Patent US6128397A successfully refreshed from Google Patents.
US6128397A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for finding all frontal faces in arbitrarily complex visual scenes
Assignee: JustSystems Corp
•
Filing: 1997-11-21
•
Granted: 2000-10-03
•
Expires: 2017-11-21
Abstract
Abstract A method for detecting a face in an image includes the steps of applying the image to a first classification tool that determines a rotational angle for rotating the image that makes the image most resemble an upright face; rotating the image by the rotational angle determined by the first classification tool; and applying the rotated image to a second classification tool, which determines whether the rotated image represents a frontal face or not.
Inventors
- 👤 Shumeet Baluja
- 👤 Henry Rowley
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 16:17
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/161; G06V40/164; G06V10/00; G06V10/20; G06V10/24; G06V10/242
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
89 words
A method for detecting a face in an unknown input image, comprising the steps of: applying the unknown input image to a first classification tool that determines a rotational angle for rotating the unknown input image to a position that makes the unknown input image most resemble an upright face; rotating the unknown input image by the rotational angle determined by the first classification tool; and applying the rotated unknown input image to a second classification tool which determines whether the rotated unknown input image represents a frontal face.
Claim 2
Independent Claim
89 words
A method for detecting a face in an unknown input image, comprising the steps of: applying the unknown input image to a first classification tool that determines a rotational angle for rotating the unknown input image to a position that makes the unknown input image most resemble an upright face; rotating the unknown input image by the rotational angle determined by the first classification tool; and applying the rotated unknown input image to a second classification tool which determines whether the rotated unknown input image represents a frontal face.
Claim 3
Dependent Claim
33 words
A method for detecting a face in an unknown input image as in claim 1, wherein the first classification tool is a neural network, and the second classification tool is a neural network.
Claim 4
Dependent Claim
35 words
A method for detecting a face in an unknown input image as in claim 1, wherein the first classification tool is a neural network, and the second classification tool is a plurality of neural networks.
Claim 5
Dependent Claim
26 words
A method for detecting a face in an unknown input image as in claim 1, wherein the first and second classifications tools are non-linear regression tools.
Claim 6
Dependent Claim
24 words
A method for detecting a face in an unknown input image as in claim 1, wherein the unknown input image is a television-video image.
Claim 7
Dependent Claim
24 words
A method for detecting a face in an unknown input image as in claim 1, wherein the unknown input image is a photographic image.
Claim 8
Dependent Claim
26 words
A method for detecting a face in an unknown input image as in claim 1, wherein the unknown input image is an image from a newspaper.
Claim 9
Dependent Claim
26 words
A method for detecting a face in an unknown input image as in claim 1, wherein the unknown input image is a hand-drawing or a painting.
Claim 10
Dependent Claim
25 words
A method for detecting a face in an unknown input image as in claim 1, wherein the method can be run on any personal computer.
Claim 11
Independent Claim
124 words
A method for detecting one or more faces in an unknown input image displayed by a pixel array, comprising the steps of: selecting from the unknown input image a subimage of a predetermined array size of pixels centered around a first pixel of the pixel array; applying the subimage to a first classification tool which determines a rotational angle for rotating the subimage to a position that makes the subimage most resemble an upright face; rotating the subimage by the rotational angle determined by the first classification tool; applying the rotated subimage to a second classification tool which determines whether the rotated subimage represents a frontal face; and repeating the above steps for each pixel in the pixel array of the unknown input image.
Claim 12
Independent Claim
124 words
A method for detecting one or more faces in an unknown input image displayed by a pixel array, comprising the steps of: selecting from the unknown input image a subimage of a predetermined array size of pixels centered around a first pixel of the pixel array; applying the subimage to a first classification tool which determines a rotational angle for rotating the subimage to a position that makes the subimage most resemble an upright face; rotating the subimage by the rotational angle determined by the first classification tool; applying the rotated subimage to a second classification tool which determines whether the rotated subimage represents a frontal face; and repeating the above steps for each pixel in the pixel array of the unknown input image.
Claim 13
Dependent Claim
28 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the predetermined array size of the subimaqe is 20×20 pixels.
Claim 14
Dependent Claim
62 words
A method for detecting one or more faces in an unknown input image as in claim 10, further comprising the step of: reducing the unknown input image by a predetermined amount and repeating all of the steps recited in claim 10 in order to find faces in the unknown input image that are larger than the predetermined array size of the subimage.
Claim 15
Dependent Claim
29 words
A method for detecting one or more faces in an unknown input image as in claim 12, wherein the reducing step is performed by subsampling the unknown input image.
Claim 16
Dependent Claim
35 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the first classification tool is a neural network, and the second classification tool is a neural network.
Claim 17
Dependent Claim
37 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the first classification tool is a neural network, and the second classification tool is a plurality of neural networks.
Claim 18
Dependent Claim
28 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the first and second classification tools are non-linear regression tools.
Claim 19
Dependent Claim
26 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the unknown input image is a television-video image.
Claim 20
Dependent Claim
26 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the unknown input image is a photographic image.
Claim 21
Dependent Claim
28 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the unknown input image is an image from a newspaper.
Claim 22
Dependent Claim
28 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the unknown input image is a hand-drawing or a painting.
Claim 23
Dependent Claim
27 words
A method for detecting one or more faces in an unknown input image as in claim 10, wherein the method can be run on any personal computer.
References Cited (Backward Citations)
US4975960A
Cited
US5012522A
Cited
JPH04330578A
Cited
US5164992A
Cited
US5448376A
Cited
US5283644A
Cited
US5561718A
Cited
US5446803A
Cited
US5450504A
Cited
US5412738A
Cited
US5438357A
Cited
US5581625A
Cited
US5596362A
Cited
US5835632A
Cited
US5642431A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-10-03 | 2004-04-03 | 2004-10-03 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-10-03 | 2008-04-03 | 2008-10-03 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-10-03 | 2012-04-03 | 2012-10-03 | $7700.00 | Window Closed / Lapsed |