Information processing apparatus, information processing method, and program
AssigneesMeiji University, Ns Solutions Corporation
InventorsRyusuke Miyamoto, Sei Sato
Life of this patent
Estimating the term…
Abstract
An appearance of a desired change can be detected in a more preferred manner even under circumstances where various kinds of changes can appear in a target image. An information processing apparatus includes: a generator configured to generate a normalized image by performing a normalization process using a learned model constructed in advance based on a machine learning with a plurality of normal images as input, on an input image; a determiner configured to determine whether the normalized image and a prescribed reference image approximately match or not; and an outputter configured to output notification information according to a result of the determination to a prescribed output destination.
Claims17
An information processing apparatus comprising:
- a generator configured to generate a normalized image by performing a normalization process using a learned model constructed in advance based on a machine learning with a plurality of normal images as input, on an input image;
- a determiner configured to determine whether the normalized image and a prescribed reference image approximately match or not;
- and
- an outputter configured to output notification information according to a result of the determination to a prescribed output destination.
An information processing method executed by an information processing apparatus, comprising:
- a generating step of generating a normalized image by performing a normalization process using a learned model constructed in advance based on a machine learning with a plurality of normal images as input, on an input image;
- a determining step of determining whether the normalized image and a prescribed reference image approximately match or not;
- and
- an outputting step of outputting notification information according to a result of the determination to a prescribed output destination.
A non-transitory computer-readable medium storing instructions executable by a processor of an information processing apparatus, wherein the instructions, when executed, cause to the processor to execute:
- a generating step of generating a normalized image by performing a normalization process using a learned model constructed in advance based on a machine learning with a plurality of normal images as input, on an input image;
- a determining step of determining whether the normalized image and a prescribed reference image approximately match or not;
- and
- an outputting step of outputting notification information according to a result of the determination to a prescribed output destination.
An information processing apparatus comprising:
- a constructor configured to construct a learned model configured to generate a normalized image by performing a normalization process of making a feature of an input image closer to a feature of a prescribed reference image on the input image, based on a machine learning, wherein
- the constructor:
- with any of a plurality of normal images as the reference image;
- by using a generative adversarial network constituted of a combination of the learned model and a discriminator configured to discriminate between the normalized image and the reference image, the normalized image being generated by the normalization process performed on other normal images other than the reference image among the plurality of normal images by the learned model;
- and
- constructs the learned model so as to perform the normalization process that makes a discrimination between the normalized image and the reference image more difficult for the discriminator, on an input image.
An information processing method executed by an information processing apparatus, comprising:
- a constructing step of constructing a learned model configured to generate a normalized image by performing a normalization process of making a feature of an input image closer to a feature of a prescribed reference image on the input image, based on a machine learning, wherein
- in the constructing step:
- with any of a plurality of normal images as the reference image;
- by using a generative adversarial network constituted of a combination of the learned model and a discriminator configured to discriminate between the normalized image and the reference image, the normalized image being generated by the normalization process performed on other normal images other than the reference image among the plurality of normal images by the learned model;
- and
- the learned model is constructed so as to perform the normalization process that makes a discrimination between the normalized image and the reference image more difficult for the discriminator, on an input image.
A non-transitory computer-readable medium storing instructions executable by a processor of an information processing apparatus, wherein the instructions, when executed, cause to the processor to execute:
- a constructing step of constructing a learned model configured to generate a normalized image by performing a normalization process of making a feature of an input image closer to a feature of a prescribed reference image on the input image, based on a machine learning, wherein
- in the constructing step:
- with any of a plurality of normal images as the reference image;
- by using a generative adversarial network constituted of a combination of the learned model and a discriminator configured to discriminate between the normalized image and the reference image, the normalized image being generated by the normalization process performed on other normal images other than the reference image among the plurality of normal images by the learned model;
- and
- the learned model is constructed so as to perform the normalization process that makes a discrimination between the normalized image and the reference image more difficult for the discriminator, on an input image.
Dependencies are inferred from the claim text.