Method and system for similarity-based image classification

• US 6,269,358 B1
• Filed: 06/16/2000
• Issued: 07/31/2001
• Est. Priority Date: 04/22/1998
• Status: Expired due to Term

• Current Assignee: NEC Corporation
• Original Assignee: Kyoji Hirata
• Inventors: Hirata, Kyoji
• Primary Examiner(s): Alam, Hosain T.
• Application Number:
  US09/595,807
• Time in Patent Office: 410 Days
• Field of Search: 707/6--, 707/104, 707/3-5, 709/217-219, 382/190, 382/192, 382/3.5
• US Class Current: 1/1
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: Y10S 707/915 Image
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method and apparatus for classifying and querying a database of images, in which the images in the database are classified using primary objects as a clustering center. A query interface is presented to the user allowing the user to use the primary objects to formulate queries to be applied to the classified database of images.

Claims

1. A method of querying a database of images, the method comprising the steps of:

(a) selecting at least one primary shape from a set of primary shapes as a query to be applied to the database of images;

(b) selecting at least one of a plurality of categories of images for each of the at least one primary shape selected, the categories having been formed by calculating a similarity value between each of the images and each of the primary shapes and classifying the images into the categories based on a threshold for the similarity value, each of the categories being represented by one of the primary shapes; and

(c) displaying ones of the images in the selected categories.

2. The method according to claim 1, wherein, when more than one primary shape is specified, the step of displaying displays only the images in an intersection of the categories.

3. The method according to claim 1, further comprising the step of defining a spatial relationship between the selected primary shapes when more than one primary shape is selected.

4. The method according to claim 1, further comprising the step of assigning a weight value to each of the selected primary shapes when more than one primary shape is selected.

5. The method according to claim 1, wherein the primary shapes comprise base primary shapes, including a circle, a square, a triangle and a line.

6. The method according to claim 1, wherein the primary shapes comprise combinations of base primary shapes, the base primary shapes including a circle, a square, a triangle and a line.

7. The method according to claim 1, wherein the primary shapes comprise variations of base primary shapes based upon size and aspect ratio.

8. The method according to claim 1, wherein the calculation of the similarity value is dependent upon a location of objects within the images.

9. The method according to claim 1, wherein the calculation of the similarity value is independent of a location of objects within the images.

10. The method according to claim 1, wherein a value of the threshold determines a number of the displayed images.

11. The method according to claim 1, wherein the database of images is a multimedia database.

12. The method according to claim 1, wherein the database of images is on the World Wide Web (WWW).

13. A system of querying a database of images, the system comprising:

(a) a workstation, including a display; and

(b) an application program, wherein a user selects at least one primary shape from a set of primary shapes as a query to be applied to the database of images;

whereupon the application program selects at least one of a plurality of categories of images for each of the at least one primary shape selected, the categories having been formed by calculating a similarity value between each of the images and each of the primary shapes and classifying the images into the categories based on a threshold for the similarity value, each of the categories being represented by one of the primary shapes; and

whereupon ones of the images in the selected categories are displayed on the display.

14. The system according to claim 13, wherein in the application program, when more than one primary shape is specified, only the images in an intersection of the categories is displayed.

15. The system according to claim 13, wherein, in the application program, a spatial relationship is defined between the selected primary shapes when more than one primary shape is selected.

16. The system according to claim 13, wherein, in the application program, a weight value is assigned to each of the selected primary shapes when more than one primary shape is selected.

17. The system according to claim 13, wherein the primary shapes comprise base primary shapes, including a circle, a square, a triangle and a line.

18. The system according to claim 13, wherein the primary shapes comprise combinations of base primary shapes, the base primary shapes including a circle, a square, a triangle and a line.

19. The system according to claim 13, wherein the primary shapes comprise variations of base primary shapes based upon size and aspect ratio.

20. The system according to claim 13, wherein, in the application program, the calculation of the similarity value is dependent upon a location of objects within the images.

21. The system according to claim 13, wherein, in the application program, the calculation of the similarity value is independent of a location of objects within the images.

22. The system according to claim 13, wherein a value of the threshold determines a number of the displayed images.

23. The system according to claim 13, wherein the database of images is a multimedia database.

24. The system according to claim 13, wherein the database of images is on the World Wide Web (WWW).