Electronic device and method for providing color recommendation information with respect to space
An electronic device comprises a processor configured to: obtain a spatial image comprising a plurality of pixels corresponding to a plurality of objects, perform a pixel analysis on the plurality of pixels to extract one or more colors from the spatial image, obtain, based on the extracted one or more colors, color characteristic information about colors included in the plurality of objects in the spatial image and relation characteristic information defining relations between the plurality of objects in the spatial image, obtain, by applying the color characteristic information and the relation characteristic information to a first artificial intelligence model, a score of a color combination between each of the colors included in the plurality of objects in the spatial image and an arbitrary color, and provide color recommendation information with respect to a space comprising the plurality of objects, based on the score of the color combination.
1 . An electronic device comprising:
a memory storing one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory to:
obtain a spatial image comprising a plurality of pixels corresponding to a plurality of objects,
perform a pixel analysis on the plurality of pixels to extract one or more colors from the spatial image,
obtain, based on the extracted one or more colors, color characteristic information about colors included in the plurality of objects in the spatial image and relation characteristic information defining relations between the plurality of objects in the spatial image,
obtain, by applying the color characteristic information and the relation characteristic information to a first artificial intelligence model, a first color scheme score of a color combination, wherein the first artificial intelligence model is trained to estimate the first color scheme score of a color combination between a color included in at least an object from the plurality of objects in the spatial image and an arbitrary color, wherein the first artificial intelligence model is trained using (i) a co-occurrence count or color with respect to a plurality of training objects in a plurality of training images and (ii) training scores of color combinations between colors included in the plurality of training objects plurality of training images, and
provide color recommendation information with respect to a first object selected by a user from the plurality of objects, based on the first color scheme score of the color combination.
2 . The electronic device of claim 1 , wherein
the processor is further configured to execute the one or more instructions stored in the memory to:
obtain object characteristic information comprising information about a type or position of each object in the plurality of objects, and
obtain the first color scheme score of the color combination by further applying the object characteristic information to the first artificial intelligence model.
3 . The electronic device of claim 1 , wherein the relation characteristic information includes at least one of (i) information about position adjacency between at least two objects from the plurality of objects, or (ii) information about category relevance between the two objects.
4 . The electronic device of claim 1 , wherein
the processor is further configured to execute the one or more instructions stored in the memory to:
obtain information about a first interior style corresponding to the spatial image from a plurality of interior styles, and
select the first artificial intelligence model corresponding to the first interior style from a plurality of artificial intelligence models.
5 . The electronic device of claim 1 , wherein
the first artificial intelligence model is configured to:
obtain the plurality of training images,
obtain, based on the plurality of training images, the co-occurrence count or the color with respect to the plurality of training objects in the plurality of training images;
obtain, based on the co-occurrence count or the color, the training scores of the color combinations between the colors included in the plurality of training objects in the plurality of training images, and
obtain, based on the training scores of the color combinations, scores of color combinations of the plurality of objects in the spatial image.
6 . The electronic device of claim 5 , wherein
the first artificial intelligence model is trained to estimate, based on the training scores of the color combinations, a first color scheme score of a color combination between a color included in at least an object from the plurality of objects and the arbitrary color.
7 . The electronic device of claim 6 , wherein,
based on a determination the first object includes a plurality of faces including a first face and a second face, the first artificial intelligence model is trained to estimate a second color scheme score of a color combination between a color included in the first face and the arbitrary color, based on the training scores of the color combinations, and
the processor is further configured to execute the one or more instructions stored in the memory to provide color recommendation information with respect to the second face selected by the user, based on the second color scheme score.
8 . The electronic device of claim 6 , further comprising: a communication interface,
wherein the processor is further configured to execute the one or more instructions stored in the memory to, based on a determination the first object is an external device including a display, transmit the color recommendation information to the first object through the communication interface so that a color based on the color recommendation information with respect to the first object is displayed on the display of the first object.
9 . The electronic device of claim 8 , wherein
the processor is further configured to execute the one or more instructions stored in the memory to:
based on a determination the display includes a first panel and a second panel, obtain first color recommendation information with respect to the first panel and second color recommendation information with respect to the second panel, based on the first color scheme score of the color combination, and
transmit the first color recommendation information with respect to the first panel and the second color recommendation information with respect to the second panel to the first object through the communication interface so that a first color based on the first color recommendation information is displayed on the first panel, and a second color based on the second color recommendation information is displayed on the second panel.
