Automatic color defect correction

• US 6,885,766 B2
• Filed: 01/30/2002
• Issued: 04/26/2005
• Est. Priority Date: 01/31/2001
• Status: Expired due to Fees

• Current Assignee: Imaging Solutions AG (ME Group International Plc)
• Original Assignee: Imaging Solutions AG (ME Group International Plc)
• Inventors: Held, Andreas, Näf, Markus
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): Alavi, Amir
• Application Number:
  US10/058,320
• Publication Number:
  US 20020126893A1
• Time in Patent Office: 1,182 Days
• Field of Search: 382/115, 382/117, 382/118, 382/162, 382/167, 382/190, 382/254, 382/264, 382/266, 382274-276, 382/296, 348/370, 348/576, 358/515, 358/518, 396/61, 396/62, 396/104, 396/121, 396/123, 396/165, 430/357, 430/359, 430/362, 430/364
• US Class Current: 382/167
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611

Abstract

The present invention refers to a method for automatically correcting color defective areas in an image, which defective color areas were recorded with a color spectrum deviating from the actual color spectrum of said areas without color defects, wherein basic areas in the image are identified on the basis of features which are common for these recorded defective areas, said basic areas supporting an increased likelihood to include defective areas, and the processing is then reduced to the basic areas to identify borderlines and/or centres of the defective areas, and afterwards, it is identified whether the localized basic area or areas deemed to be defective are defective or not, and finally, if a localized basic area has been identified to be defective, a correction mask is created to correct the visual appearance of the defective area.

Claims

1. Method for automatically correcting color defective areas in an image, said defective color areas being recorded with a color spectrum deviating from the actual color spectrum of said areas without color defects, comprising the steps of:

a) identifying basic areas in the image on the basis of features which are common for recorded defective areas, said basic areas supporting an increased likelihood of including defective areas;

b) reducing a processing to the basic areas to identify at least one of borderlines and centers of the defective areas;

c) identifying whether the basic areas deemed to be defective are defective; and

d) creating a correction mask to correct a visual appearance of the defective area if a basic area has been identified to be defective.

2. Method according to claim 1, wherein a specialized portrait mode can be activated in the case of defective red eye detection.

3. Method according to claim 1, wherein if after one of the steps 1a), 1b), and 1c) the processing of an image has not resulted in the identification of an area to be processed further, the processing of an image is stopped and another image can be processed.

4. Method according to claim 1, wherein:

after a center of a basic area has been identified, an expected defect is emphasized in its intensity to detect whether the basic area is defective, and in the case of a detected color, the following equation is used;

I_red=R−

min(G,B),

where R refers to a red color channel, G refers to a green color channel, and B refers to a blue color channel.

5. Method of claim 4, wherein a detected color defect includes a defective red eye.

6. Method according to claims 1, wherein the basic areas are treated by an edge detection processing to achieve borderlines of the basic areas.

7. Method according to claim 1, wherein in a case that a red eye defect is to be corrected and a position and a size of an iris have been estimated, a maximum of the red eye defect is determined to be an actual position of the iris of an eye.

8. Method according to claim 7, wherein neighboring pixels are analyzed with respect to at least one of the actual position and center of the iris considering several curves of an HSV color space, which curves are achieved by analyzing a variety of real-world photographs with red eye defects to acquire fuzzy membership functions of three color channels to be taken into account, and determining intersections between at least three color channel positions of each of the neighboring pixels and said fuzzy membership functions, and deciding on the basis of the intersection values that a particular neighboring pixel is defective if its intersection values exceed a predetermined threshold, wherein a correction mask is created, if these steps are repeated for all relevant pixels.

9. Method according to claim 8, wherein a first arrangement around at least one of an equal position or center of the iris forms a first layer of first neighbouring pixels, and if the first layer of first neighboring pixels is at least partially identified as belonging to the red-eye defective pixels, other second neighbouring pixels with respect to the first neighbouring pixels are analyzed along a same line as the first neighbouring, pixels to be identified as red-eye defective pixels, and if further red-eye defective pixels have been identified, considering further other neighbouring pixels, wherein the correction mask is caused to grow.

10. Method according to claim 9, wherein the analysis of and extension to neighboring pixels is terminated if at least one of no further other neighboring pixels have been identified as red-eye defective and if the borderlines of the defective red eye have been at least one of reached and exceeded.

11. Method according to claim 9, wherein pixel data representing the correction mask area directed to at least one smoothing operation.

12. Method according to claim 9, wherein the correction mask is applied to the matching area of an uncorrected image to remove the color defect.

13. Method according to claim 12, wherein the removal of the color defect is practiced by the following equation:

I_{red new}=R−

m(R−

min(G,B)),

where m is an element of the correction mask corresponding to a particular pixel of the uncorrected image.

14. Method according to claim 12, wherein, if a particular pixel of the uncorrected image has a considerably large difference between the green channel and the blue channel, the larger channel is adjusted in accordance with the following equation:

I_{red new}=R−

m(R−

min(G,B)),

where m is an element of the correction mask corresponding to a particular pixel of the uncorrected image.

15. Method of claim 12, wherein the correction mask is a gray-scale correction mask.

16. Method of claim 12, wherein the color defect is a red-eye defect.

17. Method of claim 8, intersections are determined using the following equation:

r=hsv/(max(h,s,v)).

18. Method of claim 1, wherein an identification of basic areas in the image includes the use of at least one of skin detection to identify skin related areas, face detection on the basis of a face pictogram, and eye detection.

19. Method of claim 1, wherein defective areas include red eye defects.

20. An image processing device for processing image data, comprising:

an image data input section;

an image data processing section;

an image data recording section for recording processed image data, wherein the image data processing section implements a method for automatically correcting color defective areas in an image, said defective color areas being recorded with a color spectrum deviating from the actual color spectrum of said areas without color defects, including the steps of;

a) identifying basic areas in the image on the basis of features which are common for recorded defective areas, said basic areas supporting an increased likelihood of including defective areas;

b) reducing the processing to the basic areas to identify at least one of borderlines and centers of the defective areas;

c) identifying whether the basic areas deemed to be defective are defective; and

d) creating a correction mask to correct a visual appearance of the defective area if a basic area has been identified to be defective.