High performance image identification

1. A method of deriving a representation of an image by processing signals corresponding to the image, the method comprising:

deriving a Trace transform of the image;

processing said Trace transform to obtain a plurality of intermediate representations of parts of the image, and

deriving the representation of the image from the intermediate representations, wherein the intermediate representations are obtained by selecting parts of the Trace transform, and the step of selecting parts of the Trace transform includes defining bands of values in the Trace transform, each band defined by a predetermined range of a distance parameter of the Trace transform.

2. A method as claimed in claim 1 , wherein the intermediate representation is a one dimensional function of at least part of the image.

3. A method of deriving a representation of an image by processing signals corresponding to the image, the method comprising;

deriving a Trace transform of at least part of the image;

processing the Trace transform to Obtain an intermediate representation of at least part of the image: and

deriving the representation of the image from the intermediate representation, wherein the intermediate representation is obtained using a selected part of the image, by selecting as a selected part of the image, a subset of lines over the image, wherein the selected part of the image comprises double cones and each of the lines of the subset of lines passes through the apex of said double cones, and deriving said Trace transform using said selected subset of lines.

4. A method as claimed in claim 1 , wherein the step of processing the two dimensional function of the image includes multiplying the two dimensional function with a mask function defining said part of the two dimensional function.

5. A method as claimed in claim 1 , wherein the two dimensional function of the image comprises a distance parameter and an angle parameter, and said part of the two dimensional function is defined by at least one band between values u 0 , and u 1 of the distance parameter.

6. A method as claimed in claim 1 , comprising defining a pair of bands, the ranges of which are equidistant about a centre value of the distance parameter of the two dimensional function.

7. A method as claimed in claim 1 , the step of processing the two dimensional function comprises:

applying a functional to values of said selected part of the Trace transform to obtain an intermediate representation of a selected part of the image.

8. A method as claimed in claim 7 , wherein said intermediate representation is a one dimensional function of at least a part of the image.

9. A method as claimed in claim 8 , wherein the one dimensional function is defined by the equation:

g (θ)= G ( T ( d ,θ)β( d ,θ)),

where:

G is a diametrical functional that operates along the distance parameter of the selected part of the Trace transform

T is a functional of a Trace transform

d and θ are the distance and angle parameters of the traced lines in the

Trace transform, and

β is a mask function defining a selected part of the Trace transform.

10. A method as claimed in claim 6 , wherein the mask function defines a band of values of the Trace transform with the distance parameter d

(u 0 <d<U y ), and is defined as:

[0, otherwise

β

⁡

(

d

,

θ

)

=

{

1

,



d



∈

(

u

0

,

u

1

]

0

,

otherwise

,

⁢

⁢

0

≤

u

0

<

u

1

.

11. A method as claimed in claim 1 , wherein the Trace transform is performed over values for the angle parameter in the range 0 to 180 degrees.

12. A method as claimed in claim 1 , wherein the step of deriving the representation of the image from the intermediate representation comprises:

using a plurality of frequency components of a frequency representation of the intermediate representation, to derive the representation of the selected part of the image.

13. A method as claimed in claim 12 , further comprising:

defining a representation function using magnitudes of the frequency components, and

using the magnitude of the frequency components to derive the representation of the selected part of the image.

14. A method as claimed in claim 1 , wherein the step of deriving the representation of the image from the intermediate representation, comprises combining the derived representation of the selected part of the image with one or more other representations of the image.

15. A method as claimed in claim 1 , further comprising:

reducing the resolution of the two-dimensional function and/or the intermediate representation.

16. A method of deriving a representation of an image by processing signals corresponding to the image, the method comprising:

extracting from the image a substantially circular sub-image, the sub-image having a tapered circular boundary, and

deriving the representation of the image from the extracted circular sub-image, using the method as claimed in claim 1 .

17. A method of identifying an image comprising:

deriving a representation of the image using a method is claimed in claim 1 , and

associating the representation with the image.

18. A method of comparing images comprising comparing representations of each image derived using the method of claim 1 .

19. A method as claimed in claim 18 , wherein the comparison comprises determining a Hamming distance.

20. A method as claimed in claim 18 , comprising selecting images based on comparisons of representations.

21. The method of claim 1 , further comprising transmitting, receiving, or processing, the representation of the image.

22. An apparatus comprising:

a processor and a memory, the memory storing a computer program which when executed causes the processor to perform the steps of claim 1 .

23. A computer program stored on a non-transitory computer-readable medium for executing the method of claim 1 .