Object identification
AssigneeThe Victoria University of Manchester
InventorsTimothy F Cootes, Christopher J Taylor
Life of this patent
Estimating the term…
Abstract
A method of object identification comprising, for an image in which an object is to be identified, determining for each of a set of locations in the image the direction in which the gradient of intensity change to an adjacent location is greatest together with the magnitude of that gradient, modifying the gradient magnitude using a nonlinear function, the modified gradient and the associated direction for the set of location providing a vector representative of the image, and comparing the vector with a previously generated statistical model which provides identification of the object.
Claims23
A method of object identification comprising;
- for an image in which an object is to be identified, determining for each of a set of locations in the image the direction in which the gradient of intensity change to an adjacent location is greatest together with the magnitude of that gradient, modifying the gradient magnitude using a nonlinear function, the modified gradient and the associated direction for the set of locations providing a vector representative of tie image, and comparing the vector with a previously generated statistical model which provides identification of the object.
A method of object identification according to any preceding claim, wherein the nonlinear function is the modulus of the gradient magnitude divided by the sum of the gradient magnitude and the mean or median of the expected values of the gradient magnitude.
A method of object identification according to any preceding claim, wherein the nonlinear function acts to normalise the gradient magnitude.
A method of object identification according to any preceding claim, wherein the direction of the gradient is represented by modulo 2π.
A method of object identification according to any preceding claim, wherein the location and size of an object of interest is estimated prior to determining the gradient directions and magnitudes.
A method of object identification according to any preceding claim, wherein the method provides identification of the class of an object.
A method of object identification according to any preceding claim, wherein the method provides recognition of a particular object within a class of objects.
A method of object identification according to any preceding claim, wherein the class of objects is faces.
A method of object identification according to any preceding claim, wherein the previously generated appearance model is an Active Shape Model.
An appearance model comprising a set of data representative of images of objects of interest, the model being constructed by determining for each of a set of locations in the image the direction in which the gradient of intensity change to an adjacent location is greatest together with the magnitude of that gradient, modifying the gradient using a nonlinear function, and combining the resulting set of modified gradients and associated directions with sets of modified gradients and associated directions determined for other images, to form the set of data.
Dependencies are inferred from the claim text.