Image processing apparatus, image processing method, and computer readable medium

An image processing method comprising:

• calculating, for each of a plurality of color separation images, a gradient direction of an edge gradient and an edge intensity at each position on the basis of a color captured image, the plurality of color separation images resulting from separation of the color captured image into a plurality of color components, the color captured image including an image of a subject captured with an imaging apparatus;
• detecting edge positions in each of the plurality of color separation images, on the basis of the calculated gradient directions of the edge gradients and the calculated edge intensities;
• identifying, for each position, the gradient direction of the edge gradient and the edge intensity at the position in a color separation image among the plurality of color separation images that includes the largest edge intensity at the position;
• and
• detecting a subject region on the basis of the detected edge positions, the identified gradient directions of the edge gradients, and the identified edge intensities, the subject region being a portion of the color captured image that corresponds to the image of the subject.

A computer readable medium storing a program causing a computer to execute a process for image processing, the process comprising:

• calculating, for each of a plurality of color separation images, a gradient direction of an edge gradient and an edge intensity at each position on the basis of a color captured image, the plurality of color separation images resulting from separation of the color captured image into a plurality of color components, the color captured image including an image of a subject captured with an imaging apparatus;
• detecting edge positions in each of the plurality of color separation images, on the basis of the calculated gradient directions of the edge gradients and the calculated edge intensities;
• identifying, for each position, the gradient direction of the edge gradient and the edge intensity at the position in a color separation image among the plurality of color separation images that includes the largest edge intensity at the position;
• and
• detecting a subject region on the basis of the detected edge positions, the identified gradient directions of the edge gradients, and the identified edge intensities, the subject region being a portion of the color captured image that corresponds to the image of the subject.