Information processing system, area determination method, and medium

An area determination method for causing a computer, which determines a partial area used in an erectness determination which determines whether an input determination target image is erect based on a determination feature in the partial area in an image having a predetermined format and a position of the partial area in a state in which the image having the predetermined format is erect, to execute:

• receiving input of a plurality of learning images having the predetermined format;
• extracting one or more areas common to the plurality of learning images in an erect state as one or more candidates for the partial area, each of which is a candidate for the partial area used in the erectness determination;
• determining, after extracting the one or more candidates for the partial area that are the one or more areas common to the plurality of learning images, for each of the one or more candidates for the partial area, a commonality degree indicative of a degree of a possibility that the candidate for the partial area is an area which a plurality of images that have the predetermined format and are different from each other have in common at substantially the same position;
• determining, after extracting the one or more candidates for the partial area that are the one or more areas common to the plurality of learning images, for each of the one or more candidates for the partial area, whether the candidate for the partial area corresponds to an unsuitable area which is an area unsuitable for the erectness determination;
• determining, for each of the one or more candidates for the partial area, an exclusion degree indicative of a degree of exclusion of the candidate for the partial area from a target of the partial area used in the erectness determination according to a result of determining whether the candidate for the partial area corresponds to the unsuitable area;
• calculating, for each of one or more candidates for the partial area, common area reliability indicative of a degree to which the candidate for the partial area is suitable as the partial area used in the erectness determination, based on the commonality degree and the exclusion degree that are determined as to the candidate for the partial area;
• and
• determining one or more partial areas used in the erectness determination from the one or more candidates for the partial area, based on the common area reliability,
• wherein the exclusion degree is set such that the common area reliability of the candidate for the partial area is reduced in a case where the candidate for the partial area is the unsuitable area;
• and
• the computer calculates, for each of the one or more candidates for the partial area, the common area reliability using a calculation method that adds, subtracts, or multiplies the exclusion degree that is determined as to the candidate for the partial area to the commonality degree that is determined as to the candidate for the partial area.

A non-transitory computer-readable recording medium on which is recorded a program for causing a computer, which determines a partial area used in an erectness determination which determines whether an input determination target image is erect based on a determination feature in the partial area in an image having a predetermined format and a position of the partial area in a state in which the image having the predetermined format is erect, to execute a process comprising:

• receiving input of a plurality of learning images having the predetermined format;
• extracting one or more areas common to the plurality of learning images in an erect state as one or more candidates for the partial area, each of which is a candidate for the partial area used in the erectness determination;
• determining, after extracting the one or more candidates for the partial area that are the one or more areas common to the plurality of learning images, for each of the one or more candidates for the partial area, a commonality degree indicative of a degree of a possibility that the candidate for the partial area is an area which a plurality of images that have the predetermined format and are different from each other have in common at substantially the same position;
• determining, after extracting the one or more candidates for the partial area that are the one or more areas common to the plurality of learning images, for each of the one or more candidates for the partial area, whether the candidate for the partial area corresponds to an unsuitable area which is an area unsuitable for the erectness determination;
• determining, for each of the one or more candidates for the partial area, an exclusion degree indicative of a degree of exclusion of the candidate for the partial area from a target of the partial area used in the erectness determination according to a result of determining whether the candidate for the partial area corresponds to the unsuitable area;
• calculating, for each of one or more candidates for the partial area, common area reliability indicative of a degree to which the candidate for the partial area is suitable as the partial area used in the erectness determination, based on the commonality degree and the exclusion degree that are determined as to the candidate for the partial area;
• and
• determining one or more partial areas used in the erectness determination from the one or more candidates for the partial area, based on the common area reliability,
• wherein the exclusion degree is set such that the common area reliability of the candidate for the partial area is reduced in a case where the candidate for the partial area is the unsuitable area;
• and
• the processor calculates, for each of the one or more candidates for the partial area, the common area reliability using a calculation method that adds, subtracts, or multiplies the exclusion degree that is determined as to the candidate for the partial area to the commonality degree that is determined as to the candidate for the partial area.