Method for the automatic detection of red-eye defects in photographic image data

• US 20030044177A1
• Filed: 07/09/2002
• Published: 03/06/2003
• Est. Priority Date: 09/03/2001
• Status: Abandoned Application

• Current Assignee: Agfaphoto GmbH (Agfaphoto Holding GmbH)
• Original Assignee: Agfaphoto GmbH (Agfaphoto Holding GmbH)
• Inventors: Schindler, Hans-Georg, Taresch, Gudrun, Oberhardt, Knut, Damm, Tobias, Jacob, Friedrich
• Application Number:
  US10/192,711
• Publication Number:
  US 20030044177A1
• Time in Patent Office: Days
• US Class Current: 396/158
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

In a method for the automatic detection of red-eye defects in photographic image data, image and/or recording data are analyzed independently of one another for several specified indications and/or prerequisites. Thereafter, a value is determined for the presence of the individual indications and/or prerequisites. Thereafter, the determined values are combined for an overall evaluation, and a decision about the presence of potential red-eye defects is made, based upon the overall evaluation. The potential red-eye defects are located, and a decision is made, based upon analysis criteria, as to whether there are, indeed, red-eye defects.

Claims

1. A method for the automatic detection of red-eye defects in photographic image data, said method comprising the steps of:

(a) analyzing image and/or recording data independently of one another for several specified indications and/or prerequisites;

(b) determining a value representative of the presence of each of the individual indications and/or prerequisites;

(c) combining the determined values to produce an overall evaluation;

(d) rendering a decision about the presence of potential red-eye defects based upon the overall evaluation;

(e) locating the potential red-eye defects; and

(f) rendering a decision based upon analysis criteria,

whether there are, in fact, red-eye defects.

2. Method as set forth in claim 1, wherein the values are determined as probabilities.

3. Method as set forth in claim 2, wherein the overall evaluation is carried out by computing an overall probability and the decision is rendered by comparison with a prescribed threshold.

4. Method as set forth in claim 1, wherein the determined values are weighted.

5. Method as set forth in claim 1, wherein the overall evaluation is carried out using a neural network.

6. Method as set forth in claim 5, wherein the decision in step (d) is rendered using a neural network.

7. Method as set forth in claim 1, wherein said indications and/or prerequisites are analyzed simultaneously.

8. Method as set forth in claim 1, further comprising the step of analyzing exclusion criteria that, if present, exclude the presence of red-eye defects.

9. Method as set forth in claim 8, wherein the process for automatic detection of red-eye defects is automatically terminated if one of the exclusion criteria is present.

10. Method as set forth in claim 1, wherein one of the prerequisites is the existence of a flash photograph.

11. Method as set forth in claim 10, wherein the existence of the flash photograph is determined based on recording data that are stored on the photographic film together with the digital image data when taking the photograph.

12. Method as set forth in claim 10, wherein the existence of the flash photograph is determined based on an image analysis.

13. Method as set forth in claim 1, wherein one of the indications are adjacently positioned skin tones.

14. Method as set forth in claim 1, wherein one of the indications is the recognition of a face.

15. Method as set forth in claim 1, wherein one of the prerequisites is locating a round, red spot.

16. Method as set forth in claim 1, wherein one of the prerequisites is locating small, round, red areas with a white dot of a light reflection disposed inside the red areas.

17. Method as set forth in claim 1, wherein one of the indications is the frequency of structures in the image that can be determined by the decline of the Fourier transformed signals.

18. Method as set forth in claim 1, further comprising the step of analyzing the red-eye defects if a positive decision is rendered about the existence of red-eye defects.