Electronic device for obtaining image at user-intended moment and method for controlling the same
The disclosure relates to an artificial intelligence (AI) system that simulates a function, such as cognition and judgment, of a human brain using a machine learning algorithm, such as deep learning, and an application thereof. According to an embodiment, an electronic device may include a touchscreen, a camera, a memory, and a processor, where the processor may receive information about an image capturing situation from a user, may obtain a target image based on the information about the image capturing situation using a first artificial intelligence module stored in the memory, may obtain feature information included in the target image using a second artificial intelligence module stored in the memory, may store the feature information in the memory, and may store an image related to the feature information in the memory based on obtaining the image related to the feature information through the camera.
1. An electronic device comprising:
a camera;
memory; and
a processor,
wherein the memory stores instructions that, when executed by the processor, cause the electric device to:
receive information about an image capturing situation from a user,
obtain a target image based on the information about the image capturing situation using an artificial intelligence module,
obtain feature information comprised in the target image using the artificial intelligence module stored in the memory,
store the feature information in the memory, and
store an image related to the feature information in the memory based on obtaining the image related to the feature information through the camera.
2. The electronic device of claim 1 , wherein the instructions, when executed by the processor, cause the electronic device to display the target image on a touchscreen.
3. The electronic device of claim 2 , wherein the instructions, when executed by the processor, cause the electronic device to:
edit the target image based on a user manipulation for editing the target image displayed on the touchscreen in response to receiving the user manipulation, and
obtain feature information of the edited target image using the artificial intelligence module.
4. The electronic device of claim 1 , wherein the instructions, when executed by the processor, cause the electronic device to receive the information about the image capturing situation through at least one of a voice input of the user, a drawing input of the user, or an image input.
5. The electronic device of claim 1 , wherein the instructions, when executed by the processor, cause the electronic device to:
store at least one of a target sound or a target action in the memory based on the information about the image capturing situation further comprising at least one of the target sound or the target action, and
store a video related to at least one of the target sound or the target action in the memory based on obtaining the video through the camera.
6. The electronic device of claim 5 , wherein the instructions, when executed by the processor, cause the electronic device to classify at least one of a sound or an action comprised in a plurality of frames obtained through a preview of a camera application, and
obtain the video through similarity between at least one of the classified sound or action and the at least one of the target sound or the target action.
7. The electronic device of claim 5 , wherein the instructions, when executed by the processor, cause the electronic device to classify at least one of a sound or an action comprised in a plurality of frames stored in the memory, and
obtain the video through similarity between at least one of the classified sound or action and the at least one of the target sound or the target action.
8. The electronic device of claim 1 , wherein the instructions, when executed by the processor, cause the electronic device to obtain the image related to the feature information among a plurality of frames obtained through a preview of a camera application.
9. The electronic device of claim 1 , wherein the instructions, when executed by the processor, cause the electronic device to obtain the image related to the feature information among a plurality of frames stored in the memory.
10. The electronic device of claim 1 , wherein the feature information comprises a one-dimensional feature vector.
11. A method for controlling an electronic device, the method comprising:
receiving information about an image capturing situation from a user;
obtaining, by an artificial intelligence module, a target image based on the information about the image capturing situation;
obtaining, by the artificial intelligence module, feature information comprised in the target image;
storing the feature information in memory; and
storing an image related to the feature information in the memory based on obtaining the image related to the feature information through a camera.
12. The method of claim 11 , further comprising:
displaying the target image on a touchscreen; and
editing the target image based on a user manipulation for editing the target image displayed on the touchscreen in response to receiving the user manipulation,
wherein the obtaining of the feature information comprises
obtaining feature information of the edited target image using the artificial intelligence module.
13. The method of claim 11 , wherein the receiving comprises receiving the information about the image capturing situation through at least one of a voice input of the user, a drawing input of the user, or an image input.
14. The method of claim 11 , further comprising:
storing at least one of a target sound or a target action in the memory based on the information about the image capturing situation further comprising at least one of the target sound or the target action; and
storing a video related to at least one of the target sound or the target action in the memory based on obtaining the video through the camera.
15. The method of claim 14 , wherein the storing of the video in the memory comprises:
classifying at least one of a sound or an action comprised in a plurality of frames obtained through a preview of a camera application; and
obtaining the video through similarity between at least one of the classified sound or action and the at least one of the target sound or the target action.
16. The method of claim 14 , wherein the storing of the video in the memory comprises:
classifying at least one of a sound or an action comprised in a plurality of frames stored in the memory; and
obtaining the video through similarity between at least one of the classified sound or action and the at least one of the target sound or the target action.
17. The method of claim 11 , wherein the storing the image in the memory comprises obtaining the image related to the feature information among a plurality of frames obtained through a preview of a camera application.
18. The method of claim 11 , wherein the storing the image in the memory comprises obtaining the image related to the feature information among a plurality of frames stored in the memory.
19. The method of claim 11 , wherein the feature information comprises a one-dimensional feature vector.
20. A method comprising:
capturing a video in a single-take mode, the single take mode collecting a plurality of frames for a predetermined time;
compressing the plurality of frames into low-dimensional vectors;
comparing feature information for each of the plurality of frames, wherein the feature information is obtained from a reference database based on information about an image capturing situation input from a user;
extracting at least one frame including a feature stored in the reference database among the plurality of frames collected for the predetermined time; and
storing the extracted at least one frame or suggesting the extracted at least one frame to the user.