Methods, devices and computer program products for creating textured 3D images

1. A method for processing Two-Dimensional, 2D, images to create Three-Dimensional, 3D, images, the method comprising:

receiving, by a processor, a plurality of 2D images of an object;

identifying, by the processor, respective 2D positions of one or more features in each of the plurality of 2D images;

generating, by the processor, a 3D representation of the object, based on the respective 2D positions of the one or more features in each of the plurality of 2D images;

determining, by the processor, a 3D angular orientation of the 3D representation of the object based on relative positions of the one or more features in the 3D representation of the object;

determining, by the processor, respective 2D angular orientations of the object in each of the plurality of 2D images;

ranking, by the processor, the plurality of 2D images based on the respective 2D angular orientations;

selecting, by the processor, a 2D image out of the plurality of 2D images, based on the ranking the plurality of 2D images; and

generating, by the processor, a texture for the 3D representation of the object based on the 2D image that was selected, wherein the texture of the 3D image comprises features that are aligned with one another.

2. The method of claim 1 , wherein the determining respective 2D angular orientations of the object in each of the plurality of 2D images comprises:

determining, by the processor, the respective 2D angular orientations of the object based on the respective 2D positions of the one or more features in each of the plurality of 2D images.

3. The method of claim 2 , wherein the determining respective 2D angular orientations of the object in each of the plurality of 2D images further comprises:

determining, by the processor, the respective 2D angular orientations of the object based on identification of the object based on at least two of the one or more features in one or more of the plurality of 2D images.

4. The method of claim 1 , wherein the object comprises a face of a person, wherein a first feature of the one or more features comprises a first eye of the person, wherein a second feature of the one or more features comprises a second eye of the person, and wherein the selecting the 2D image out of the plurality of 2D images comprises:

selecting, by the processor, the 2D image such that both the first eye and the second eye are in an open position.

5. The method of claim 4 , wherein the generating the texture of the 3D representation of the object comprises the first eye and the second eye looking in a same direction based on a single one of the plurality of 2D images that comprises the 2D image that was selected.

6. The method of claim 1 , wherein the ranking the plurality of 2D images based on the respective 2D angular orientations comprises:

ranking, by the processor, the plurality of 2D images in an order based on the respective 2D angular orientations, wherein a first 2D image comprises the respective 2D angular orientation being a substantially perpendicular view of the object and a last 2D image comprises the respective 2D angular orientation being offset from the substantially perpendicular view of the object.

7. The method of claim 6 , further comprising:

determining two or more 2D images of the plurality of 2D images that have respective 2D angular orientations that are substantially perpendicular views of the object; and

generating, by the processor, the texture of the 3D image, based on the two or more 2D images.

8. The method of claim 1 , wherein the texture comprises one or more of shading or coloring based on the 2D image out of the plurality of 2D images that was selected.

9. The method of claim 1 , wherein the generating the 3D representation of the object comprises:

generating, by the processor, the 3D representation of the object based on image capture positional information associated with each of the 2D images.

10. The method of claim 1 , wherein the determining the 3D angular orientation of the 3D representation of the object comprises:

determining, by the processor, a cross product of two vectors; and

determining, by the processor, the 3D angular orientation of the 3D representation of the object based on the cross product of the two vectors,

wherein a first vector of the two vectors comprises a difference between a first feature point 3D coordinate of a first feature of the one or more features in the 3D representation of the object and a second feature point 3D coordinate of a second feature of the one or more features in the 3D representation of the object, and

wherein a second vector of the two vectors comprises a difference between the first feature point 3D coordinate of the first feature of the one or more features in the 3D representation of the object and a third feature point 3D coordinate of a third feature of the one or more features in the 3D representation of the object.

11. The method of 10 , wherein the determining the 3D angular orientation of the 3D representation of the object based on the cross product of the two vectors further comprises:

determining, by the processor, a plane that comprises a midpoint between the first feature and the second feature;

determining, by the processor, a normal vector to the plane; and

applying, by the processor, a tilt to the cross product of the two vectors by rotating around the normal vector.

12. A computer program product for operating an image capturing system, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied in the medium that when executed by a processor causes the processor to perform the method of claim 1 .

13. An image processing system for processing images, the image processing system comprising:

a processor; and

a memory coupled to the processor and storing computer readable program code that when executed by the processor causes the processor to perform operations comprising:

receiving a plurality of 2D images of an object;

identifying respective 2D positions of one or more features in each of the plurality of 2D images;

generating a 3D representation of the object, based on the respective 2D positions of the one or more features in each of the plurality of 2D images; and

determining a 3D angular orientation of the 3D representation of the object based on relative positions of the one or more features in the 3D representation of the object;

determining respective 2D angular orientations of the object in each of the plurality of 2D images;

ranking the plurality of 2D images based on the respective 2D angular orientations;

selecting a 2D image out of the plurality of 2D images, based on the ranking the plurality of 2D images; and

generating a texture of the 3D representation of the object based on the 2D image that was selected, wherein the texture of the 3D image comprises features that are aligned with one another.

14. The image processing system of claim 13 , wherein the ranking the plurality of 2D images based on the respective 2D angular orientations comprises:

ranking the plurality of 2D images in an order based on the respective 2D angular orientations, wherein a first 2D image comprises the respective 2D angular orientation being a substantially perpendicular view of the object and a last 2D image comprises the respective 2D angular orientation being offset from the substantially perpendicular view of the object.

15. The image processing system of claim 14 , wherein the ranking the plurality of 2D images based on the respective 2D angular orientations further comprises:

determining two or more 2D images of the plurality of 2D images that have respective 2D angular orientations that are substantially perpendicular views of the object; and

generating, by the processor, the texture of the 3D image, based on the two or more 2D images.

16. The image processing system of claim 13 , wherein the texture comprises one or more of shading or coloring based on the 2D image out of the plurality of 2D images that was selected.

17. The image processing system of claim 13 , wherein the determining the 3D angular orientation of the 3D representation of the object comprises:

determining a cross product of two vectors; and

determining the 3D angular orientation of the 3D representation of the object based on the cross product of the two vectors,

wherein a first vector of the two vectors comprises a difference between a first feature point 3D coordinate of a first feature of the one or more features in the 3D representation of the object and a second feature point 3D coordinate of a second feature of the one or more features in the 3D representation of the object, and

wherein a second vector of the two vectors comprises a difference between the first feature point 3D coordinate of the first feature of the one or more features in the 3D representation of the object and a third feature point 3D coordinate of a third feature of the one or more features in the 3D representation of the object.

18. The image processing system of claim 17 , wherein the determining the 3D angular orientation of the 3D representation of the object based on the cross product of the two vectors further comprises:

determining a plane that comprises a midpoint between the first feature and the second feature;

determining a normal vector to the plane; and

applying a tilt to the cross product of the two vectors by rotating around the normal vector.