Method and electronic device for providing object recognition result

1. An electronic device comprising:

a memory storing computer executable instructions;

at least one processor configured to execute the computer executable instructions to detect an object included in an image, determine an image group corresponding to a first side of the detected object from among image groups, through matching between the image and the image groups each grouped for a same object, and estimate a front direction of the object of the determined image group in the image based on a photographing condition of the determined image group and a photographing condition of the image; and

an outputter configured to output information of the image group in the estimated front direction,

wherein the at least one processor is further configured to determine first similarities between the image and images of the image groups, and determine the image group corresponding to the object from among the image groups, based on a result of applying at least one weight to the first similarities, and

wherein the at least one weight is based on a difference between photographing conditions of the image estimated from the images of the image groups.

2. The electronic device of claim 1 , wherein the photographing condition includes at least one of a photographing position and a photographing direction.

3. The electronic device of claim 2 ,

wherein the at least one processor is further configured to:

estimate the photographing condition of the image from a photographing condition of a representative image of the determined image group through matching between the image and the representative image, and

estimate a front direction of the object of the representative image in the image from a predetermined front direction of the object of the representative image, based on the estimated photographing condition of the image, and

wherein the outputter is further configured to display a graphical user interface (GUI) representing information of the image group in the estimated front direction.

4. The electronic device of claim 3 , further comprising a user inputter configured to receive a user input of selecting the displayed GUI,

wherein the at least one processor is further configured to execute the computer executable instructions to access a site for purchasing the object of the image group based on the information of the image group.

5. The electronic device of claim 2 , wherein the at least one processor is further configured to:

execute the computer executable instructions to determine second similarities between the image and the image groups, based on the first similarities and the photographing conditions of the image, and

determine an image group having the second similarity that is greater than or equal to a threshold value, as the image group corresponding to the detected object.

6. The electronic device of claim 5 , wherein the at least one processor is further configured to multiply the first similarities by the at least one weight, and sum results of the multiplying.

7. The electronic device of claim 5 , wherein the at least one processor is further configured to learn a criterion for determining the first similarities.

8. The electronic device of claim 1 ,

wherein when the image is a depth image, the at least one processor is further configured to determine a three-dimensional model corresponding to the detected object through matching between three-dimensional models of a plurality of objects and the depth image, and

wherein the outputter is further configured to output information of the three-dimensional model in a front direction of the object of the three-dimensional model in the depth image, based on depth information of the depth image.

9. The electronic device of claim 1 , further comprising a sensor configured to track movement of a camera capturing the image,

wherein the at least one processor is further configured to estimate a front direction of the object of the determined image group in the image, based on the photographing condition of the determined image group and the photographing condition of the image changed according to the movement of the camera, and

wherein the outputter is configured to output information of the image group in the front direction in the image.

10. The electronic device of claim 1 , wherein the at least one processor is further configured to estimate the photographing condition of the image from the photographing condition of the determined image group through geometric verification.

11. A method of providing a recognition result of an object, comprising:

detecting an object included in an image;

determining an image group corresponding to a first side of the detected object from among image groups, through matching between the image and the image groups each grouped for a same object; and

outputting information of the image group in a front direction of the object of the determined image group, estimated from the image, based on a photographing condition of the determined image group and a photographing condition of the image,

wherein the determining of the image group corresponding to the detected object comprises:

determining first similarities between the image and images of the image groups, and

determining the image group corresponding to the object from among the image groups, based on a result of applying at least one weight to the first similarities, and

wherein the at least one weight is based on a difference between photographing conditions of the image estimated from the images of the image groups.

12. The method of claim 11 , wherein the photographing condition includes at least one of a photographing position and a photographing direction.

13. The method of claim 12 , wherein the outputting comprises:

estimating the photographing condition of the image from a photographing condition of a representative image of the determined image group through matching between the image and the representative image;

estimating a front direction of the object of the representative image in the image from a predetermined front direction of the object of the representative image, based on the estimated photographing condition; and

displaying a graphical user interface (GUI) representing information of the image group in the estimated front direction.

14. The method of claim 12 , wherein the determining of the image group corresponding to the detected object further comprises:

determining second similarities between the image and the image groups, based on the first similarities and the photographing conditions of the image; and

determining an image group having a second similarity that is greater than or equal to a threshold value, as the image group corresponding to the detected object.

15. A computer-readable recording medium storing a program for executing the method of claim 11 on a computer.