Information processing apparatus, information processing method, and storage medium
AssigneeCanon Kabushiki Kaisha
InventorYosuke Takada
Life of this patent
Estimating the term…
Abstract
The information processing apparatus obtains a distribution characteristic representing an attribute of a color included in an acquired first image group and determines the number of times of learning based on the distribution characteristic. The information processing apparatus generates a data set consisting of a set of the first image group and a second image group corresponding to the first image group and by using the generated data set, generates a learning model by performing learning using a network based on the determined number of times of learning.
Claims13
An information processing apparatus that generates a learning model using a network, the information processing apparatus comprising:
- an acquisition unit configured to acquire a first image group consisting of teacher images comprising plural color components;
- an analysis unit configured to obtain a distribution characteristic representing an attribute of a color included in the first image group;
- a generation unit configured to generate a data set consisting of a set of the first image group and a second image group corresponding to the first image group;
- a determination unit configured to determine a number of times of learning based on the distribution characteristic;
- and
- a learning unit configured to generate a learning model by performing learning using the network by using the data set based on the number of times of learning.
An information processing method of generating a learning model using a network, the information processing method comprising:
- an acquisition step of acquiring a first image group consisting of teacher images comprising plural color components;
- an analysis step of obtaining a distribution characteristic representing an attribute of a color included in the first image group;
- a generation step of generating a data set consisting of a set of the first image group and a second image group corresponding to the first image group;
- a determination step of determining a number of times of learning based on the distribution characteristic;
- and
- a learning step of generating a learning model by performing learning using the network by using the data set based on the number of times of learning.
A non-transitory computer-readable storage medium storing a program for causing a computer to execute an information processing method of generating a learning model using a network, the information processing method comprising:
- acquiring a first image group consisting of teacher images comprising plural color components;
- obtaining a distribution characteristic representing an attribute of a color included in the first image group;
- generating a data set consisting of a set of the first image group and a second image group corresponding to the first image group;
- determining a number of times of learning based on the distribution characteristic;
- and
- generating a learning model by performing learning using the network by using the data set based on the number of times of learning.
Dependencies are inferred from the claim text.