Two stage detection for photographic eye artifacts

• US 8,180,115 B2
• Filed: 05/09/2011
• Issued: 05/15/2012
• Est. Priority Date: 11/18/2005
• Status: Expired due to Fees

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Nanu, Florin, Capata, Adrian, Steinberg, Eran, Corcoran, Peter, Bigioi, Petronel, Pososin, Alexei, Ciuc, Mihai
• Primary Examiner(s): Rahmjoo, Mike
• Application Number:
  US13/103,842
• Publication Number:
  US 20110211095A1
• Time in Patent Office: 372 Days
• Field of Search: 382/117, 382/118, 382/115, 382/128, 382/130, 382/275, 382/167, 382/273, 382/289, 348/241, 348/242, 348/207.1, 348/231.3
• US Class Current: 382/117
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A digital image acquisition device is for acquiring digital images including one or more preview images. A face detector analyzes the one or more preview images to ascertain information relating to candidate face regions therein. A speed-optimized filter produces a first set of candidate red-eye regions based on the candidate face region information provided by the face detector.

Claims

1. A digital image acquisition device, comprising:

an imaging optic and detector for acquiring digital images including one or more preview images and a main image;

a processor;

a face detector to analyze the one or more preview images to ascertain information relating to candidate face regions therein, the face detector including a search module for detecting candidate face regions;

a face tracking module for predicting and confirming candidate face regions;

an image acquisition chain for image processing to generate a sub-sample resolution version of the main image, including a reduced resolution version of an approximately same scene as the main image;

a first speed-optimized face defect filter to produce a first set of candidate face defect regions in the sub-sample resolution version of the main image based on the candidate face region information provided by the face detector;

a display to show a first speed-optimized face defect filtered acquired image thereon; and

a second analysis-optimized face defect filter configured to be activated after display of said first speed-optimized corrected acquired image on said display, said second filter being activated upon initiation of an image playback mode, said second analysis-optimized face defect filter being configured to produce, with enhanced accuracy of face defect detection and/or higher quality of image correction than the first filter, a second set of candidate face defect regions for viewing at a higher resolution than the first speed-optimized face defect filtered acquired image shown on said display.

2. The device of claim 1, further comprising an image encoder for encoding said acquired image.

3. The device of claim 1, further comprising an image store memory for storing therein an encoded image in association with said first set of candidate face defect regions for later image processing of said encoded image.

4. The device of claim 1, wherein the second analysis-optimized filter is configured to operate on regions of said array identified as corresponding to regions of said first speed-optimized set of candidate face defect regions.

5. The device of claim 1, further comprising a display for displaying an image processed by said first speed-optimized face defect filter.

6. The device of claim 1, further comprising an image compressor for compressing said acquired image.

7. The device of claim 1, further comprising a signal connection for transferring said image to a computing appliance for further image processing of said image.

8. The device of claim 1, wherein the one or more preview images comprises a sub-sampled version of an acquired image.

9. The device of claim 1, wherein the candidate face region information comprises:

(i) a list of one or more candidate face regions;

(ii) a set of data associated with one or more candidate face regions and statistical data derived from a history of the one or more candidate face regions;

or

(iii) a predicted location for one or more candidate face regions;

or

(iv) combinations thereof.

10. A method for filtering a face defect artifact from an acquired digital image, the method comprising:

using a processor;

detecting candidate face regions;

predicting and confirming candidate face regions;

acquiring one or more preview images;

analyzing the one or more preview images to ascertain information relating to candidate face regions therein;

acquiring a main image using a lens and image sensor;

generating and analyzing a sub-sample resolution version of the main image, including a reduced resolution version of an approximately same scene as the main image;

producing a first set of candidate face defect regions in the main image based on the candidate face region information in the one or more preview images provided by the face detector and on the analysis of the sub-sample resolution version of the main image;

displaying a first speed-optimized face defect filtered acquired image thereon; and

activating a second analysis-optimized filter after displaying said first speed-optimized corrected acquired image, said activating being performed upon initiation of an image playback mode, said second analysis-optimized face defect filter being configured for enhanced accuracy of face defect detection and/or higher quality of image correction than the first speed-optimized face defect filtered acquired image, and thereby producing a second set of candidate face defect regions for viewing at a higher resolution than the displaying of said first speed-optimized face defect filtered acquired image.

11. The method of claim 10, further comprising encoding said main image.

12. The method of claim 10, further comprising storing an encoded main image in association with said first set of candidate face defect regions for later image processing of said encoded main image.

13. The method of claim 12, further comprising image processing a full resolution version of the main image with an analysis-optimized face defect filter based only in part on information obtained in the previous analyzing.

14. The method of claim 13, further comprising correcting detected face defect artifacts within the main image, and storing a corrected main image.

15. The method of claim 10, wherein the producing said second set of candidate face defect regions comprises operating the second analysis-optimized filter on regions identified as corresponding to the first set of candidate face defect regions.

16. The method of claim 10, further comprising transferring the main image to a PC or other microprocessor-based device, or both, for further image processing along with information obtained in the previous analyzing.

17. The method of claim 10, wherein the one or more preview images comprises a sub-sampled version of an acquired image.

18. The method of claim 10, wherein the candidate face region information comprises:

(i) a list of one or more candidate face regions;

(ii) a set of data associated with one or more candidate face regions and statistical data derived from a history of the one or more candidate face regions;

or

(iii) a predicted location for one or more candidate face regions;

or

(iv) combinations thereof.

19. One or more storage devices having program instruction embedded therein for programming a processor to perform the method of any of claims 10-18.