IMAGE CLASSIFICATION USING CAPTURE-LOCATION-SEQUENCE INFORMATION

• US 20090257663A1
• Filed: 04/14/2008
• Published: 10/15/2009
• Est. Priority Date: 04/14/2008
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Eastman Kodak Company
• Inventors: Luo, Jiebo, Yuan, Junsong
• Granted Patent: US 8,055,081 B2
• Time in Patent Office: Days
• US Class Current: 382/224
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

Classification of a group of temporally related images is disclosed, wherein a capture-location sequence is identified from the group of temporally related images. The capture-location-sequence information, which is associated collectively with the capture-location sequence, is compared with each of a plurality of sets of predetermined capture-location-sequence characteristics. Each set is associated with a predetermined classification. An identified classification associated with the group of temporally related images is identified based at least upon results from the comparing step; and the identified classification is stored in a processor-accessible memory system.

Claims

1. A method implemented at least in part by a data processing system, the method for facilitating classification of a group of temporally related images, and the method comprising the steps of:

identifying a capture-location sequence from the group of temporally related images;

comparing capture-location-sequence information, which is associated collectively with the capture-location sequence, with each of a plurality of sets of predetermined capture-location-sequence characteristics, each set associated with a predetermined classification;

identifying an identified classification associated with the group of temporally related images based at least upon results from the comparing step; and

storing the identified classification in a processor-accessible memory system.

2. The method of claim 1, wherein the capture-location sequence is identified based at least upon GPS information associated with at least some of the images in the group.

3. The method of claim 1, further comprising the step of comparing image-content information, which is associated collectively with the group of temporally related images, with each of a plurality of sets of predetermined image-content characteristics, each set of predetermined image-content characteristics associated with a predetermined classification, wherein the identifying step identifies the identified classification based at least upon results from the two comparing steps.

4. The method of claim 1, wherein the identified classification is identified from one of the predetermined classifications.

5. The method of claim 1, wherein the capture-location-sequence information comprises a trace of the capture-location sequence.

6. The method of claim 5, wherein the trace includes a spatial and a temporal domain.

7. The method of claim 5, further comprising the step of:

determining a feature of the trace, the feature pertaining to a spatial range represented by the trace or a speed of movement represented by the trace, wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.

8. The method of claim 5, further comprising the step of:

determining a feature of the trace, the feature pertaining to an entropy, a distance to a centroid, a variance, a skewness, a kurtosis, a spatial range, a temporal duration, a length, or a speed,

wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.

9. The method of claim 1, wherein the predetermined classifications comprise hiking and city tour.

10. The method of claim 9, wherein the predetermined classifications further comprise a wedding, a ball game, a backyard activity, a beach activity, a road trip, a picnic, a Christmas activity, and a Birthday party.

11. A processor-accessible memory system storing instructions configured to cause a data processing system to implement a method for facilitating classification of a group of temporally related images, wherein the instructions comprise:

instructions for identifying a capture-location sequence from the group of temporally related images;

instructions for comparing capture-location-sequence information, which is associated collectively with the capture-location sequence, with each of a plurality of sets of predetermined capture-location-sequence characteristics, each set associated with a predetermined classification;

instructions for identifying an identified classification associated with the group of temporally related images based at least upon results from the comparing step; and

instructions for storing the identified classification in a processor-accessible memory system.

12. The processor-accessible memory system of claim 11, wherein the capture-location-sequence information comprises a trace of the capture-location sequence.

13. The processor-accessible memory system of claim 12, wherein the trace includes a spatial and a temporal domain.

14. The processor-accessible memory system of claim 12, further comprising the step of:

determining a feature of the trace, the feature pertaining to a spatial range represented by the trace or a speed of movement represented by the trace,

wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.

15. The processor-accessible memory system of claim 12, further comprising the step of:

determining a feature of the trace, the feature pertaining to an entropy, a distance to a centroid, a variance, a skewness, a tkurtosis, a spatial range, a temporal duration, a length, or a speed,

wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.

16. A system comprising:

a data processing system; and

a memory system communicatively connected to the data processing system and storing instructions configured to cause the data processing system to implement a method for facilitating classification of a group of temporally related images, wherein the instructions comprise;

instructions for identifying a capture-location sequence from the group of temporally related images;

instructions for comparing capture-location-sequence information, which is associated collectively with the capture-location sequence, with each of a plurality of sets of predetermined capture-location-sequence characteristics, each set associated with a predetermined classification;

instructions for identifying an identified classification associated with the group of temporally related images based at least upon results from the comparing step; and

instructions for storing the identified classification in the memory system.

17. The memory system of claim 16, wherein the capture-location-sequence information comprises a trace of the capture-location sequence.

18. The memory system of claim 17, wherein the trace includes a spatial and a temporal domain.

19. The memory system of claim 17, further comprising the step of:

determining a feature of the trace, the feature pertaining to a spatial range represented by the trace or a speed of movement represented by the trace,

wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.

20. The memory system of claim 17, her comprising the step of:

determining a feature of the trace, the feature pertaining to an entropy, a distance to a centroid, a variance, a skewness, a kurtosis, a spatial range, a temporal duration, a length, or a speed,

wherein the comparing step involves comparing the feature to a corresponding value or range of values represented in at least one of the sets of predetermined capture-location-sequence characteristics.