Computer-implemented method for obtaining a combined image

1 . A computer-implemented method for obtaining a combined image from two images, the computer-implemented method comprising:

obtaining a first image and a second image of a biometric feature of a user, the biometric feature comprising a plurality of characteristics;

identifying, in the first image and in the second image, the plurality of characteristics;

storing the first and second image and the identified plurality of the characteristics;

identifying, for at least some of the identified plurality of the characteristics in the first image, a corresponding identified plurality of the characteristics in the second image;

deriving a transformation for transforming the at least some of the identified plurality of the characteristics in the second image into the corresponding identified plurality of the characteristics in the first image, wherein deriving the transformation comprises using a neural network to determine at least one value characterizing the transformation;

modifying at least a portion of the second image using the transformation; and

obtaining the combined image comprising at least one portion of the first image and the at least one modified portion of the second image.

2 . The computer-implemented method of claim 1 , wherein obtaining the first and the second image comprises binarizing a first original image and a second original image.

3 . The computer-implemented method of claim 1 , wherein deriving the transformation comprises:

obtaining for at least two disjointed pairs of an identified characteristic in the first image and the corresponding identified characteristic in the second image, a sub-transformation; and

obtaining, from at least two sub-transformations, the transformation.

4 . The computer-implemented method of claim 3 , wherein obtaining, from the at least two sub-transformations, the transformation, comprises:

calculating a global transformation from the at least two sub-transformations;

determining, for at least one sub-transformation, a deviation from the global transformation; and

determining, depending on the deviation, whether to discard or maintain the at least one sub-transformation.

5 . The computer-implemented method of claim 4 , further comprising:

recalculating the global transformation using only maintained sub-transformations; and

using the recalculated global transformation as the transformation.

6 . The computer-implemented method of claim 1 , wherein the transformation is indicative of at least one of an amount of scaling, moving, or rotating to transform the portion of the second image.

7 . The computer-implemented method of claim 1 , wherein obtaining the combined image comprises:

modifying each portion of the second image using the transformation to generate a modified second image; and

using, for at least one portion existing in the first image and the modified second image, the at least one portion existing in the first image.

8 . The computer-implemented method of claim 1 , wherein deriving the transformation further comprises:

obtaining, from the first and the second image, an orientation map; and

using the orientation map for deriving the transformation.

9 . The method of claim 8 , wherein obtaining the orientation map comprises:

identifying, for at least one characteristic in the first image and a corresponding characteristic in the second image, a pixel in the at least one characteristic in the first image and a corresponding pixel in the corresponding characteristic in the second image for which a first orientation similarity is higher than a second orientation similarity for at least one other pixel in the at least one characteristic in the first image and a corresponding other pixel in the corresponding characteristic in the second image; and

providing orientation information on the pixel in the orientation map.

10 . The computer-implemented method of claim 9 , wherein the first orientation similarity of the pixel and the corresponding pixel is a highest orientation similarity of all pixels in the at least one characteristic and the corresponding characteristic.

11 . The computer-implemented method of claim 1 , wherein the biometric feature comprise at least one of a fingerprint or an iris, and wherein the plurality of characteristics comprise at least one of minutia of the fingerprint or pigments in the iris.

12 . The computer-implemented method of claim 1 , wherein obtaining the first image and the second image comprises using an optical sensor to obtain the first image and the second image.

13 . The computer-implemented method of claim 1 , further comprising using the combined image in an identification process identifying the user.

14 . A device comprising at least one processor and a memory comprising computer-executable instructions that, when executed by the at least one processor, cause the device to perform operations comprising:

obtaining a first image and a second image of a biometric feature of a user, the biometric feature comprising a plurality of characteristics;

identifying, in the first image and in the second image, the plurality of characteristics;

storing the first and second image and the identified plurality of the characteristics;

identifying, for at least some of the identified plurality of the characteristics in the first image, a corresponding identified plurality of the characteristics in the second image;

deriving a transformation for transforming the at least some of the identified plurality of the characteristics in the second image into the corresponding identified plurality of the characteristics in the first image, wherein deriving the transformation comprises using a neural network to determine at least one value characterizing the transformation;

modifying at least a portion of the second image using the transformation; and

obtaining a combined image comprising at least one portion of the first image and the at least one modified portion of the second image.

15 . The device of claim 14 , wherein deriving the transformation comprises:

obtaining for at least two disjointed pairs of an identified characteristic in the first image and the corresponding identified characteristic in the second image, a sub-transformation; and

obtaining, from at least two sub-transformations, the transformation.

16 . The device of claim 15 , wherein obtaining, from the at least two sub-transformations, the transformation, comprises:

calculating a global transformation from the at least two sub-transformations;

determining, for at least one sub-transformation, a deviation from the global transformation; and

determining, depending on the deviation, whether to discard or maintain the at least one sub-transformation.

17 . The device of claim 14 , wherein obtaining the combined image comprises:

modifying each portion of the second image using the transformation to generate a modified second image; and

using, for at least one portion existing in the first image and the modified second image, the at least one portion existing in the first image.

18 . The device of claim 14 , the operations further comprising:

obtaining, from the first and the second image, an orientation map by:

identifying, for at least one characteristic in the first image and a corresponding characteristic in the second image, a pixel in the at least one characteristic in the first image and a corresponding pixel in the corresponding characteristic in the second image for which a first orientation similarity is higher than a second orientation similarity for at least one other pixel in the at least one characteristic in the first image and a corresponding other pixel in the corresponding characteristic in the second image; and

providing orientation information on the pixel in the orientation map; and

using the orientation map for deriving the transformation.

19 . The device of claim 16 , the operations further comprising:

recalculating the global transformation using only maintained sub-transformations; and

using the recalculated global transformation as the transformation.

20 . The device of claim 18 , wherein the first orientation similarity of the pixel and the corresponding pixel is a highest orientation similarity of all pixels in the at least one characteristic and the corresponding characteristic.