Method and apparatus for representing and searching for an object in an image

摘要

A method of representing an object appearing in an image, comprises deriving a plurality of view descriptors of the object, each view descriptor corresponding to a different view of the object, the method comprising indicating for each view descriptor whether or not the respective view corresponds to a view of the object appearing in the image, wherein at least one view descriptor comprises a representation of the colour of the object in the respective view.