Granted Patent B2

US 12,353,495 · App. 18/107,611 · Granted Jul 8, 2025

Inventors: Hyunseung Choo (Gwacheon-si, KR); Ha Nl Choi (Seoul, KR)

Assignee: Research & Business Foundation Sungkyunkwan University

G06F16/9558G06F16/9566G06T7/10G06T7/70

Abstract

Claims (39)

1. A processor-implemented method of providing information, the method comprising:

wirelessly receiving, using a wireless communication, an image from a terminal, the image being captured using an image sensor;

generating a segmentation map including coordinate information on objects included in the image from the image, including segmenting the image into pixel units and recognizing the objects and labeling the objects with pixel values, differently assigned for each of the objects, in pixel units corresponding to each of the objects, wherein the pixel values are used to identify and distinguish different objects in the image;

extracting contexts including the objects included in the image and determining intentions of the objects based on the contexts;

obtaining at least one segmented image based on the image and the contexts using the segmentation map;

obtaining at least one keyword related to at least one of the objects based on the contexts;

generating a hyperlink based on the at least one segmented image and the at least one keyword, including selecting at least one of the at least one segmented image or the keyword based on a threshold value set in advance based on predetermined objection detection accuracy, wherein the threshold value relates to object detection accuracy in the image;

generating a silhouette based on the hyperlink and the coordinate information, wherein the silhouette corresponds to the object's boundaries according to the coordinate information;

mapping the hyperlink to the silhouette; and

wirelessly transmitting, using the wireless communication, the silhouette, to which the hyperlink is mapped, to the terminal.

2. The method of claim 1 , wherein the generating of the hyperlink comprises:

selecting at least one of the at least one segmented image or the keyword;

generating a search word based on the selection result;

obtaining a uniform resource locator (URL) based on the search word; and

generating the hyperlink based on the URL, wherein the URL is associated with information related to the object.

3. The method of claim 1 , wherein the transmitting of the silhouette to which the hyperlink is mapped to the terminal comprises:

overlapping the silhouette to which the hyperlink is mapped on the image, wherein the silhouette represents a boundary of the object; and

transmitting the image on which the silhouette overlaps to the terminal.

4. An apparatus for providing information, comprising:

a memory containing at least one instruction; and

a processor configured to perform the at least one instruction;

wherein the at least one instruction comprises:

wirelessly receiving, using a wireless communication, an image from a terminal, the image being captured using an image sensor;

generating a segmentation map including coordinate information on objects included in the image from the image, including segmenting the image into pixel units and recognizing the objects and labeling the objects with pixel values, differently assigned for each of the objects, in pixel units corresponding to each of the objects, wherein the pixel values are used to identify and distinguish different objects in the image;

extracting contexts including the objects included in the image and determining intentions of the objects based on the contexts;

obtaining at least one segmented image based on the image and the contexts using the segmentation map;

obtaining at least one keyword related to at least one of the objects based on the contexts;

generating a hyperlink based on the at least one segmented image and the at least one keyword, including selecting at least one of the at least one segmented image or the keyword based on a threshold value set in advance based on predetermined objection detection accuracy, wherein the threshold value relates to object detection accuracy in the image;

generating a silhouette based on the hyperlink and the coordinate information, wherein the silhouette corresponds to the object's boundaries according to the coordinate information;

mapping the hyperlink to the silhouette; and

wirelessly transmitting, using the wireless communication, the silhouette to which the hyperlink is mapped to the terminal.

5. The apparatus of claim 4 , wherein the generating of the hyperlink comprises:

selecting at least one of the at least one segmented image or the keyword;

generating a search word based on the selection result;

obtaining a uniform resource locator (URL) based on the search word; and

generating the hyperlink based on the URL, wherein the URL is associated with information related to the object.

6. The apparatus of claim 4 , wherein the transmitting of the silhouette to which the hyperlink is mapped to the terminal comprises:

overlapping the silhouette to which the hyperlink is mapped on the image, wherein the silhouette represents a boundary of the object; and

transmitting the image on which the silhouette overlaps to the terminal.

Assignments (1)

Priority Claims (2)

Continuity (1)

References Cited (11)