Image alignment method and device therefor

Abstract

Provided is a method for automatically performing image alignment without a user input. An image alignment method performed by an image alignment device, according to one embodiment of the present invention, can comprise the steps of: recognizing at least one person in an inputted image; determining a person-of-interest among the recognized persons; and performing image alignment, on the basis of the person-of-interest, on the inputted image, wherein the image alignment is performed without an input of a user of the image alignment deice for the image alignment.

1 . An image alignment method comprising:
 determining, by an image alignment device, a first person of interest and a second person of interest among the persons in an input image;   calculating respective scores based on respective actions performed by the first person of interest and the second person of interest as shown by the input image; and   performing image alignment for the input image based on the respective scores calculated with regard to the first person of interest and the second person of interest.   
     
     
         2 . The method of  claim 1 , further comprising:
 displaying, by the image alignment device, within a first display area, the image of the first person of interest; and   displaying, by the image alignment device, within a second display area, the image of the second person of interest,   wherein the performing image alignment comprises performing image alignment for at least one of the first display area and the second display area.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining an age of a person to be an age matching a pre-specified age range as a result of analyzing the age of the person among the persons in the input image; and   determining the person as the first person of interest.   
     
     
         4 . The method of  claim 1 , wherein the determining comprises:
 detecting an object having a specified shape at a specified position on each of the persons in the input image; and   determining a person as the first person of interest when the object having the specified shape is detected at the specified position on the person.   
     
     
         5 . The method of  claim 4 , wherein the specified position is a position corresponding to fingertips of a person, and the object having the specified shape is an object having the shape of a toothbrush. 
     
     
         6 . The method of  claim 4 , wherein the specified position is a position corresponding to fingertips of a person, and the object having the specified shape is an object having the shape of a pointer. 
     
     
         7 . The method of  claim 6 , further comprising:
 displaying, by the image alignment device, within a first display area, the image of the first person of interest; and   displaying, by the image alignment device, within a second display area, presentation content.   
     
     
         8 . The method of  claim 7 , wherein the displaying, by the image alignment device, within a first display area, the image of the first person of interest, comprising, displaying within the first display area, an image resulting from performing image alignment on the image based on the first person of interest. 
     
     
         9 . The method of  claim 8 , wherein the presentation content is received from a user terminal of the first person of interest. 
     
     
         10 . An image alignment method comprising:
 determining, by an image alignment device, a first person of interest among the recognized persons in an input image;   displaying, by the image alignment device, within a first display area, the image of the first person of interest; and   displaying, by the image alignment device, within a second display area, presentation content.   
     
     
         11 . The method of  claim 10 , wherein the determining comprises:
 detecting an object having a shape of a pointer at a specified position on each of the recognized persons in the input image; and   determining a person as the first person of interest when the object having the shape of the pointer is detected at the specified position on the person.   
     
     
         12 . The method of  claim 10 , wherein the displaying, by the image alignment device, within the first display area, the image of the first person of interest, comprising, displaying within the first display area, an image resulting from performing image alignment on the image based on the first person of interest. 
     
     
         13 . A smart mirror comprising:
 a front camera sensor which generates an input image;   an image alignment processor; and   a display device,   wherein the image alignment processor is configured to:   recognize one or more persons in the input image;   determine a first person of interest among the recognized persons;   display, within a first display area of the display device, the first person of interest; and   display, within a second display area of the display device, the presentation content.   
     
     
         14 . The smart mirror of  claim 13 , wherein the image alignment processor is further configured to:
 detect an object having a shape of a pointer at a specified position on each of the recognized persons in the input image; and   determine a person as the first person of interest when the object having the shape of the pointer is detected at the specified position on the person.   
     
     
         15 . The smart mirror of  claim 14 , wherein the image alignment processor is further configured to:
 display, within the first display area, an image resulting from performing image alignment on the image based on the first person of interest.