Data creation system, learning system, estimation system, processing device, evaluation system, data creation method, and program
View Patent ↗A data creation system creates, based on first image data, second image data for use as learning data. A processor of the data creation system generates, based on the first image data including a first region as a pixel region representing the object and a second region adjacent to the first region, the second image data by causing deformation about height of the first region with respect to a reference plane. The processor generates the second image data such that the closer to a reference point within the first region a point of interest is, the greater a variation in the height of the first region with respect to the reference plane is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the variation in the height of the first region with respect to the reference plane is.
1 . A data creation system configured to create, based on first image data, second image data for use as learning data to generate a learned model about an object, the data creation system comprising:
a processor configured to generate, based on the first image data including a first region as a pixel region representing the object and a second region adjacent to the first region, the second image data by causing deformation about height of the first region such that the closer to a reference point within the first region a point of interest is, the greater a variation in the height of the first region with respect to a reference plane is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the variation in the height of the first region with respect to the reference plane is.
2 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused to make a tilt angle at the reference point with respect to the reference plane fall within a predetermined angular range including zero degrees.
3 . The data creation system of claim 1 , wherein
the reference point includes a plurality of reference points arranged side by side in a direction intersecting with an arrangement direction of the first region and the second region.
4 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused to allow height at the reference point with respect to the reference plane to go beyond a maximum point, of which height with respect to the reference plane is maximum within the first region before the deformation.
5 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused to allow height at the reference point with respect to the reference plane to come under a maximum point, of which height with respect to the reference plane is maximum within the first region before the deformation.
6 . The data creation system of claim 1 , wherein
the reference point is set at a middle of the first region in an arrangement direction of the first region and the second region.
7 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused to allow the variation at the boundary to fall within a predefined range including zero.
8 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused to allow a tilt angle at the boundary with respect to the reference plane to fall within a predetermined angular range including zero degrees.
9 . The data creation system of claim 1 , wherein
the deformation about the height of the first region is caused, when any particular region showing a particular form is present in the first region with respect to the boundary, to the first region except the particular region.
10 . The data creation system of claim 1 , wherein
the first region is a pixel region representing a welding region formed by welding together two base materials to be welded, and
the second region is a pixel region representing any one of the two base materials.
11 . The data creation system of claim 1 , wherein
the processor includes an acquirer configured to acquire specification information to specify a location of the reference point in the first region.
12 . A learning system configured to generate the learned model using a learning data set, the learning data set including the learning data as the second image data, the second image data being created by the data creation system of claim 1 .
13 . An estimation system configured to estimate a particular condition of the object as an object to be recognized using the learned model generated by the learning system of claim 12 .
14 . A data creation method for creating, based on first image data, second image data for use as learning data to generate a learned model about an object, the data creation method comprising:
a processing step including generating, based on the first image data including a first region as a pixel region representing the object and a second region adjacent to the first region, the second image data by causing deformation about height of the first region such that the closer to a reference point within the first region a point of interest is, the greater a variation in the height of the first region with respect to a reference plane is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the variation in the height of the first region with respect to the reference plane is.
15 . A non-transitory storage medium storing a program designed to cause one or more processors to perform the data creation method of claim 14 .
16 . A data creation system configured to create, based on first image data, second image data for use as learning data to generate a learned model about an object, the data creation system comprising:
a first processing device configured to determine, with respect to the first image data including a first region as a pixel region representing the object and a second region adjacent to the first region, a height variation as a variation in height of the first region with respect to a reference plane such that the closer to a reference point within the first region a point of interest is, the greater the height variation is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the height variation is; and
a second processing device configured to determine, based on the height variation determined by the determiner, the second image data by causing deformation about the height of the first region to the first image data.
17 . The data creation system of claim 16 , wherein
the first processing device is configured to transmit information indicating the height variation to the second processing device.
18 . The data creation system of claim 17 , wherein
the first processing device further includes a specifier configured to specify the reference point in the first image data in accordance with an operating command entered by a user.
19 . The data creation system of claim 17 , wherein
the second processing device is configured to receive the information indicating the height variation.
20 . An evaluation system comprising at least one processing device, wherein
the at least one processing device is configured to;
determine, based on first image data including a first region as a pixel region representing an object and a second region adjacent to the first region, a height variation as a variation in height of the first region with respect to a reference plane such that the closer to a reference point within the first region a point of interest is, the greater the height variation is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the height variation is; and output information indicating the height variation thus determined, and
generate a learned model, the learned model being configured to output, in response to either second image data or a deformed first region included in the second image data corresponding to the first region of the first image data, an estimation result similar to a situation where the first image data is subjected to estimation made about a particular condition of the object, the second image data being generated based on the height variation by causing deformation about the first region to the first image data and the deformed first region being generated by deforming the first region.
21 . An evaluation system comprising at least one processing device, wherein
the at least one processing device is configured to:
determine, based on first image data including a first region as a pixel region representing an object and a second region adjacent to the first region, a height variation as a variation in height of the first region with respect to a reference plane such that the closer to a reference point within the first region a point of interest is, the greater the height variation is and the closer to a boundary between the first region and the second region the point of interest is, the smaller the height variation is; and output information indicating the height variation thus determined,
to estimate a particular condition of the object as an object to be recognized using a learned model, and
to output, in response to either second image data or a deformed first region in the second image data corresponding to the first region of the first image data, an estimation result similar to a situation where the first image data is subjected to estimation made about the particular condition of the object, the second image data being generated based on the height variation by causing deformation about the first region to the first image data and the deformed first region being generated by deforming the first region.