US 8,509,561 B2Granted

Separating directional lighting variability in statistical face modelling based on texture space decomposition

AssigneesDigitalOptics Corporation Europe Limited, National University of Ireland

InventorsMircea Ionita, Peter Corcoran, Ioana Bacivarov

Life of this patent

Estimating the term…

Loading patent…

Abstract

A technique for determining a characteristic of a face or certain other object within a scene captured in a digital image including acquiring an image and applying a linear texture model that is constructed based on a training data set and that includes a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations. A fit of the model to the face or certain other object is obtained including adjusting one or more individual values of one or more of the model components of the linear texture model. Based on the obtained fit of the model to the face or certain other object in the scene, a characteristic of the face or certain other object is determined.

Claims68

Dependent claims

A method of determining a characteristic of a face or certain other object within a scene captured in a digital image, comprising:

(a) acquiring a digital image including a face or certain other object within a scene;
(b) applying a linear texture model that is constructed based on a training data set and that comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;
(c) determining an initial location of the face or certain other object in the scene;
(d) obtaining a fit of said model to said face or certain other object including adjusting one or more individual values of one or more of the model components of said linear texture model;
(e) based on the obtained fit of the model to said face or certain other object in the scene, determining at least one characteristic of the face or certain other object;
and
(f) electronically storing, transmitting, applying a face or other object recognition program to, editing, or displaying the corrected face image or certain other object including the determined characteristic, or combinations thereof.

4 more elements

A method of adjusting a characteristic of a face or certain other object within a scene captured in a digital image, comprising:

(a) acquiring a digital image including a face or certain other object within a scene;
(b) applying a linear texture model that is constructed based on a training data set and comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;
(c) determining an initial location of the face or certain other object in the scene;
(d) obtaining a fit of said model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said linear texture model;
and
(e) based on the obtained fit of the model to said face or certain other object in the scene, adjusting at least one characteristic of the face or certain other object including changing one or more values of one or more model components of the linear texture model to generate an adjusted object model;
(f) superimposing the adjusted object model onto said digital image;
and
(g) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof.

6 more elements

A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a method of determining a characteristic of a face or certain other object within a scene captured in a digital image, wherein the method comprises:

(a) acquiring a digital image including a face or certain other object within a scene;
(b) applying a linear texture model that is constructed based on a training data set and that comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;
(c) determining an initial location of the face or certain other object in the scene;
(d) obtaining a fit of said model to said face or certain other object including adjusting one or more individual values of one or more of the model components of said linear texture model;
(e) based on the obtained fit of the model to said face or certain other object in the scene, determining at least one characteristic of the face or certain other object;
and
(f) electronically storing, transmitting, applying a face or other object recognition program to, editing, or displaying the corrected face image or certain other object including the determined characteristic, or combinations thereof.

4 more elements

A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a method of adjusting a characteristic of a face or certain other object within a scene captured in a digital image, wherein the method comprises:

(a) acquiring a digital image including a face or certain other object within a scene;
(b) applying a linear texture model that is constructed based on a training data set and comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;
(c) determining an initial location of the face or certain other object in the scene;
(d) obtaining a fit of said model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said linear texture model;
and
(e) based on the obtained fit of the model to said face or certain other object in the scene, adjusting at least one characteristic of the face or certain other object including changing one or more values of one or more model components of the linear texture model to generate an adjusted object model;
(f) superimposing the adjusted object model onto said digital image;
and
(g) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 12/038,147Filed 27 Feb 2008 · us provisional application
Priority: 28 Feb 2007
Published: US 2008/0205712 A128 Aug 2008
Granted: 13 Aug 2013
Term ends: Not estimatedThe source records don’t support an estimate.

Classification10 codes

G06V 40/171
Feature extraction; Face representation: local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
G06T 5/90
Image enhancement or restoration: dynamic range modification of images or parts thereof
G06V 10/60
Extraction of image or video features: relating to illumination properties, e.g. using a reflectance or lighting model
G06V 10/7557
Deformable models or variational models, e.g. snakes or active contours: based on appearance, e.g. active appearance models [AAM]