Image processing apparatus, image forming system, image processing method, and non-transitory computer-readable storage medium
There is provided with an image processing apparatus that generates learning data for use in machine learning using a model. An obtaining unit is configured to obtain a first image for use in learning by the model. A generating unit is configured to, in a case where a first luminance of the first image is greater than a threshold, generate a second image with a second luminance different to the first luminance.
1. An image processing apparatus, comprising:
at least one memory storing instructions; and
at least one processor that, upon execution of the instructions, is configured to:
obtain a model that learns an image on the basis of image luminance, a first image already learned by the model, and a second image not learned by the model;
determine whether or not a second luminance of the second image is greater than a first luminance of the first image;
generate, as an image with a luminance different from the first luminance, according to a result of the at least one processor, the second image as third image; and
estimate a third luminance of the third image using the model including a learning result of the first image,
wherein the at least one processor sets a range of the third luminance on the basis of a frequency that a difference between an estimating result of the at least one processor and the first luminance is greater than specified value.
2. The image processing apparatus according to claim 1 , the at least one processor is further configured to:
recover the third luminance estimated by the at least one processor to the second luminance.
3. An image processing method executed by an image processing apparatus that generates learning data for use in machine learning using a model, the image processing method comprising:
obtaining a model that learns an image on the basis of image luminance, a first image already learned by the model, and a second image not learned by the model;
determining whether or not a second luminance of the second image is greater than a first luminance of the first image;
generating, as an image with a luminance different from the first luminance, according to a result of the determining, the second image as a third image; and
estimating a third luminance of the third image using the model including a learning result of the first image,
wherein the generating includes setting a range of the third luminance on the basis of a frequency that a difference between an estimating result of the estimating and the first luminance is greater than a specified value.
4. A non-transitory computer-readable storage medium storing a program that, when executed by a computer, causes the computer to perform an image processing method, the image processing method comprising:
obtaining a model that learns an image on the basis of image luminance, a first image already learned by the model, and a second image not learned by the model;
determining whether or not a second luminance of the second image is greater than a first luminance of the first image;
generating, as an image with a luminance different from the first luminance, according to a result of the determining, the second image as a third image; and
estimating a third luminance of the third image using the model including a learning result of the first image,
wherein the generating includes setting a range of the third luminance on the basis of a frequency that a difference between an estimating result of the estimating and the first luminance is greater than a specified value.