Information processing apparatus, information processing method, and storage medium
AssigneeCanon Kabushiki Kaisha
InventorAtsushi Nogami
Life of this patent
Estimating the term…
Abstract
An information processing apparatus comprising: a first acquiring unit configured to acquire information about learning data used in learning of each of a plurality of prelearned models for recognizing input data; a second acquiring unit configured to acquire information indicating an attribute of recognition target data; and a model selecting unit configured to select a model to be used in recognition of the recognition target data from the plurality of models, based on a degree of matching between the attribute of the recognition target data and an attribute of the learning data used in learning of each of the plurality of models, and on diversity of the attribute of the learning data used in learning of each of the plurality of models.
Claims9
An information processing apparatus comprising:
- a first acquiring unit configured to acquire information about learning data used in learning of each of a plurality of prelearned models for recognizing input data;
- a second acquiring unit configured to acquire information indicating an attribute set of recognition target data, the recognition target data comprising images of an infrastructure;
- and
- a model selecting unit configured to select, from the plurality of models, as a model to be used in recognition of the recognition target data, a model having learned attribute items of an attribute set of the learning data used in learning of each of the plurality of models, which match with attribute items of the attribute set of the recognition target data for which True is set,
- wherein the attribute set of the learning data and the attribute set of the recognition target data is information in which True or False is set for each attribute item, and
- wherein the recognition of the recognition target data comprises the recognition of a defect of the infrastructure, and
- wherein, in case several models which have learned the attribute items for which True is set are selected by the model selecting unit, the model selecting unit is configured to select from the several models as the model to be used in recognition of the recognition target data a model in which a number of attribute items for which True is set in the learning data is smallest.
An information processing method comprising:
- acquiring information about learning data used in learning of each of a plurality of prelearned models for recognizing input data;
- acquiring information indicating an attribute set of recognition target data, the recognition target data comprising images of an infrastructure;
- and
- selecting from the plurality of models as a model to be used in recognition of the recognition target data, a model having learned attribute items of an attribute set of the learning data used in learning of each of the plurality of models, which match with attribute items of the attribute set of the recognition target data for which True is set,
- wherein the attribute set of the learning data and the attribute set of the recognition target data is information in which True or False is set for each attribute item, and
- wherein the recognition of the recognition target data comprises the recognition of a defect of the infrastructure, and
- wherein, in case several models which have learned the attribute items for which True is set are selected, a model that has a smallest number of attribute items for which True is set in the learning data is selected from the several models as the model to be used in recognition of the recognition target data.
A non-transitory computer readable storage medium storing a computer program for causing a computer to execute an information processing method comprising:
- acquiring information about learning data used in learning of each of a plurality of prelearned models for recognizing input data;
- acquiring information indicating an attribute set of recognition target data, the recognition target data comprising images of an infrastructure;
- and
- selecting from the plurality of models as a model to be used in recognition of the recognition target data, a model having learned attribute items of an attribute set of the learning data used in learning of each of the plurality of models, which match with attribute items of the attribute set of the recognition target data for which True is set,
- wherein the attribute set of the learning data and the attribute set of the recognition target data is information in which True or False is set for each attribute item, and
- wherein the recognition of the recognition target data comprises the recognition of a defect of the infrastructure, and
- wherein, in case several models which have learned the attribute items for which True is set are selected, a model that has a smallest number of attribute items for which True is set in the learning data is selected from the several models as the model to be used in recognition of the recognition target data.
Dependencies are inferred from the claim text.