Detecting redeye defects in digital images

• US 8,290,267 B2
• Filed: 08/04/2011
• Issued: 10/16/2012
• Est. Priority Date: 11/08/2007
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Ciuc, Mihai
• Primary Examiner(s): AHMED, SAMIR ANWAR
• Application Number:
  US13/198,624
• Publication Number:
  US 20120063677A1
• Time in Patent Office: 439 Days
• Field of Search: 382/173, 382/171, 382/167, 382/164, 358/1.9, 358/518, 358/523
• US Class Current: 382/173
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A method for detecting a redeye defect in a digital image containing an eye comprises converting the digital image into an intensity image, and segmenting the intensity image into segments each having a local intensity maximum. Separately, the original digital image is thresholded to identify regions of relatively high intensity and a size falling within a predetermined range. Of these, a region is selected having substantially the highest average intensity, and those segments from the segmentation of the intensity image whose maxima are located in the selected region are identified.

Claims

1. A method for detecting a redeye defect in a digital image containing an eye, the method comprising the following steps:

(a) converting the digital image into an intensity image, including;

(i) subjecting the intensity image to local averaging, and

(ii) subjecting the intensity image to mean shift segmentation, and

(b) segmenting at least a portion of the intensity image into segments each having a local intensity maximum,

(c) thresholding a corresponding portion of the digital image to identify regions exhibiting an intensity measure that is above a threshold value,

(d) selecting a region from at least two regions of step (c) having the most extreme average intensity, and

(e) identifying segments from step (b) intersecting the region selected at step (d) according to a pre-determined criterion,

wherein the average intensities of the two regions from step (c) having the highest and next highest average intensities differ by more than a predetermined amount, and the region selected at step (d) is the region having the highest average intensity.

2. The method of claim 1, further comprising identifying regions from step (c) having a size falling within a predetermined range, and wherein said region of the most extreme average intensity is selected from said regions.

3. The method of claim 1, wherein step (e) comprises identifying those segments from step (b) whose maxima are located in the region selected at step (d).

4. The method of claim 1, wherein the subjecting the intensity image to local averaging is performed prior to the subjecting of the intensity image to mean shift segmentation.

5. The method of claim 1, further including the steps of:

(f) computing the intensity histogram of the portion of the intensity image corresponding to the segments from step (e),

(g) smoothing said histogram,

(h) determining a threshold from the smoothed histogram, and

(i) thresholding the intensity histogram with the threshold from step (h).

6. The method of claim 1 wherein steps (a) and (b) are applied to one or more portions of the image suspected to contain an eye.

20. A digital image acquisition and processing apparatus including a lens, an image sensor, a processor, and a memory having code embedded therein for programming the processor that performs the method as claimed in any of claims 1-6 and 13-15.

21. One or more non-transitory computer readable media having code embedded therein for programming a processor that performs the method as claimed in any of claims 1-6 and 13-15.

7. A method for detecting a redeye defect in a digital image containing an eye, the method comprising the following steps:

(a) converting the digital image into an intensity image, including;

(i) subjecting the intensity image to local averaging, and

(ii) subjecting the intensity image to mean shift segmentation, and

(b) segmenting at least a portion of the intensity image into segments each having a local intensity maximum,

(c) thresholding a corresponding portion of the digital image to identify regions exhibiting an intensity measure that is above a threshold value,

(d) selecting a region from at least two regions of step (c) having the most extreme average intensity, and

(e) identifying segments from step (b) intersecting the region selected at step (d) according to a pre-determined criterion,

wherein step (c) uses a threshold obtained by identifying the highest intensity pixel inside the intensity image, computing the average intensity of the pixels inside a smaller rectangle centered on the highest intensity pixel, and assigning the threshold to the sum of the average intensity and a fixed quantity.

8. The method of claim 7, wherein the average intensities of the two regions from step (c) having the highest and next highest average intensities differ by more than a predetermined amount, and the region selected at step (d) is the region having the highest average intensity.

9. The method of claim 7, further comprising identifying regions from step (c) having a size falling within a predetermined range, and wherein said region of the most extreme average intensity is selected from said regions.

10. The method of claim 7, wherein step (e) comprises identifying those segments from step (b) whose maxima are located in the region selected at step (d).

11. The method of claim 7, wherein the subjecting the intensity image to local averaging is performed prior to the subjecting of the intensity image to mean shift segmentation.

12. The method of claim 7, further including the steps of:

(f) computing the intensity histogram of the portion of the intensity image corresponding to the segments from step (e),

(g) smoothing said histogram,

(h) determining a threshold from the smoothed histogram, and

(i) thresholding the intensity histogram with the threshold from step (h).

13. The method of claim 7 wherein steps (a) and (b) are applied to one or more portions of the image suspected to contain an eye.

14. A method for detecting a redeye defect in a digital image containing an eye, the method comprising the following steps:

(a) converting the digital image into an intensity image, including;

(i) subjecting the intensity image to local averaging, and

(ii) subjecting the intensity image to mean shift segmentation, and

(b) segmenting at least a portion of the intensity image into segments each having a local intensity maximum,

(c) thresholding a corresponding portion of the digital image to identify regions exhibiting an intensity measure that is above a threshold value,

(d) selecting a region from at least two regions of step (c) having the most extreme average intensity, and

(e) identifying segments from step (b) intersecting the region selected at step (d) according to a pre-determined criterion,

wherein the average intensities of the two regions from step (c) having the highest and next highest average intensities differ by less than a predetermined amount, and the region selected at step (d) is the region having the highest average saturation.

15. The method of claim 14, further comprising identifying regions from step (c) having a size falling within a predetermined range, and wherein said region of the most extreme average intensity is selected from said regions.

16. The method of claim 14, wherein step (e) comprises identifying those segments from step (b) whose maxima are located in the region selected at step (d).

17. The method of claim 14, wherein the subjecting the intensity image to local averaging is performed prior to the subjecting of the intensity image to mean shift segmentation.

18. The method of claim 14, further including the steps of:

(f) computing the intensity histogram of the portion of the intensity image corresponding to the segments from step (e),

(g) smoothing said histogram,

(h) determining a threshold from the smoothed histogram, and

(i) thresholding the intensity histogram with the threshold from step (h).

19. The method of claim 14 wherein steps (a) and (b) are applied to one or more portions of the image suspected to contain an eye.