Image-capturing device and method for controlling same
The present disclosure relates to a tag and a method, performed by the tag, of transmitting a response signal to a tag search signal. Specifically, the disclosed method of transmitting a response signal includes operations of receiving, from at least one of a plurality of slave nodes, the tag search signal including identification data for identifying the tag, charging an energy storage element in the tag by using the received tag search signal, obtaining the identification data for identifying the tag from the received tag search signal, determining whether the obtained identification data matches identification information previously stored in the tag, and outputting a response signal to the tag search signal when the energy storage element is charged greater than a predetermined value and the obtained identification data matches the identification information previously stored in the tag.
1. A method, performed by an electronic device, of obtaining an image, the method comprising:
obtaining a first image including at least one object and a background;
detecting the at least one object and the background in the obtained first image, based on feature information regarding the at least one object and the background, respectively, in the first image;
determining image filters exhibiting different image effects, which are to be applied to each of the detected at least one object and the detected background; and
generating a second image by applying the determined image filters to each of the at least one object and the background,
wherein the determining of the image filters comprises:
analyzing a composition of the first image based on a relative positional relationship between the detected background and the detected at least one object;
when a proportion of the detected background occupying the obtained first image is greater than or equal to a preset threshold, determining information about a light source in the first image based on values of pixels in the first image; and
determining the image filters based on at least one of the determined information about the light source and the composition.
2. The method of claim 1 , wherein the detecting of the at least one object and the background comprises, when the obtained first image is input, obtaining the feature information regarding the at least one object and the background, respectively, by using a first neural network that outputs feature information for identifying an object region including an image of a portion corresponding to the at least one object and a background region including an image of a portion corresponding to the background.
3. The method of claim 2 , wherein the feature information comprises:
information about a type of the at least one object or the background; and
location information for determining locations of the object region and the background region in the first image.
4. The method of claim 2 , wherein the detecting of the at least one object and the background comprises:
determining location information for determining the object region and the background region in the obtained first image; and
detecting the object region and the background region in the first image based on the determined location information.
5. The method of claim 4 , wherein the obtaining of the feature information comprises:
determining information about types of the at least one object and the background respectively included in the object region and the background region; and
obtaining the feature information based on the determined information about the types of the at least one object and the background and the determined location information.
6. The method of claim 2 , wherein the generating of the second image comprises:
adjusting a size and an application range of the determined image filters; and
applying the image filters whose size and application range have been adjusted for each of the object region and the background region.
7. The method of claim 1 , wherein the determining of the image filters comprises, when the feature information is input, determining the image filters by using a second neural network that outputs the image filters to be applied to the first image.
8. The method of claim 1 , wherein the determining of the image filters comprises:
determining a shooting mode of the electronic device for capturing the first image, by using the feature information; and
determining the image filters based on shooting parameters determined according to the determined shooting mode.
9. A non-transitory computer-readable recording medium having recorded thereon a program for performing the method of claim 1 on a computer.
10. An electronic device comprising:
a display displaying at least one image;
a storage storing one or more instructions; and
a processor configured to execute the one or more instructions to:
obtain a first image including at least one object and a background,
detect the at least one object and the background in the obtained first image, based on feature information regarding the at least one object and the background, respectively, in the first image,
determine image filters exhibiting different image effects, which are to be applied to each of the detected at least one object and the background,
generate a second image by applying the determined image filters to each of the at least one object and the background,
wherein the processor, to determine the image filters, is further configured to execute the one or more instructions to:
analyze a composition of the first image based on a relative positional relationship between the detected background and the detected at least one object,
when a proportion of the detected background occupying the obtained first image is greater than or equal to a preset threshold, determine information about a light source in the first image based on values of pixels in the first image, and
determine the image filters based on at least one of the determined information about the light source and the composition.
11. The electronic device of claim 10 , wherein the processor is further configured to, when the obtained first image is input, obtain the feature information by using a first neural network that outputs feature information for identifying an object region including an image of a portion corresponding to the at least one object and a background region including an image of a portion corresponding to the background.
12. The electronic device of claim 11 , wherein the processor is further configured to:
determine location information for determining the object region and the background region in the obtained first image, and
detect the object region and the background region in the first image based on the determined location information.
13. The electronic device of claim 10 , wherein the processor is further configured to, when the feature information is input, determine the image filters by using a second neural network that outputs the image filters to be applied to the first image.