Method, medium, and system classifying photos

• US 20070081813A1
• Filed: 08/25/2006
• Published: 04/12/2007
• Est. Priority Date: 10/10/2005
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Seong-woon, Hong, Young-jin, Yoo, Myung-hyun
• Application Number:
  US11/509,610
• Publication Number:
  US 20070081813A1
• Time in Patent Office: Days
• US Class Current: 396/310
• CPC Class Codes: G03B 17/24 with means for separately producing marks on the film, e.g. title, time of exposure
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: H04N 1/32128 attached to the image data, e.g. file header, transmitted message header, information on the same page or in the same computer file as the image for information embedded in the image H04N1/32144
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/3214 of a date
• CPC Class Codes: H04N 2201/3215 of a time or duration
• CPC Class Codes: H04N 2201/3253 Position information, e.g. geographical position at time of capture, GPS data
• CPC Class Codes: H04N 2201/3277 The additional information being stored in the same storage device as the image data

Abstract

A method, medium, and system for classifying photos. The system apparatus may include a storage module which stores a plurality of photos, a location-based classification module which classifies the plurality of photos into one or more photo groups according to photographing locations of the plurality of photos, and a time-based classification module which chooses one of the photo groups produced by the location-based classification module and classifies a plurality of photos included in the chosen photo group into one or more sub-photo groups according to photographing times of the photos included in the chosen photo group.

Claims

1. A method of classifying photos, comprising:

classifying a plurality of photos into one or more photo groups according to photographing locations at which corresponding photos are respectively taken; and

performing a photo classifying operation for at least one photo group among the one or more photo groups according to photographing times at which photos included in the photo group are respectively taken.

2. The method of claim 1, wherein the classifying of the plurality of photos into one or more photo groups according to the corresponding photographing locations comprises:

creating a grid map having a plurality of cells and mapping to respective cells a quantity of iterations of a photographing operation which have been performed at a location corresponding to the respective cells and user stay time information indicating how long a user has stayed at the location corresponding to the respective cells, wherein each of the respective cells corresponds to one or more pieces of location information;

choosing one of the respective cells as a first reference cell;

classifying the first reference cell into a first cell group if a quantity of cells which are located within a first predetermined distance of the first reference cell, and correspond to longer user stay times than a first predetermined time, exceeds a first predetermined quantity; and

classifying into a first photo group a plurality of photos photographed at locations corresponding to cells that are classified into the first cell group.

3. The method of claim 2, further comprising:

classifying into a candidate cell group remaining cells of the grid map which do not belong to the first cell group and which correspond to photographing operation iteration quantities not smaller than a value of 1;

choosing one of the cells included in the candidate cell group as a second reference cell;

classifying the current second reference cell into a second cell group if a quantity of cells which are located within a second predetermined distance of the current second reference cell exceeds a second predetermined quantity; and

classifying into a second photo group a plurality of photos corresponding to cells included in the second cell group.

4. The method of claim 3, further comprising:

searching for a name of a place corresponding to photographing location information of the photos included in the second photo group; and

mapping the detected place name to the second photo group.

5. The method of claim 3, wherein the performing of the photo classifying operation for at least one photo group among the one or more photo groups according to photographing times comprises:

sequentially arranging the photos included in the first photo group in order of photographing times;

choosing one of the sequentially arranged photos as a reference photo; and

setting a photo group boundary between the reference photo and a next photo after the reference photo if a time interval between the reference photo and the next photo is larger than a sum of a predetermined value and an average of time intervals among a predefined number of photos ahead of or behind the reference photo.

6. The method of claim 5, wherein the predetermined value is determined based on photographing times of the photos included in the second photo group.

7. The method of claim 3 further comprising:

classifying the current second reference cell into a third cell group if a quantity of cells which are included in the candidate cell group and are located within the second predetermined distance of the current second reference cell is not greater than the second predetermined quantity; and

classifying into a third photo group a plurality of photos corresponding to cells included in the third cell group.

16. At least one medium comprising computer readable code to implement the method of claim 1.

17. At least one medium comprising computer readable code to implement the method of claim 2.

8. A system for classifying photos, comprising:

a location-based classification module to classify a plurality of photos into one or more photo groups according to corresponding photographing locations at which the plurality of photos are respectively taken; and

a time-based classification module to choose at least one of the photo groups and classify a plurality of photos included in the chosen photo group into one or more sub-photo groups according to photographing times at which the photos included in the chosen photo group are respectively taken.

9. The system of claim 8, further comprising a storage module to store the plurality of photos.

10. The system of claim 8, further comprising an additional information management module to create a grid map having a plurality of cells and to map to respective cells the quantity of iterations of a photographing operation which have been performed at a location corresponding to the respective cells and user stay time information indicating how long a user has stayed at the location corresponding to the respective cells, wherein each of the cells corresponds to one or more pieces of location information,

wherein the location-based classification module chooses one of the respective cells as a current first reference cell, classifies the current first reference cell into a first cell group if a quantity of cells which are located within a first predetermined distance of the current first reference cell, and correspond to longer user stay times than a first predetermined time, exceeds a first predetermined quantity, and classifies into a first photo group a plurality of photos corresponding to cells that are classified into the first cell group.

11. The system of claim 10, wherein the location-based classification module classifies into a candidate cell group remaining cells of the grid map which do not belong to the first cell group and which correspond to photographing operation iteration quantities not smaller than a value of 1, chooses one of the cells included in the candidate cell group as a second reference cell, classifies the current second reference cell into a second cell group if a quantity of cells which are located within a second predetermined distance of the current second reference cell exceeds a second predetermined quantity, and classifies into a second photo group a plurality of photos corresponding to cells included in the second cell group.

12. The system of claim 11 further comprising a group name mapping module to search for a name of a place corresponding to photographing location information of the photos included in the second photo group, and to map the detected place name to the second photo group.

13. The system of claim 11, wherein the time-based classification module sequentially arranges the photos included in the first photo group in order of photographing times, chooses one of the sequentially arranged photos as a reference photo, and sets a photo group boundary between the reference photo and a next photo after the reference photo if a time interval between the reference photo and the next photo is larger than a sum of a predetermined value and an average of time intervals among a predefined number of photos ahead of or behind the reference photo.

14. The system of claim 13, wherein the predetermined value is determined based on photographing times of the photos included in the second photo group.

15. The system of claim 11, wherein the location-based classification module classifies the current second reference cell into a third cell group if a quantity of cells which are included in the candidate cell group and are located within the second predetermined distance of the current second reference cell is not greater than the second predetermined quantity, and classifies into a third photo group a plurality of photos corresponding to cells included in the third cell group.