Information processing apparatus, information processing method, and program
An object of the present invention is to provide an information processing apparatus, an information processing method, and a program which make it possible to appropriately identify a lens from an image showing a cross section of the lens. In the present invention, a processor detects an existing region of a lens in a target image showing a cross section of a part including the lens in a target device including the lens, and the processor identifies the lens of the target device existing in the existing region based on a feature amount of the existing region by an identification model constructed by machine learning using a plurality of learning images showing a cross section of the lens.
1 . An information processing apparatus comprising:
a processor,
wherein the processor
detects an existing region of a lens, which is a region in which the lens exists, in a target image showing a cross section of a part including the lens in a target device including the lens,
identifies the lens of the target device existing in the existing region based on a feature amount of the existing region by an identification model constructed by machine learning using a plurality of learning images showing a cross section of the lens, and
the identification model is configured by machine learning using the plurality of learning images including two or more same-type lens cross-sectional images showing cross sections of the same type of lens with different drawing styles, the identification model being a model that identifies a lens shown by each of the two or more same-type lens cross-sectional images as the same type of lens.
2 . The information processing apparatus according to claim 1 ,
wherein the processor accumulates information about the identified lens of the target device to construct a database of the information.
3 . A database device acquiring information about the identified lens of the target device from the information processing apparatus according to claim 1 and accumulating the information.
4 . The database device according to claim 3 ,
wherein the database device accumulates the information about the identified lens of the target device in association with information about a document including the target image.
5 . An information processing apparatus comprising:
a processor,
wherein the processor
detects an existing region of a lens, which is a region in which the lens exists, in a target image that shows a cross section of a part including the lens in a target device including the lens and that is published or inserted in documents,
identifies the lens of the target device existing in the existing region based on a feature amount of the existing region by an identification model constructed by machine learning using a plurality of learning images showing a cross section of the lens,
accumulates information about the identified lens of the target device to construct a database of the information,
acquires input information about a lens provided in a search device,
calculates a degree of similarity between the lens of the search device and the lens of the target device based on the input information and the information about the lens of the target device accumulated in the database, and
outputs the information about the lens of the target device accumulated in the database in association with the degree of similarity.
6 . An information processing apparatus comprising:
a processor,
wherein the processor
detects an existing region of a lens, which is a region in which the lens exists, in a target image that shows a cross section of a part including the lens in a target device including the lens and that is published or inserted in documents,
identifies the lens of the target device existing in the existing region based on a feature amount of the existing region by an identification model constructed by machine learning using a plurality of learning images showing a cross section of the lens,
accumulates information about the identified lens of the target device to construct a database of the information,
detects the existing region for each lens in the target image showing a cross section of a part including lens groups arranged in a row in the target device including the lens groups,
identifies a lens in the lens group existing in the existing region for each existing region by using the identification model,
aggregates information about the lens in the lens group identified for each existing region with the lens group as one unit, and accumulates the aggregated information in the database,
specifies, for each existing region, a type of the lens in the lens group identified for each existing region,
generates character string information representing the type of each lens in an order in which the lenses are arranged in the lens group, based on the type of the lens in the lens group specified for each existing region and a position of the existing region in the target image,
accumulates the generated character string information in the database,
acquires input information about a lens included in a search device,
in a case in which the search device includes a lens group, acquires character string information representing a type of each lens in an order in which lenses are arranged in the lens group of the search device, as the input information,
calculates a first degree of similarity between the lens group of the search device and the lens group of the target device, based on the acquired character string information about the lens group of the search device and the character string information about the lens group of the target device accumulated in the database, and
outputs the character string information about the lens group of the target device accumulated in the database in association with the first degree of similarity.
7 . An information processing method comprising:
via a processor,
a step of detecting an existing region of a lens, which is a region in which the lens exists, in a target image showing a cross section of a part including the lens in a target device including the lens;
via the processor,
a step of identifying the lens of the target device existing in the existing region based on a feature amount of the existing region by an identification model constructed by machine learning using a plurality of learning images showing a cross section of the lens; and
the identification model is configured by machine learning using the plurality of learning images including two or more same-type lens cross-sectional images showing cross sections of the same type of lens with different drawing styles, the identification model being a model that identifies a lens shown by each of the two or more same-type lens cross-sectional images as the same type of lens.