines that the outer shape of the modeled object is defective.
In the detection of the degree of coincidence, the comparison unit includes a first value representing the degree of coincidence when the plurality of two-dimensional design data and the plurality of two-dimensional real data are compared with each other in the corresponding angular directions. Detects the difference between the second value representing the degree of coincidence when comparing in the angular directions shifted by a predetermined angle, and
The inspection unit, the inspection of the outer shape based on the coincidence degree, based on said said first value difference, the shaped article molded product detection unit you examine the outer shape of. A turntable for rotating the modeled object produced by the 3D printer around one axis is provided.
The imaging unit generates moving image data obtained by capturing the modeled object from one direction while rotating the modeled object on the turntable.
The modeled object inspection device according to claim 1 , wherein the second generation unit generates the plurality of two-dimensional real data based on the plurality of imaging data included in the moving image data. The two-dimensional design data is binarized digital data including external contour information obtained by projecting the three-dimensional design data onto a two-dimensional plane.
The modeled object inspection device according to claim 1 or 2 , wherein the two-dimensional actual data is binarized digital data including external contour information obtained by capturing the modeled object from directions corresponding to the plurality of angular directions. Two-dimensional design data that projects the three-dimensional design data used to create a modeled object with a 3D printer onto a two-dimensional plane, and
A comparison unit that compares two-dimensional real data including external contour information generated based on imaging data obtained by imaging the modeled object produced by the 3D printer in the corresponding angular directions.
An inspection unit for inspecting the outer shape of the modeled object based on the comparison result of the comparison unit is provided .
The comparison unit prepares a plurality of the two-dimensional design data and the two-dimensional real data in the vicinity of the angle of the two-dimensional plane on which the two-dimensional design data is projected, and prepares the two-dimensional design data and the two-dimensional real object, respectively. data compare the modeled object inspection controller. A first generator that generates 2D design data that projects 3D design data used to create a modeled object with a 3D printer onto a 2D plane.
An imaging unit that images the modeled object produced by the 3D printer, and
A second generation unit that generates two-dimensional real data including two-dimensional outline contour information based on the imaging data captured by the imaging unit, and a second generation unit.
A comparison unit that compares the two-dimensional design data and the two-dimensional real data,
Equipped with a,
The comparison unit prepares a plurality of the two-dimensional design data and the two-dimensional real data in the vicinity of the angle of the two-dimensional plane on which the two-dimensional design data is projected, and prepares the two-dimensional design data and the two-dimensional real object, respectively. shaped object inspection device data compare. A process of generating a plurality of two-dimensional design data by projecting the three-dimensional design data used for producing a modeled object with a 3D printer onto a two-dimensional plane, and
The process of imaging the modeled object produced by the 3D printer and
A process of generating two-dimensional real data including two-dimensional outline contour information based on the captured image data, and
Wherein the two-dimensional design data and the two-dimensional real data, and comparing with the corresponding angular direction between,
Including a step of inspecting the outer shape of the modeled object based on the result of the comparison.
In the comparison step, the plurality of the two-dimensional design data acquired from the plurality of angular directions and the plurality of the two-dimensional real data are compared with each other in the corresponding angular directions, and the corresponding two-dimensional design data and the imaging are performed. Including detecting the degree of agreement with the data
In the step of inspecting, the outer shape of the modeled object is inspected based on the degree of matching, and if the degree of matching is lower than a predetermined threshold value, it is determined that the outer shape of the modeled object is defective. Including
In the step of comparing, in the detection of the degree of coincidence, the plurality of two-dimensional design data and the plurality of two-dimensional real data are compared with the first value representing the degree of coincidence when the corresponding angular directions are compared with each other. Includes detecting the difference between the second value representing the degree of coincidence when comparing in the angular directions shifted by a predetermined angle.
The step of inspecting is a modeled object inspection method including inspecting the outer shape of the modeled object based on the first value and the difference in the inspection of the outer shape based on the degree of coincidence.

Images