10 . The electronic device of claim 9 , wherein
the processor is further configured to execute the one or more instructions stored in the memory to:
based on a determination the second panel is a part of the first panel, provide the first color recommendation information with respect to the first panel, based on the first color scheme score, and
provide the second color recommendation information with respect to the second panel, based on the first color scheme score and the second color scheme score.
11 . The electronic device of claim 9 , wherein, based on a determination the first object is a refrigerator, the second panel corresponds to a position of a food ingredient of which a storage period exceeds a threshold period.
12 . The electronic device of claim 8 , wherein
the processor is further configured to execute the one or more instructions stored in the memory to:
select an item corresponding to schedule information of the user, and
transmit information about the item and color recommendation information with respect to the first object to the first object through the communication interface so that the item is displayed on the display in a color based on the color recommendation information with respect to the first object.
13 . A method, performed by an electronic device, of recommending a color of an object, the method comprising:
obtaining a spatial image comprising a plurality of pixels corresponding to a plurality of objects;
performing a pixel analysis on the plurality of pixels to extract one or more colors from the spatial image;
obtaining, based on the extracted one or more colors, color characteristic information about colors included in the plurality of objects in the spatial image and relation characteristic information defining relations between the plurality of objects in the spatial image;
obtaining, by applying the color characteristic information and the relation characteristic information to a first artificial intelligence model, a first color scheme score of a color combination, wherein the first artificial intelligence model is trained to estimate the first color scheme score of a color combination between a color included in at least an object from the plurality of objects in the spatial image and an arbitrary color, wherein the first artificial intelligence model is trained using (i) a co-occurrence count of color with respect to a plurality of training objects in a plurality of training images and (ii) training scores of combinations between colors included in the plurality of training objects in the plurality of training images, and
providing color recommendation information with respect to a first object selected by a user from the plurality of objects, based on the first color scheme score of the color combination.
14 . The method of claim 13 , wherein the relation characteristic information includes at least one of (i) information about position adjacency between at least two objects from the plurality of objects, or (ii) information about category relevance between the two objects.
15 . The method of claim 13 , further comprising:
obtaining information about a first interior style corresponding to the spatial image from a plurality of interior styles; and
selecting the first artificial intelligence model corresponding to the first interior style from a plurality of artificial intelligence models.
16 . The method of claim 13 , wherein
the first artificial intelligence model is configured to:
obtain the plurality of training images,
obtain, based on the plurality of training images, the co-occurrence count or the color with respect to the plurality of training objects in the plurality of training images,
obtain, based on the co-occurrence count or the color, the color, the training scores of the color combinations between the colors included in the plurality of training objects in the plurality of training images, and
obtain, based on the training scores of the color combinations, scores of color combinations of the plurality of objects in the spatial image.
17 . The method of claim 16 , wherein
the first artificial intelligence model is trained to estimate, based on the training scores of the color combinations, a first color scheme score of a color combination between a color included in at least a first object from the plurality of objects and the arbitrary color.
18 . The method of claim 17 , wherein,
based on a determination the first object includes a plurality of faces including a first face and a second face, the first artificial intelligence model is trained to estimate a second color scheme score of a color combination between a color included in the first face and the arbitrary color, based on the training scores of the color combinations, and
color recommendation information with respect to the second face selected by the user is provided based on the second color scheme score.
19 . The method of claim 17 , further comprising: based on a determination the first object is an external device including a display, transmitting the color recommendation information to the first object through the communication interface so that a color based on the color recommendation information with respect to the first object is displayed on the display of the first object.
20 . A non-transitory computer readable medium, having instructions stored therein, which when executed by a processor in an electronic device cause the processor to execute a method comprising:
obtaining a spatial image comprising a plurality of pixels corresponding to a plurality of objects;
performing a pixel analysis on the plurality of pixels to extract one or more colors from the spatial image,
obtaining, based on the extracted one or more colors, color characteristic information about colors included in the plurality of objects in the spatial image and relation characteristic information defining relations between the plurality of objects in the spatial image;
obtaining, by applying the color characteristic information and the relation characteristic information to a first artificial intelligence model, a first color scheme score of a color combination; wherein the first artificial intelligence model is trained to estimate the first color scheme score of a color combination between a color included in at least an object from the plurality of objects in the spatial image and an arbitrary color, wherein the first artificial intelligence model is trained using (i) a co-occurrence count of color with respect to a plurality of training objects in a plurality of training images and (ii) training scores of color combinations between colors included in the plurality of training objects in the plurality of training images, and
providing color recommendation information with respect to a first object selected by a user from the plurality of object, based on the score of the color combination.