US6707933B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Face direction estimation using a single gray-level image
Assignee: Agency for Science, Technology and Research
•
Filing: 2000-03-17
•
Granted: 2004-03-16
•
Expires: 2020-03-17
Abstract
Abstract A method, apparatus, and computer program product for estimating face direction using a single gray-level image (110, 150) of a face are described. Given the single image (110, 150), a face direction can be determined by computing a nose axis (140, 180) maximizing a correlation measure between left and right sides (120, 130; 160, 170) of the face. The correlation measure is computed by comparing one of the two sides (A) with another synthetic side (C) derived from the other side (B) using symmetry and perspective transforms. Optionally, this process can be accelerated using a contrast enhancement algorithm taking advantage of the circumstances that the nose is the part of a face reflecting the most light and that this reflected light is represented as a line-like region close to the real nose axis. The computation result is a word describing the spatial position of the face and combining height ("up", "normal", "down") and neck-rotation ("left", "frontal", "right").
Inventors
- 👤 Roberto Mariani
- 👤 Jiankang Wu
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 19:33
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/70; G06T7/73; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/161; G06T2207/00; G06T2207/30; G06T2207/30196; G06T2207/30201
Claims Analysis
Total Claims: 9
Claim 1
Independent Claim
140 words
A method for generating a quantitative face direction from a single digital image of a person's face, said method including the steps of: computing the rotation of a face in said image using a nose axis of said face; computing the tilt of said face in said image; determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 2
Independent Claim
140 words
A method for generating a quantitative face direction from a single digital image of a person's face, said method including the steps of: computing the rotation of a face in said image using a nose axis of said face; computing the tilt of said face in said image; determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 3
Dependent Claim
54 words
The method according to claim 1 , wherein said nose-axis determining step further includes the step of comparing one of said left and right sides with a synthetic side derived from the other of said left and right sides using symmetry and a perspective transformation of said other side to compute said correlation measure.
Claim 4
Independent Claim
145 words
An apparatus for generating a quantitative face direction from a single digital image of a person's face, said apparatus including: means for computing the rotation of a face in said image using a nose axis of said face; means for computing the tilt of said face in said image; means for determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and means for determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 5
Independent Claim
145 words
An apparatus for generating a quantitative face direction from a single digital image of a person's face, said apparatus including: means for computing the rotation of a face in said image using a nose axis of said face; means for computing the tilt of said face in said image; means for determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and means for determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 6
Dependent Claim
53 words
The apparatus according to claim 3 , wherein said nose-axis determining means further includes means for comparing one of said left and right sides with a synthetic side derived from the other of said left and right sides using symmetry and a perspective transformation of said other side to compute said correlation measure.
Claim 7
Dependent Claim
180 words
A computer program product having a computer usable medium having a computer readable program code means embodied therein for generating a quantitative face direction from a single digital image of a person's face, said computer program product including: computer readable program code means for computing the rotation of a face in said image using a nose axis of said face; computer readable program code means for computing the tilt of said face in said image; and computer readable program code means for determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and computer readable program code means for determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 8
Dependent Claim
180 words
A computer program product having a computer usable medium having a computer readable program code means embodied therein for generating a quantitative face direction from a single digital image of a person's face, said computer program product including: computer readable program code means for computing the rotation of a face in said image using a nose axis of said face; computer readable program code means for computing the tilt of said face in said image; and computer readable program code means for determining said quantitative face direction of said face in said image using the computed rotation and computed tilt of said face; and computer readable program code means for determining said nose axis by maximizing a correlation measure between a left side and a right side of said face from left and right sub-images of said image and applying a contrast enhancement algorithm to a nose region of said image, wherein said nose is the part of a face that reflects the most light, said reflected light being represented as a line-like region close to a real nose axis.
Claim 9
Dependent Claim
66 words
The computer program product according to claim 5 , wherein said computer readable program code means for determining said nose axis further includes computer readable program code means for comparing one of said left and right sides with a synthetic side derived from the other of said left and right sides using symmetry and a perspective transformation of said other side to compute said correlation measure.
References Cited (Backward Citations)
US5293427A
Cited
US5561718A
Cited
US5659625A
Cited
US5867588A
Cited
US5481622A
Cited
US5497430A
Cited
US5859921A
Cited
US5774591A
Cited
US5982912A
Cited
US6028960A
Cited
US6144755A
Cited
US6075557A
Cited
US6246779B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-03-16 | 2007-09-15 | 2008-03-16 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-03-16 | 2011-09-15 | 2012-03-16 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-03-16 | 2015-09-15 | 2016-03-16 | $7700.00 | Window Closed / Lapsed |