Image processing apparatus, image processing method, computer program, and storage medium

Claim 2

An image processing apparatus comprising: a calculating unit configured to calculate an evaluation amount of red eye for every pixel satisfying a predetermined condition in an image; an extracting unit configured to extract a candidate pixel having red eye including a pupil on the basis of the evaluation amount; and one or more processors programmed to control at least one of the calculating unit and extracting unit, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 3

An image processing method comprising the steps of: calculating an evaluation amount of red eye for every pixel satisfying a predetermined condition in an image; and extracting a candidate pixel having red eye including a pupil on the basis of the evaluation amount, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 4

An image processing method comprising the steps of: calculating an evaluation amount of red eye for every pixel satisfying a predetermined condition in an image; and extracting a candidate pixel having red eye including a pupil on the basis of the evaluation amount, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 5

An image processing apparatus comprising: a calculating unit configured to calculate an evaluation amount of red eye on the basis of a predetermined color component for every pixel satisfying a predetermined condition in an image; a pixel extracting unit configured to extract a candidate pixel in the image area having red eye including a pupil on the basis of the evaluation amount; an area extracting unit configured to extract a candidate area having a predetermined shape, including the candidate pixel; a determining unit configured to determine whether the candidate area is used as a correction area on the basis of a characteristic amount of the eye, calculated from the candidate area; and one or more processors programmed to control at least one of the calculating unit, the pixel extracting unit, the area extracting unit and the determining unit, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 6

An image processing apparatus comprising: a calculating unit configured to calculate an evaluation amount of red eye on the basis of a predetermined color component for every pixel satisfying a predetermined condition in an image; a pixel extracting unit configured to extract a candidate pixel in the image area having red eye including a pupil on the basis of the evaluation amount; an area extracting unit configured to extract a candidate area having a predetermined shape, including the candidate pixel; a determining unit configured to determine whether the candidate area is used as a correction area on the basis of a characteristic amount of the eye, calculated from the candidate area; and one or more processors programmed to control at least one of the calculating unit, the pixel extracting unit, the area extracting unit and the determining unit, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 7

The image processing apparatus according to claim 1 , wherein the evaluation amount is calculated by (R-G)/R from red and green components of the pixel in the image.

Claim 8

The image processing apparatus according to claim 3 , wherein the evaluation amount is calculated by (R-G)/R from red and green components of the pixel in the image.

Claim 9

The image processing apparatus according to claim 1 , further comprising: an area extracting unit configured to extract an area having a plurality of candidate pixels extracted by the extracting unit, determine whether the extracted area has a predetermined shape, and extract an area, having been determined to have the predetermined shape, as a red-eye candidate area.

Claim 10

The image processing apparatus according to claim 1 , wherein the extracting unit sets a predetermined window area near a target pixel in the image, determines a threshold value from the evaluation amount of a pixel in the window area, and binarizes the evaluation amount of the target pixel by the use of the threshold value to extract the candidate pixel.

Claim 11

The image processing apparatus according to claim 7 , wherein the extracting unit sets the window area corresponding to multiple pixels on a line of the target pixel.

Claim 12

The image processing apparatus according to claim 7 , wherein, after scanning the target pixel in a direction on a line to extract the candidate pixel, the extracting unit scans the target pixel in the opposite direction on the line to extract the candidate pixel and uses the pixel extracted in both the two scannings as the candidate pixel.

Claim 13

The image processing apparatus according to claim 6 , wherein the area, having the predetermined shape, is an area that has a shape approximated to a circle or an ellipse.

Claim 14

The image processing apparatus according to claim 6 , further comprising: a determining unit configured to determine whether the candidate area is used as a correction area on the basis of a characteristic amount of an eye, calculated from the candidate area, and a correcting unit configured to perform red-eye correction process on the correction area in a case where the determining unit determines to use the candidate area as the correction area.

Claim 15

The image processing apparatus according to claim 3 , further comprising an area excluding unit configured to exclude any candidate area that is smaller than the candidate area and that is adjacent to the candidate area.

Claim 16

The image processing apparatus according to claim 3 , further comprising an area combining unit configured to combine another candidate area adjacent to the candidate area with the candidate area.

Claim 17

The image processing apparatus according to claim 13 , wherein, if an area including the combination of the two candidate areas has a shape approximated to a square, compared with the two candidate areas, the area combining unit combines the two candidate areas into one.

Claim 18

The image processing apparatus according to claim 3 , further comprising a correcting unit configured to correct the poor color tone in the correction area.

Claim 19

The image processing apparatus according to claim 15 , wherein the correcting unit includes: a first calculator for calculating a first weight in accordance with a distance between a pixel in the correction area and the center of the correction area; a second calculator for calculating a second weight in accordance with a ratio of the evaluation amount of a target pixel to a maximum value in the evaluation amounts of the pixels in the correction area; a third calculator for calculating a third weight in accordance with a ratio of a luminance of the target pixel to a maximum value in the luminances of the pixels in the correction area; a determiner for determining correction amounts of luminance and color difference components by using the first to third weights; and a corrector for correcting the luminance and color difference components of the target pixel by using the correction amounts.

Claim 20

The image processing apparatus according to claim 16 , wherein the determiner determines the correction amount of the luminance component by using the first to third weights and determines the correction amount of the color difference component by using the first and second weights.

Claim 21

An image processing method comprising the steps of: calculating an evaluation amount of red eye on the basis of a predetermined color component for every pixel satisfying a predetermined condition in an image; extracting a candidate pixel in the image area having red eye including a pupil on the basis of the evaluation amount; extracting a candidate area having a predetermined shape, including the candidate pixel; and determining whether the candidate area is used as a correction area on the basis of a characteristic amount of the eye, calculated from the candidate area, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 22

An image processing method comprising the steps of: calculating an evaluation amount of red eye on the basis of a predetermined color component for every pixel satisfying a predetermined condition in an image; extracting a candidate pixel in the image area having red eye including a pupil on the basis of the evaluation amount; extracting a candidate area having a predetermined shape, including the candidate pixel; and determining whether the candidate area is used as a correction area on the basis of a characteristic amount of the eye, calculated from the candidate area, wherein the evaluation amount is calculated from only red and green components of the pixel in the image and without a blue component of the pixel in the image.

Claim 23

A non-transitory computer readable recording medium having a program for controlling an image processing apparatus so as to realize the image processing method according to claim 2 recorded therein.

Claim 24

The image processing apparatus according to claim 3 , wherein the evaluation amount is calculated by (R-G) or R/G from red and green components of the pixel in the image.

Claim 25

The image processing method according to claim 2 , wherein the evaluation amount is calculated by (R-G)/R of a pixel having a red component that is larger than a green component in the image.

Claim 26

The image processing apparatus according to claim 1 , wherein the evaluation amount is calculated by (R-G) or R/G from red and green components of the pixel in the image.