US5561718A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Classifying faces
Assignee: US Philips Corp
•
Filing: 1994-10-24
•
Granted: 1996-10-01
•
Expires: 2014-10-24
Abstract
Abstract A face classification system which receives video data representative of a scene and extracts therefrom data representative of a face which is present in the scene. The facial video data is applied to a homomorphic filter to eliminate the effects of lighting changes in the scene. The positions of the eyes and mouth are located to form two sub-divisions, one in relation to a first line joining the eyes and the other in relation to a second line perpendicular to the first line and passing through the nose. A feature vector which is representative of the face and is rotation, scaling, translation and grey level intensity invariant is then produced by applying a recursive second order sub-division of moments to the filtered data. Such sub-division of moments is constrained to act first on the sub-divisions formed by the aforesaid lines, thereby reducing the effect of noise. The feature vector may be applied to a classifier which employs multi-layer perception to compare it with stored feature vectors of faces in one or more previous scenes to determine if the faces match. The system may be used, for example, for allowing access to secure areas or to secure computer work stations.
Inventors
- 👤 Timothy I. P. Trew
- 👤 Richard D. Gallery
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 16:40
CPC Classifications
A; A61; A61B; A61B5/00; A61B5/72; A61B5/7235; A61B5/7264; A61B5/117; A61B5/1171; A61B5/1176; G; G06; G06V; G06V40/00; G06V40/10; G06V40/16; G07; G07C; G07C9/00; G07C9/30; G07C9/32; G07C9/37; A61B5/7267; G16; G16H; G16H50/00; G16H50/20
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
162 words
A face classification system comprising: input means for receiving video data representing a video image of a scene in which a face is present; means for locating and extracting the video data representing the face in said scene; transform means for processing the facial data to derive a feature vector representative of the face and which is rotation, scaling, translation and grey level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; storage means for storing the feature vector; and comparing means for comparing the feature vector of the face in a present video image with a stored feature vector of a face in a previous video image to determine if the face in the present and previous video images is the same.
Claim 2
Dependent Claim
162 words
A face classification system comprising: input means for receiving video data representing a video image of a scene in which a face is present; means for locating and extracting the video data representing the face in said scene; transform means for processing the facial data to derive a feature vector representative of the face and which is rotation, scaling, translation and grey level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; storage means for storing the feature vector; and comparing means for comparing the feature vector of the face in a present video image with a stored feature vector of a face in a previous video image to determine if the face in the present and previous video images is the same.
Claim 3
Dependent Claim
17 words
The face classification system as claimed in claim 1, wherein said transform means comprises a homomorphic filter.
Claim 4
Dependent Claim
77 words
The face classification system claimed in claim 1, wherein said transform means includes means for locating the eyes and nose of the face and means for sub-dividing the face by a first line joining the eyes and a second line perpendicular thereto and extending through the nose; and said recursive second order sub-division of moments includes a first sub-division of moments relative to said first line and a second sub-division of moments relative to said second line.
Claim 5
Dependent Claim
195 words
A security system comprising: a video camera for producing video data representing a picture frame of a scene in which a face is present; means for locating in the video data and extracting therefrom data representing the face in the picture frame; transform means for processing the facial data to derive a feature vector representative of the face and which is rotation, scaling, translation and gray level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; means for storing a corresponding feature vector derived by said transform means which is representative of a face in a previous picture frame; means for comparing the feature vector of the face in a present picture frame with the stored feature vector of a face in a previous picture frame, to determine whether the face in both picture frames is the same; and means for initiating a security measure if the face is not the same in both picture frames.
Claim 6
Dependent Claim
195 words
A security system comprising: a video camera for producing video data representing a picture frame of a scene in which a face is present; means for locating in the video data and extracting therefrom data representing the face in the picture frame; transform means for processing the facial data to derive a feature vector representative of the face and which is rotation, scaling, translation and gray level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; means for storing a corresponding feature vector derived by said transform means which is representative of a face in a previous picture frame; means for comparing the feature vector of the face in a present picture frame with the stored feature vector of a face in a previous picture frame, to determine whether the face in both picture frames is the same; and means for initiating a security measure if the face is not the same in both picture frames.
Claim 7
Dependent Claim
202 words
A computer terminal security system for periodically validating continued access to said terminal by a user; comprising: a video camera for producing video data representing periodic picture frames of a scene which includes the face of a user of the terminal; means for locating in the video data of a present picture frame and extracting therefrom the data representing the user's face; transform means for processing the facial data of the present picture frame to derive a feature vector which is representative of the face in such picture frame and is rotation, scaling, translation and grey level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; means for storing the feature vectors relating to user faces in the periodic picture frames; and means for comparing the feature vector of the user's face in the present picture frame with the feature vector of the user's face in a previous picture frame to determine if the user's face is the same in both pictures frames.
Claim 8
Dependent Claim
202 words
A computer terminal security system for periodically validating continued access to said terminal by a user; comprising: a video camera for producing video data representing periodic picture frames of a scene which includes the face of a user of the terminal; means for locating in the video data of a present picture frame and extracting therefrom the data representing the user's face; transform means for processing the facial data of the present picture frame to derive a feature vector which is representative of the face in such picture frame and is rotation, scaling, translation and grey level intensity invariant; said transform means comprising means for fitting an outline to the face, means for locating the mid-point between the eyes, and means for producing a feature vector of the face by performing a Fourier-Mellin transformation on the facial data referenced to the mid-point between the eyes; means for storing the feature vectors relating to user faces in the periodic picture frames; and means for comparing the feature vector of the user's face in the present picture frame with the feature vector of the user's face in a previous picture frame to determine if the user's face is the same in both pictures frames.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-10-01 | 2000-04-01 | 2000-10-01 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-10-01 | 2004-04-01 | 2004-10-01 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-10-01 | 2008-04-01 | 2008-10-01 | $7700.00 | Window Closed / Lapsed |