Identification photo system and image processing method which automatically corrects image data of a person in an identification photo

• US 7,548,260 B2
• Filed: 12/21/2000
• Issued: 06/16/2009
• Est. Priority Date: 12/24/1999
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Yamaguchi, Yoshihiro
• Primary Examiner(s): Ye; Lin
• Assistant Examiner(s): HERNANDEZ, NELSON D
• Application Number:
  US09/741,048
• Publication Number:
  US 20010005222A1
• Time in Patent Office: 3,099 Days
• Field of Search: 382/118, 382/115, 382/190, 382/203, 382/266, 348/584, 348/580, 348/581, 348/655, 348/61, 348/585, 348/586, 348/223.1, 348/222.1, 348/207.2, 348/578, 348/207.1, 348/207.11, 358/518, 283/75, 283/70, 283/72, 283/73
• US Class Current: 348/239
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/628 Memory colours, e.g. skin or sky
• CPC Class Codes: H04N 9/641 Multi-purpose receivers, e.g. for auxiliary information H04N9/642 takes precedence
• CPC Class Codes: H04N 9/73 Colour balance circuits, e.g. white balance circuits or colour temperature control camera processing pipelines for colour balance H04N23/88

Abstract

An automatic correcting device of an identification photo system comprises a skin pigmentation area abstracting device that abstracts a skin pigmentation area from an image of a person, a skin pigmentation correction value calculating device that calculates skin pigmentation correction values according to colors of the skin pigmentation area abstracted by the skin pigmentation area abstracting device and a predetermined skin pigmentation correction target value, and a color correcting device that corrects colors of the skin pigmentation area according to the skin pigmentation correction values calculated by the skin pigmentation correction value calculating device. Thus, the skin pigmentation of the person in the photo can be corrected to the person'"'"'s true pigmentation.

Claims

1. An image processing method, comprising:

determining a background area of an image;

determining a person area of the image as an area of the image other than the background area of the image; and

sizing the image based on a size of the person area of the image such that the size of the person area is a predetermined person area size,

wherein the step of determining the background area of the image comprises;

separating the image into a plurality of areas by an area separating device; and

wherein the step of separating the image into the plurality of areas comprises;

comparing properties of adjoining pixels of the image; and

determining that two adjoining pixels belong in the same area if the compared properties of the two adjoining pixels are less than predetermined thresholds for each property compared, and

determining whether or not the each area of the plurality of areas belongs in the background area based on a comparison of the each area with a reference background area, wherein the reference background area includes at least one corner of the image, and

wherein the step of determining whether or not the each area of the plurality of areas belongs in the background area based on the comparison of the each area with the reference background area includes determining that the each area belongs in the background area if

a difference between an average luminance value of the pixels of the each area and an average luminance value of the reference background area is within a predetermined luminance difference threshold and a difference between an average chromaticity value of the pixels of the each area and an average chromaticity value of the reference background area is within a predetermined chromaticity difference threshold, or

a difference between an average red (R) value of the pixels of the each area and an average R value of the reference background area is within a predetermined R difference threshold, a difference between an average green (G) value of the pixels of the each area and an average G value of the reference background area is within a predetermined G difference threshold and a difference between an average blue (B) value of the pixels of the each area and an average B value of the reference background area is within a predetermined B difference threshold.

2. The image processing method as defined in claim 1, wherein the properties of the adjoining pixels compared include:

luminance and chromaticity values;

or

red (R), green (G) and blue (B) values.

3. The image processing method as defined in claim 1, further comprising abstracting a facial area based on the person area.

4. The image processing method as defined in claim 3, wherein the step of abstracting the facial area based on the person area comprises determining that an area of the person area is the facial area when a color of the of the area is determined to be a skin pigmentation color.

5. The image processing method as defined in claim 4, further comprising correcting the facial area to a target skin pigmentation color.

6. The image processing method as defined in claim 1, further comprising:

allowing a user to select the predetermined person area size from a plurality of predetermined person area sizes prior to sizing the image,

wherein in the step of sizing the image comprises sizing the image based on the selected predetermined person area size.

7. The image processing method as defined in claim 1, wherein the step of sizing the image based on the size of the person area such that the size of the person area is the predetermined size is performed after the image is generated through photography.