Enhancement of image data based on plural image parameters
A technology is provided whereby correction may be carried out appropriately for both a person's face and other portions of an image, when performing color correction for image data of a photographic image in which a person appears. A process such as the following is carried out during color correction of image data of a photographic image. First, the image data of the photographic image is analyzed, and a first region which is part of the photographic image and in which a person's face is present is determined. Then, on the basis of the portion corresponding to the first region of the image data, a first parameter relating to color is calculated. On the basis of part of the image data corresponding to a second region which is part of the photographic image but different from the first region, a second parameter relating to color is calculated. The color tone of the data is then corrected on the basis of the first and second parameters.
1. A method for enhancing image data, comprising:
analyzing image data, and determining a first region which is part of an image of the image data; and
enhancing the image data based on values of first and second parameters, the value of the first parameter being determined based on pixel values of the image data which corresponds to the first region, the value of the second parameter being determined based on pixel values of the image data corresponding to a second region which is part of the image and which differs from the first region, wherein
the enhancing the image data includes
preparing a first target value representing an ideal value for the first parameter, and a second target value representing an ideal value for the second parameter,
calculating a weight for the weighted average based on a difference between the value of the first parameter and the value of the second parameter, and
enhancing the image data based on the weighted average of a difference between the first target value and the value of the first parameter, and a difference between the second target value and the value of the second parameter, the difference between the first target value and the value of the first parameter and the difference between the second target value and the value of the second parameter being obtained by a subtraction operation.
2. The method of claim 1 , wherein
the first region is a region in which a human face is present.
3. The method of claim 2 , wherein
calculating the second parameter includes
determining, as the second region, a region taken from a region except for the first region of the image and whose colors of neighboring pixels resemble each other by at least a prescribed degree.
4. The method of claim 2 , further comprising:
receiving a selection made by a user of one mode from among a plurality of processing modes including: a first processing mode for processing an image whose main target is a human object; a second processing mode for processing an image whose main target is a landscape; and a third processing mode for processing an image whose main target includes both a human object and a landscape; and
calculating a value of a third parameter based on the image data, in a case where the first or second processing mode has been selected from among the plurality of processing modes, the value of the third parameter being determined based on pixel values of the image data corresponding to a third region in the image, the third region being different from the first and second regions, wherein
the enhancing the image data further includes:
enhancing the image data based on the third parameter, in a case where the first or second processing mode has been selected from among the plurality of processing modes; and
enhancing the image data based on the first and second parameters, in a case where the third processing mode has been selected from among the plurality of processing modes.
5. The method of claim 1 , wherein
the enhancing the image data further includes:
calculating a weight for the weighted average based on a proportion of the first region to the entire image.
6. The method of claim 1 , wherein
the first parameter is average brightness of the first region, and
the second parameter is average brightness of the second region.
7. The method of claim 1 , wherein
the first parameter is an average brightness of the first region, and
the second parameter is an average brightness of the second region, and wherein
the first target value and the second target value are determined according to a scene of a picture image determined based on the image data.