Information processing apparatus, control method, and non-transitory computer-readable storage medium for storing program

A control method implemented by an information processing apparatus configured to perform image processing on an image captured by an imaging apparatus, the method comprising:

• executing generation processing that includes generating candidates of second image processing program based on an image processing program, the image processing program being a program having a tree structure, and the second image processing program being a next generation image processing program in genetic programming;
• executing first evaluation processing that includes evaluating fitness of the candidates of the second image processing program by using low-resolution learning data, the low-resolution learning data being learning data including an input image and a target processing result, and being the learning data obtained by reducing the resolution of at least the input image;
• executing second evaluation processing that includes
• narrowing down the candidates of the second image processing program based on an evaluation result in the first evaluation processing, and
• evaluating the fitness of the narrowed-down candidates of the second image processing program by using the learning data;
• and
• executing determination processing that includes determining the second image processing program based on an evaluation result in the second evaluation processing.

A non-transitory computer-readable storage medium for storing a program which causes a computer to perform processing, the computer being configured to perform image processing on an image captured by an imaging apparatus, the processing comprising:

• executing generation processing that includes generating candidates of second image processing program based on an image processing program, the image processing program being a program having a tree structure, and the second image processing program being a next generation image processing program in genetic programming,
• executing first evaluation processing that includes evaluating fitness of the candidates of the second image processing program by using low-resolution learning data, the low-resolution learning data being learning data including an input image and a target processing result, and being the learning data obtained by reducing the resolution of at least the input image;
• executing second evaluation processing that includes
• narrowing down the candidates of the second image processing program based on an evaluation result in the first evaluation processing, and
• evaluating the fitness of the narrowed-down candidates of the second image processing program by using the learning data;
• and
• executing determination processing that includes determining the second image processing program based on an evaluation result in the second evaluation processing.