Image analysis – Applications – Personnel identification
Reexamination Certificate
2000-10-16
2004-04-06
Johns, Andrew W. (Department: 2621)
Image analysis
Applications
Personnel identification
C382S162000
Reexamination Certificate
active
06718051
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to a novel and non-obvious image processing method for detecting potential red-eye in an image. The invention is not directed to a method for correcting red-eye once detected, as numerous red-eye correction methods are well known in the art. The present invention provides a faster and more accurate red-eye detection method or potential red-eye detection method without operator intervention, and is adapted for use upstream relative to a conventional red-eye detection/correction system.
Red-eye is a common phenomenon apparent in photographic images (whether continuous tone or digital) taken using a flash or strobe, wherein a human subject's eyes appear “blood red” instead of their natural color. Red-eye is caused by a reflection of the flash light from the retina of the eye back into the objective lens of the camera.
Red-eye has become more prevalent and severe as cameras have been made smaller with integrated flashes. The small size coupled with the built-in nature of the flash requires placement of the flash in close proximity the objective lens. Thus, a greater portion of the reflected light from a subject's retinas enters the object lens and is recorded. Recognizing this problem, camera manufacturers have attempted to minimize or inhibit red-eye by equipping cameras with the ability to emit one or more pre-flashes of light immediately prior to completion of the actual photograph. These pre-flashes are intended to constrict the subject's pupils to minimize light incident on the retina and reflected therefrom. While these modern cameras do reduce the occurrence of red-eye, it continues to be a common and bothersome occurrence.
As noted above, image processing techniques are known and utilized to detect and correct red-eye. Prior methods are disclosed, for example, in the following U.S. Patents, the disclosures of which are hereby expressly incorporated by reference: U.S. Pat. Nos. 5,990,973; 5,130,789; 6,016,354; 5,153,632; 5,202,719; 5,404,192; 5,432,863; 5,666,215; 5,698,379; 5,747,228; 5,748,764; 5,804,356; and, 5,840,470.
In general, conventional image processing techniques for detecting or identifying red-eye have required human intervention or have been highly inefficient in terms of required image processing operations. In one prior method, an operator must visually scan all images and mark those images including red-eye for further processing. This is time-consuming and expensive. Attempts to eliminate or reduce operator involvement have resulted in automated processes that attempt to detect red-eye based upon color, size, and shape criteria. Given that the color red is very common, and given that red-eye is not present in a great many images (e.g., those not taken using a flash, those not including human subjects, etc.) vast amounts of image processing resources are used inefficiently for this purpose. Furthermore, false-positives are common owning to the fact that every red object satisfying the size/shape criteria will be identified as red-eye. Thus, red buttons, a piece of red candy, etc., all may be misidentified as red-eye using these prior automated red-eye detection techniques.
In light of the foregoing specifically noted deficiencies and others associated with conventional red-eye detection techniques, it has been deemed desirable to develop and novel and non-obvious red-eye detection technique that overcomes these deficiencies while providing better overall results.
SUMMARY OF THE INVENTION
In accordance with the present invention, a red-eye detection method includes receiving digital image data that defines an image. The digital image data are processed to identify all regions of the image that include a specular reflection. Image regions deemed to include a specular reflection are processed further, according to conventional techniques, to determine the presence or absence of red-eye. Specular reflections are identified according to luminace-chrominance characteristics, geometric (e.g., size/shape) characteristics, and/or luminance gradient characteristics.
One advantage of the present invention is the provision of an automated red-eye detection method that requires less image processing resources relative to conventional automated red-eye detection methods.
Another advantage of the present invention resides in the provision of a red-eye detection method that first identifies image regions that potentially include red-eye incorporating less resource intensive methods, wherein intensive image processing for red-eye detection is performed on these areas only.
A further advantage of the present invention is found in the provision of a red-eye detection method wherein color is not or not dominantly used as an indication of an image region potentially including red-eye.
Still another advantage of the present invention is found in the provision of a red-eye detection method that identifies potential red-eye regions of an image upstream from a conventional red-eye detection and/or correction system.
Still other benefits and advantages of the present invention will become apparent to those of ordinary skill in the art to which the invention pertains upon reading the following specification.
REFERENCES:
patent: 5130789 (1992-07-01), Dobbs et al.
patent: 5136312 (1992-08-01), Weaver et al.
patent: 5153632 (1992-10-01), Maida et al.
patent: 5202719 (1993-04-01), Taniguchi et al.
patent: 5287134 (1994-02-01), Cocca
patent: 5315342 (1994-05-01), Cocca
patent: 5404192 (1995-04-01), Konishi et al.
patent: 5432863 (1995-07-01), Benati et al.
patent: 5500671 (1996-03-01), Andersson et al.
patent: 5666215 (1997-09-01), Fredlund et al.
patent: 5698379 (1997-12-01), Bohan et al.
patent: 5717964 (1998-02-01), Dowe
patent: 5747228 (1998-05-01), Bohan et al.
patent: 5748764 (1998-05-01), Benati et al.
patent: 5804356 (1998-09-01), Cole et al.
patent: 5840470 (1998-11-01), Bohan et al.
patent: 5990973 (1999-11-01), Sakamoto
patent: 6016354 (2000-01-01), Lin et al.
patent: 6151403 (2000-11-01), Luo
patent: WO 97/21188 (1997-06-01), None
patent: WO 99/17254 (1999-04-01), None
Haro et al., Detecting and Tracking Eyes by Using Their Physiological Properties, Dynamics, and Appearance, IEEE (2000), pps. 163-168 (Document No. XP001035597).
Alavi Amir
Fay Sharp Fagan Minnich & McKee, LLP
Johns Andrew W.
Xerox Corporation
LandOfFree
Red-eye detection method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Red-eye detection method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Red-eye detection method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3239135