Enhanced image identification
A method for deriving a representation of an image is described. The method involves processing signals corresponding to the image. A three dimensional representation of the image is derived. The three dimensional representation of the image to used to derive the representation of the image. In one embodiment, each line of the image is defined by a first parameter (d) and a second parameter (θ), and a position on each line is defined by a third parameter (t), and the three dimensional representation is parameterized by the first, second and third parameters. A set of values is extracted from the three dimensional representation at a value of the first parameter, and a functional is applied along lines, or parts of lines, of the extracted set of values, the lines extending along values of the second or third parameter.
1. A method for deriving a representation of an image by processing signals corresponding to the image, the method comprising:
processing the image to obtain a three dimensional representation of the image by
tracing lines across the image, each line across the image being defined by a first, distance, parameter (d) and a second, angle, parameter (θ), wherein a position on each line is defined by a third, position, parameter (t); and
deriving a three dimensional representation of the image represented by said first, second, and third parameters (d, θ, t) and the corresponding pixel value; and
using the three dimensional representation of the image to derive the representation of the image, by
extracting values of the three dimensional representation for a predetermined value of the first, distance, parameter, and
applying a functional along one or more lines of the extracted values of the three dimensional representation, each line extending along values of the second, angle, parameter at a corresponding, variable, value of the third, position, parameter (t), to obtain a one-dimensional function in terms of the third, position, parameter (t).
2. A method for deriving a representation of an image by processing signals corresponding to the image, the method comprising:
processing the image to obtain a three dimensional representation of the image by
tracing lines across the image, each line across the image being defined by a first, distance, parameter (d) and a second, angle, parameter (θ), wherein a position on each line is defined by a third, position, parameter (t); and
deriving a three dimensional representation of the image represented by said first, second, and third parameters (d, θ, t) and the corresponding pixel value; and
using the three dimensional representation of the image to derive the representation of the image, by
extracting values of the three dimensional representation for a predetermined value of the first, distance, parameter (d), and
applying a functional along one or more segments of lines of the extracted values, the line segments defined by an interval between predefined positions of the third, position, parameter (t), each line extending along fixed values of the third, position, parameter at a corresponding, variable, value of the second, angle, parameter (θ), to obtain a one-dimensional function in terms of the second, angle, parameter (θ).
3. A method as claimed in claim 1 or 2 , comprising:
extracting values of the three dimensional representation for a predetermined positive value of the first parameter to derive a first set of extracted values, and
extracting values of the three dimensional representation for a negative value of the first, distance, parameter (d) equivalent to the predetermined positive value, to derive a second set of extracted values.
4. A method as claimed in claim 3 , further comprising:
applying a functional along lines of each of the first and second sets of extracted values to derive respective first and second functions, and
combining the first and second functions.
5. A method as claimed in claim 1 or 2 , further comprising:
using the one dimensional function to derive a binary representation of the image.
6. A method as claimed in claim 1 or 2 , comprising using the magnitudes of frequency components to derive a representation of the image.
7. A method as claimed in claim 6 , wherein the frequency components are determined using a Fourier transform or a Haar transform.
8. A method as claimed in claim 6 , wherein the step of using the magnitudes of frequency components, comprises the steps of:
calculating the magnitude of a plurality of frequency coefficients, and
determining a difference between the magnitude of each coefficient and its subsequent coefficient.
9. A method as claimed in claimed in claim 8 , further comprising deriving a binary function by:
applying a threshold to each determined difference to derive a series of binary values, wherein applying the threshold provides a binary value of 0 if a said difference is less than a threshold value, and a binary value of 1 if a said difference is greater than or equal to the threshold value.
10. A method as claimed in claim 6 , wherein the step of using the magnitudes of frequency components, comprises the steps of:
calculating the logarithm of the magnitude of a plurality of frequency coefficients, and
determining a difference between the logarithm of the magnitude of each coefficient and its subsequent coefficient.
11. A method as claimed in claim 1 or 2 , comprising deriving a representation having n digits or bits, further comprising selecting a subset of m digits orbits.
12. A method as claimed in claim 11 , wherein said combining comprises concatenating said two or more representations.
13. A method as claimed in claim 1 or 2 , comprising deriving a plurality of representations of the image by applying a plurality of different functionals along lines of the three dimensional representation, and combining two or more of said plurality of representations.
14. A method for identifying or comparing an image using a method as claimed in claim 1 or claim 2 .
15. A method of identifying an image comprising deriving a representation of the image using the method of claim 1 or claim 2 and associating the representation with the image.
16. A method of comparing images comprising comparing representations of each image derived using the method of claim 1 or claim 2 .
17. The method of claim 16 wherein the comparison comprises determining a Hamming distance using the equation:
H
(
B
1
,
B
2
)
=
1
N
∑
N
B
1
⊗
B
2
where is the exclusive OR (XOR) operator, and N is the length of identifiers B 1 and B 2 .
18. The method of claim 16 comprising selecting images based on the comparison of representations.
19. A method of transmitting or receiving a representation derived using the method of claim 1 or claim 2 .
20. Apparatus for deriving a representation of an image by processing signals corresponding to the image, the apparatus comprising:
a database having one or more images stored therein; and
a processor configured to execute executing the method of claim 1 or claim 2 .
21. Apparatus as claimed in claim 20 , further comprising:
a descriptor database, a display means, and an image selecting means.
22. A non-transitory computer readable medium having stored there on a computer executable program for executing the method of claim 1 or claim 2 .
23. A method as claimed in claim 1 or 2 , comprising:
extracting values of the three dimensional representation for the first parameter equal to zero.