Method for retrieving image and electronic device thereof

• US 9,886,762 B2
• Filed: 07/24/2015
• Issued: 02/06/2018
• Est. Priority Date: 07/25/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Iyer, Kiran Nanjunda, Kumar, Raushan, Lokkoju, Satish, Gopalakrishnan, Viswanath, Veera, Viswanath
• Primary Examiner(s): Kholdebarin, Iman K
• Assistant Examiner(s): Tran, Mai
• Application Number:
  US14/808,014
• Publication Number:
  US 20160027180A1
• Time in Patent Office: 928 Days
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 18/24147 Distances to closest patterns, e.g. nearest neighbour classification
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/162 involving graph-based methods
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

The present disclosure relates to image retrieval in an electronic device. An operating method of an electronic device includes determining an object included in an image and a position of extent occupied by the object in the image and retrieving at least one image including the object at the position from among a plurality of images.

Claims

1. A method for operating an electronic device, the method comprising:

detecting a user input on an image displayed in the electronic device;

determining, by the electronic device, an object included in the image, based on the detected user input;

retrieving at least one image from among a plurality of images stored in the electronic device, by comparing the object to metadata associated with each of the plurality of images; and

displaying, by the electronic device, the at least one image,

wherein the metadata comprises information regarding at least one object included in each of the plurality of images, and the information regarding the at least one object is determined by applying an unsupervised image segmentation to an output of a supervised image segmentation on each of the plurality of images, and

wherein the supervised image segmentation comprises training a random forest with a ground truth associated with the each of the plurality of images for processing pixels in the plurality of images, and the unsupervised image segmentation comprises a graph partitioning algorithm that defines each pixel for further processing the pixels.

2. The method of claim 1, wherein the determining the object comprises determining the object in the image based on at least one stroke or contour marked as the user input on the image.

3. The method of claim 1, wherein the determining the object comprises determining the object in the image based on a name corresponding to a text input as the user input.

4. The method of claim 1, further comprising:

determining, by the electronic device, the metadata including the information regarding the at least one object included in each of the plurality of images based on the image segmentations applied on each of the plurality of images; and

storing each of the plurality of images with the metadata.

5. The method of claim 1, wherein the information regarding the at least one object indicate semantic information of each of the plurality of images, and

wherein the metadata comprises semantic metadata of each of the plurality of images.

11. The method of claim 1, wherein the user input comprises at least one of a tap input, a press input or a drag input.

13. The method of claim 1, wherein each of the output of the supervised image segmentation on each of the plurality of images, is processed depending on labels of the pixels thereof during applying the unsupervised image segmentation thereon.

14. The method of claim 13, wherein the output of the supervised image segmentation, for which the pixels are assigned to the same label, is not modified during applying the unsupervised image segmentation thereon.

15. The method of claim 13, wherein the output of the supervised image segmentation, for which the pixels are distributed over various labels, is updated depending on the labels of the majority of the pixels during applying the unsupervised image segmentation thereon.

6. An electronic device comprising:

a controller configured to;

detect a user input on an image displayed in the electronic device;

determine an object included in the image, based on the detected user input; and

retrieve at least one image from among a plurality of images stored in the electronic device, by comparing the object to metadata associated with each of the plurality of images; and

a user interface configured to display the at least one image,

wherein the metadata comprises information regarding at least one object included in each of the plurality of images, and the information regarding the at least one object is determined by applying an unsupervised image segmentation to an output of a supervised image segmentation on each of the plurality of images, and

wherein the supervised image segmentation comprises training a random forest with a ground truth associated with the each of the plurality of images for processing pixels in the plurality of images, and the unsupervised image segmentation comprises a graph partitioning algorithm that defines each pixel for further processing the pixels.

7. The device of claim 6, wherein the controller is further configured to determine the object in the image based on at least one stroke or contour marked as the user input on the image.

8. The device of claim 6, wherein the controller is further configured to determine the object in the image based on a name corresponding to a text input as the user input.

9. The device of claim 6, further comprising:

a memory configured to store data,

wherein the controller is further configured to determine the metadata including the information regarding the at least one object included in each of the plurality of images, based on the image segmentations applied on each of the plurality of images, and

wherein the memory is configured to store each of the plurality of images with the metadata.

10. The device of claim 6, wherein the information regarding the at least one object indicate semantic information of each of the plurality of images, and

wherein the metadata comprises semantic metadata of each of the plurality of images.

12. The device of claim 6, wherein the user input comprises at least one of a tap input, a press input or a drag input.

16. The device of claim 6, wherein each of the output of the supervised image segmentation on each of the plurality of images, is processed depending on labels of the pixels thereof during applying the unsupervised image segmentation thereon.

17. The device of claim 16, wherein the output of the supervised image segmentation, for which the pixels are assigned to the same label, is not modified during applying the unsupervised image segmentation thereon.

18. The device of claim 16, wherein the output of the supervised image segmentation, for which the pixels are distributed over various labels, is updated depending on the labels of the majority of the pixels during applying the unsupervised image segmentation thereon.