Method and apparatus for representing and searching for an object in an image
A method of representing an object appearing in an image, the method comprising deriving a plurality of view descriptors of the object, each view descriptor corresponding to a different view of the object, and associating the two or more view descriptors, the method comprising indicating for each view descriptor when the respective view corresponds to a view of the object appearing in the image.
1. A method of representing an object appearing in an image, the method comprising:
deriving a plurality of view descriptors of the object, each view descriptor including a representation of the shape of the object in a respective view, which is a view of the object from a respective angle of view, the plurality of view descriptors including at least one descriptor of the view of the object in the image and at least one descriptor of a view of the object from an angle of view different from the angle of view of the object in the image;
associating the plurality of view descriptors to form an object descriptor; and
indicating in the object descriptor for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the image.
2. A method as claimed in claim 1 comprising associating a flag with each view descriptor to indicate whether or not the respective view corresponds to a view of the object appearing in the image.
3. A method as claimed in claim 1 wherein the shape view descriptors are derived using a curvature scale space representation.
4. A method as claimed in claim 1 which is for indexing the image or collection of images for searching purposes.
5. An image search and retrieval system adapted for implementing a method as claimed in claim 1 .
6. A method of representing an object appearing in a group of images, the method comprising:
deriving a plurality of view descriptors of the object, each view descriptor corresponding to a different view of the object, and comprising a representation of the shape of the object in the respective view;
associating the plurality of view descriptors to form an object descriptor; and
indicating in the object descriptor for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the group of images.
7. A method as claimed in claim 6 comprising associating a flag with each view descriptor to indicate whether or not the respective view appears in at least one image of the group of images.
8. A method as claimed in claim 6 comprising indicating, for each image in the group of images, for each view descriptor whether or not the respective view corresponds to a view of the object appearing in said image.
9. A method as claimed in any one of claims 6 to 8 wherein the group of images is a sequence of images.
10. A method as claimed in claim 9 wherein the sequence of images is from a video or film.
11. A method as claimed in claim 6 wherein the plurality of view descriptors includes at least one descriptor of the view of the object in the group of images and at least one descriptor of a view of the object different from the view or views of the object in the group of images.
12. A method as claimed in claim 1 or claim 6 wherein the object descriptor is a searchable object descriptor.
13. A computer readable medium encoded with a computer program for performing the steps of:
deriving a plurality of view descriptors of an object appearing in an image, each view descriptor including a representation of the shape of the object in a respective view, which is a view of the object from a respective angle of view, the plurality of view descriptors including at least one descriptor of the view of the object in the image and at least one descriptor of a view of the object from an angle of view different from the angle of view of the object in the image;
associating the plurality of view descriptors to form an object descriptor; and
indicating in the object descriptor for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the image.
14. A system for representing an object appearing in an image, the system comprising:
at least one processor configured to
derive a plurality of view descriptors of the object, each view descriptor corresponding to a different view of the object, and comprising a representation of the shape of the object in the respective view;
associate the plurality of view descriptors to form an object descriptor; and
indicate in the object descriptor for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the group of images.
15. A computer-readable storage medium encoded with a computer program for performing the steps of:
deriving a plurality of view descriptors of an object appearing in a group of images, each view descriptor corresponding to a different view of the object, and comprising a representation of the shape of the object in the respective view;
associating the plurality of view descriptors to form an object descriptor; and
indicating in the object descriptor for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the group of images.