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

An image processing method executed by an image processing apparatus for processing an image acquired by imaging a living body, the method comprising:

• extracting a plurality of blood vessel candidate regions from the image;
• extracting, from among the plurality of blood vessel candidate regions, a blood vessel candidate region group estimated to form a line shape when integrated, as an identical blood vessel candidate region;
• calculating one or more kinds of evaluation values for evaluating a likelihood that the identical blood vessel candidate region corresponds to an identical blood vessel;
• discriminating whether or not the identical blood vessel candidate region forms an identical blood vessel region, based on the evaluation values;
• calculate depth information that is information corresponding to a distance between an imaging unit and a subject when capturing the image;
• and
• calculate feature data representing continuity of the depth information within the identical blood vessel candidate region,
• wherein the feature data representing the continuity of the depth information is used as the evaluation value.

A non-transitory computer-readable recording medium with an executable program stored thereon, the program instructing an image processing apparatus for processing an image acquired by imaging a living body, to execute:

• extracting a plurality of blood vessel candidate regions from the image;
• extracting, from among the plurality of blood vessel candidate regions, a blood vessel candidate region group estimated to form a line shape when integrated, as an identical blood vessel candidate region;
• calculating one or more kinds of evaluation values for evaluating a likelihood that the identical blood vessel candidate region corresponds to an identical blood vessel;
• discriminating whether or not the identical blood vessel candidate region forms an identical blood vessel region, based on the evaluation values;
• calculate depth information that is information corresponding to a distance between an imaging unit and a subject when capturing the image;
• and
• calculate feature data representing continuity of the depth information within the identical blood vessel candidate region,
• wherein the feature data representing the continuity of the depth information is used as the evaluation value.