Image analysis method and image analysis device for identifying musical information
AssigneeYamaha Corporation
InventorKazuhiko Yamamoto
Life of this patent
Estimating the term…
Abstract
Disclosed is an image analysis method implemented by a computer, the method including analyzing a partial image which is a part of an image of a planar subject, generating partial-image analysis data representing a characteristic of the partial image, comparing, for each of a plurality of images, candidate-image analysis data with the partial-image analysis data, the candidate-image analysis data representing a characteristic of each of the plurality of images, and selecting a candidate image among the plurality of images, the candidate image including a part corresponding to the partial image.
Claims9
An image analysis method implemented by a computer, the method comprising:
- analyzing a partial image which is a part of an image of a planar subject;
- generating, based on the analysis of the partial image, partial-image analysis data representing a characteristic of the partial image;
- comparing, for each of a plurality of images, candidate-image analysis data with the partial-image analysis data, wherein
- the candidate-image analysis data representing a characteristic of each of the plurality of images,
- the candidate-image analysis data includes a plurality of projection points,
- and
- at least one projection point of the plurality of projection points is a point obtained by projection of at least one feature point of a plurality of feature points onto a reference line;
- and
- selecting, based on the comparison, a candidate image among the plurality of images, wherein the candidate image including a part corresponding to the partial image.
An image analysis device, comprising:
- an electronic controller including at least one processor, the electronic controller being configured to execute a plurality of modules including:
- an analysis processing module configured to:
- analyze a partial image which is a part of an image of a planar subject;
- and
- generate, based on the analysis of the partial image, partial-image analysis data representing a characteristic of the partial image;
- and
- an identification processing module configured to:
- compare, for each of a plurality of images, candidate-image analysis data with the partial-image analysis data, wherein
- the candidate-image analysis data representing a characteristic of each of the plurality of images,
- the candidate-image analysis data includes a plurality of projection points, and
- at least one projection point of the plurality of projection points is a point obtained by projection of at least one feature point of a plurality of feature points onto a reference line;
- and
- select, based on the comparison, a candidate image among the plurality of images, wherein the candidate image including a part corresponding to the partial image.
A non-transitory computer-readable storage medium storing a program for causing a computer to execute processing, comprising:
- by an analysis processing module, analyzing a partial image which is a part of an image of a planar subject;
- by the analysis processing module, generating partial-image analysis data representing a characteristic of the partial image based on the analysis of the partial image;
- by an identification processing module, comparing, for each of a plurality of images, candidate-image analysis data with the partial-image analysis data, wherein
- the candidate-image analysis data representing a characteristic of each of the plurality of images,
- the candidate-image analysis data includes a plurality of projection points,
- and
- at least one projection point of the plurality of projection points is a point obtained by projection of at least one feature point of a plurality of feature points onto a reference line;
- and
- by the identification processing module, selecting, based on the comparison, a candidate image among the plurality of images, wherein the candidate image including a part corresponding to the partial image.
Dependencies are inferred from the claim text.