Eye image recognition method, eye image selection method and system therefor

An eye image selection method comprising the steps of:

• locating a center position of a pupil of an eye from an input image including the eye;
• and
• determining that, if a distance between the center position of said pupil and a center position of said input image is not greater than a preset value, said input image includes necessary eye data for carrying out individual identification, and selecting said input image,
• wherein said steps of locating a center position of a pupil comprises:
• dividing said input image into a plurality of blocks;
• producing a mosaic image with said blocks each representing a density value;
• determining one of said blocks as having a small distance from a center point of said mosaic image and having a small density value;
• and
• locating the center position of said pupil based on said determined block.

An eye image selection method comprising the steps of:

• locating a center position of a pupil of an eye from an input image including the eye;
• and
• determining that, if a density of a region including said center position is not greater than a given value, said input image includes said pupil for carrying out individual identification, and selecting said input image,
• wherein said step of locating a center position of a pupil comprises:
• dividing said input image into a plurality of blocks;
• producing a mosaic image with said blocks each representing a density value;
• determining one of said blocks as having a small distance from a center point of said mosaic image and having a small density value;
• and
• locating the center position of said pupil based on said determined block.

An eye image selection method comprising the steps of:

• locating a center position of a pupil of an eye from an input image including the eye, said step of locating a center position of a pupil including
• dividing an input image including an eye into a plurality of blocks,
• producing a mosaic image with said blocks each representing a density value,
• determining that one of said blocks, having a small distance from a center point of said mosaic image and having a small density value, is a block including said center position of said pupil, and
• locating the center position of said pupil from said determined block;
• and selecting said input image for carrying out individual identification if a distance between the center position of said pupil and a center position of said input image is not greater than a preset value and if a density of a region including the center position of said pupil is not greater than a preset value.