Method and apparatus for representing a group of images

1. A method of representing a group of images using a processor to process signals corresponding to the images, the method comprising:

obtaining, using a processor, a dominant colour representation for each image in the group of images, wherein each of the dominant colour representations has one or more components including at least one dominant colour value, and optionally for each dominant colour value, a variance indicating colour distribution variance of the image with respect to the dominant colour value, a weight indicating the influence of the dominant colour in the image, the number of dominant colours in the image, and spatial homogeneity of pixels corresponding to the dominant colors in the image;

determining the values of one or more dominant colours for the group of images;

combining the components including at least the dominant color values of the dominant colour representations to determine combined components including at least a combined dominant colour value for the group of images;

deriving, using a processor, a group dominant colour representation expressing the group of images in terms of said combined components including at least said combined dominant colour value for the group of images; and

storing the group dominant colour representation as a descriptor for the group of images,

wherein for two dominant colours m 1 and m 2 , and respective weights W 1 and W 2 , the merged dominant colour m has the value:

m=w 1 m 1 +w 2 m 2 ,

where w 1 , w 2 are the relative weights, W 1 /W 1 +W 2 and W 2 /W 1 +W 2 respectively.

2. A method as claimed in claim 1 where the group dominant colour representation has one or more components including at least one dominant colour value of the combined or selected image, and optionally for each dominant colour value, a variance indicating colour distribution variance with respect to the dominant colour value, a weight indicating the influence of the dominant colour in the combined or selected image, the number of dominant colours, and spatial homogeneity of pixels corresponding to the dominant colors in the combined or selected image.

3. A method as claimed in claim 1 involving temporally or spatially subsampling the group of images.

4. A method as claimed in claim 3 wherein images are omitted or included depending on their similarity to other images in the group.

5. An apparatus comprising:

an image database storing images or groups of images;

a descriptor database storing descriptors for the images or groups of images in the image database; and

a processor configured to perform the method according to claim 1 .

6. A computer-readable storage medium storing computer-executable process steps for implementing a method as claimed in claim 1 .

7. A computer system comprising:

an image database storing images or groups of images;

a descriptor database storing descriptors for the images or groups of images in the image database; and

a control unit programmed to perform the method as claimed in claim 1 .