Image analysis – Applications – Personnel identification
Reexamination Certificate
1999-08-30
2003-02-25
Chang, Jon (Department: 2623)
Image analysis
Applications
Personnel identification
C382S154000, C382S199000
Reexamination Certificate
active
06526161
ABSTRACT:
FIELD OF THE INVENTION
The present invention pertains generally to the field of detecting human faces, and in particular, the invention relates to a system and method for locating facial features in a digital image using biometrics information.
BACKGROUND OF THE INVENTION
Systems and methods are known that analyze digital images and recognize human faces. Extraction of facial feature information has been used for various applications such as in automated/surveillance systems, monitoring systems, human interfaces to computers, television and video signal analysis.
Conventional facial detection systems use methods such as facial color tone detection, template matching or edge detection approaches. There are, however, numerous shortcomings to these types of conventional systems. In general, these conventional systems lack robustness, e.g., due to variations in human races, facial expression and lighting conditions.
More particularly, in systems using facial color tone detection, for example, a tint conversion is applied to an input digital image to determine skin-color regions. A mask pattern based upon the skin-color regions is used extract characteristic facial regions. However, depending on light sources, the hue of the respective facial regions may change, which causes difficulty in extracting accurate information. In addition, movement, while the digital image is generated, may cause shadows which also causes difficulty in detecting the skin-color regions accurately.
In systems using template matching, facial templates are first determined based upon average positions of facial features (i.e., eyes, nose and mouth) for a particular sex or race. A digital image is then matched to a template to identify sex or race. One shortcoming of this type of system is that expressions, e.g., a smile, may cause the wrong template to be used which leads to incorrect results.
Conventional systems using edge detection are also known. Edge detection approaches are useful in locating the position of eyes because the eyes typically have high edge density values. However, eye glasses and facial hair such as a mustache may cause these conventional systems to generate erroneous results. In addition, edge detection can not typically be used to determine the position of a nose.
There thus exists in the art a need for improved systems and methods for extraction of facial features from digital images that provide robust performance despite variations in the facial features due to movement or different facial expressions.
BRIEF SUMMARY OF THE INVENTION
It is an object of the present invention to address the limitations of the conventional extraction systems discussed above.
It is a further object of the invention to provide a facial feature extraction system that uses biometrics information to define regions of interest in an image and to accurately extract positions of facial features.
In one aspect of the present invention, an image processing device includes a disparity detector that compares locations of like pixel information in a pair of images and determines disparity information and a region detector which identifies a region of interest in one of the images in accordance with the disparity information. The region of interest includes a plurality of facial features. The device also includes a first position detector coupled to the region detector which identifies a position of one of the facial features in accordance with the disparity information.
In another aspect of the invention, an image processing apparatus includes a disparity detector that determines disparity information and an outline identifier that determines approximate boundaries of a face in an image based upon a comparison of a predetermined threshold value and the disparity information. The device also includes a nose position identifier that identifies a position of a nose in the face in accordance with the disparity information within a center region of the face.
One embodiment of the invention relates to a method of determining positions of facial features in an image that includes the steps of calculating a disparity between a pair of images and determining a face region of interest (ROI) in at least one of the images. The method also includes the step of identifying a nose position within the face region of interest in accordance with the calculated disparity.
Another embodiment of the invention relates to a computer-readable memory medium including code for processing a pair of images. The memory medium includes code to compare locations of like pixel information in a pair of images to determine disparity information and code to identify a region of interest in one of the images in accordance with the disparity information. The region of interest includes a plurality of facial features. The memory medium also includes code to identify a position of one of the facial features in accordance with the disparity information.
These and other embodiments and aspects of the present invention are exemplified in the following detailed disclosure.
REFERENCES:
patent: 4975969 (1990-12-01), Tal
patent: 5471542 (1995-11-01), Ragland
patent: 5805745 (1998-09-01), Graf
patent: 5835616 (1998-11-01), Lobo et al.
patent: 6055330 (2000-04-01), Eleftheriadis et al.
patent: 6188777 (2001-02-01), Darrell et al.
patent: 6301370 (2001-10-01), Steffens et al.
Kim et al. “Object Oriented Face Detection Using Range and Color Information.” Proc. Third IEEE Int. Conf. on Automatic Face and Gesture Recognition, Apr. 1998, pp. 76-81.*
van Schalkwyk et al. “Low Bitrate Video Coding with Depth Compensation.” Proc. IEE Vision, Image and Signal Processing, vol. 141, issue 3, Jun. 1994, pp. 149-153.*
Galicia et al. “Depth Based Recovery of Human Facial Features from Video Sequences.” Proc. Int. Conf. on Image Processing vol. 2, Oct. 1995, pp. 603-606.*
Lengagne et al. “From 2D Images to 3D Face Geometry.” Proc. Second Int. Conf. on Automatic Face and Gesture Recognition Oct. 1996, pp. 301-306.*
Xu et al. “Detecting Head Pose from Stereo Image Sequence for Active Face Recognition.” Proc. Third IEEE Int. Conf. on Automatic Face and Gesture Recognition, Apr. 1998, pp. 82-87.*
“Finding Face Features”, by Ian Craw et al, Computer Vision—ECCV '92, Second European Conference on Computer Vision, Sana Margherita Ligure, Italy, May 19-22, 1992 Proceedings.
“Two-Dimensional Signal and Image Processing”, by J.S. Lim, Signals, Systems, and the Fourier Transform, Englewood Cliffs, NJ 1990, pp. 42-43.
“Image Sequence Coding at Very Low Bitrates: A Review”, by Haibo Li et al, IEEE, vol. 3, No. 5, Sep. 1994, pp. 589-609.
“Feature Extraction from Faces Using Deformable Templates”, by Alan L. Yuille et al, International Journal of Computer Vision, Aug. 2, 1992, pp. 99-111.
“Facial Model Refinement Using Stereo Image Sequence”, by Chung J. Kuo et al, Signal and Media Laboratory Deprt. of Electrical Engineering, National Chung Chen University, Chiayi, Taiwan.
“Depth Discontinuities by Pixel-to-Pixel Stereo”, by Stan Birchfield et al, Proceedings of the 1998 IEEE International conference on Computer Vision, Bombay, India.
LandOfFree
System and method for biometrics-based facial feature... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for biometrics-based facial feature..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for biometrics-based facial feature... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3128051