Image processing system, apparatus, method and storage medium
An image processing system includes a first setting unit configured to set, in a learning image, a plurality of mutually different position coordinates belonging to a region of interest presenting a site of interest rendered in the learning image, an extracting unit configured to extract the region of interest by using the plurality of position coordinates, a calculating unit configured to calculate a feature value for determining an attribute of the site of interest from a plurality of extraction results of the region of interest corresponding to the plurality of position coordinates, and a constructing unit configured to construct an identifier for determining the attribute based on a plurality of the feature values corresponding to the plurality of extraction results of the region of interest and a correct answer value of the attribute of the site of interest rendered in the learning image.
1. An image processing system comprising:
a memory that stores a program; and
a processor that executes the program stored in the memory to function as units including:
a first setting unit configured to set, in a learning image, a plurality of mutually different position coordinates belonging to a region of interest presenting a site of interest rendered in the learning image;
an extracting unit configured to extract the region of interest by using each of the plurality of position coordinates;
a calculating unit configured to calculate a feature value for determining an attribute of the site of interest from each of a plurality of extraction results of the region of interest corresponding to each of the plurality of position coordinates;
a constructing unit configured to construct an identifier for determining the attribute based on training data including a set of each of a plurality of the feature values corresponding to each of the plurality of extraction results of the region of interest and a correct answer value of the attribute of the site of interest rendered in the learning image;
a second setting unit configured to set, in an identification image, position coordinates belonging to the region of interest presenting the site of interest rendered in the identification image; and
a determining unit configured to determine an attribute of the site of interest rendered in the identification image by using the identifier and the position coordinates set by the second setting unit.
2. The image processing system according to claim 1 , wherein the first setting unit sets, in the learning image, the position coordinates based on a feature of the region of interest rendered in the learning image.
3. The image processing system according to claim 2 , wherein the feature is a concentration value of the region of interest rendered in the learning image.
4. The image processing system according to claim 1 , wherein the first setting unit sets, in the learning image, the position coordinates based on position coordinates set in the past.
5. The image processing system according to claim 4 , further comprising:
a generating unit configured to generate a model based on the position coordinates set in the past,
wherein the first setting unit sets, in the learning image, the position coordinates based on the model.
6. The image processing system according to claim 5 , wherein the model is a model representing probabilities that pixels in an image are designated as position coordinates.
7. The image processing system according to claim 5 , wherein the model is updated by using positional information set for the identification image.
8. An apparatus comprising:
a memory that stores a program; and
a processor that executes the program stored in the memory to function as units including:
a setting unit configured to set, in a learning image, a plurality of position coordinates belonging to a region of interest presenting a site of interest rendered in the learning image;
an extracting unit configured to extract the region of interest by using each of the plurality of position coordinates;
a calculating unit configured to calculate a feature value for determining an attribute of the site of interest from each of a plurality of extraction results of the region of interest corresponding to each of the plurality of position coordinates; and
a constructing unit configured to construct an identifier for determining the attribute based on training data including a set of each of a plurality of the feature values corresponding to each of the plurality of extraction results of the region of interest and a correct answer value of the attribute of the site of interest.
9. A method comprising:
setting, in a learning image, a plurality of position coordinates belonging to a region of interest presenting a site of interest rendered in the learning image;
extracting the region of interest by using each of the plurality of position coordinates;
calculating a feature value for determining an attribute of the site of interest from each of a plurality of extraction results of the region of interest corresponding to each of the plurality of position coordinates; and
constructing an identifier for determining the attribute based on training data including a set of each of a plurality of the feature values corresponding to the plurality of extraction results of the region of interest and a correct answer value of the attribute of the site of interest.
10. A non-transitory computer-readable storage medium storing a program causing a computer to execute the method according to claim 9 .