Method and apparatus for representing and searching for an object using shape

• US 7,362,921 B1
• Filed: 04/28/2000
• Issued: 04/22/2008
• Est. Priority Date: 04/29/1999
• Status: Expired due to Term

• Current Assignee: Rakuten Group, Inc.
• Original Assignee: Mitsubishi Denki Kabushiki Kaisha (Mitsubishi Electric Corporation)
• Inventors: Bober, Miroslaw
• Primary Examiner(s): Wu; Jingge
• Assistant Examiner(s): Seth; Manav
• Application Number:
  US09/959,469
• Time in Patent Office: 2,916 Days
• Field of Search: 382/100, 382/103, 382/107, 382/128, 382/131, 382/132, 382/173, 382/199, 382/203, 382/225, 382/305, 382/306, 707 1- 5, 707101-102, 378/41, 348/26, 348/42, 348169-172
• US Class Current: 382/305
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06F 16/7854 using shape G06F16/7837 takes precedence
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/752 Contour matching
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A method is disclosed for representing a sequence of images constituting a moving image by processing signals corresponding to the image. An object appearing in one image is identified in the sequence in a first perspective view, and the same object appearing in another image is identified in the sequence in a second perspective view. A view descriptor of the outline of the object in the first perspective view is derived and at least one additional view descriptor of the outline of the object in another perspective view is also derived. The two or more view descriptors are associated to form a descriptor which is a single indexable entity for the sequence of images.

Claims

1. A method of representing a sequence of images constituting a video segment, by processing signals corresponding to the image, the method comprising:

identifying an object appearing in one image in the sequence in a first perspective view and identifying the same object appearing in another image in the sequence in a second perspective view;

deriving a view descriptor of the outline of the object in the first perspective view and at least one additional view descriptor of the outline of the object in another perspective view,

associating the two or more view descriptors to form a descriptor which is a single indexable entity for said sequence of images, and

wherein one of the at least one additional view descriptors corresponds to the outline of the object in the second perspective view also appearing in the image sequence,

wherein the view descriptors are derived using a curvature scale space representation.

2. A method as claimed in claim 1 further comprising deriving a descriptor of the object which is related to the shape the object and which is independent of the view of the object in the image.

4. An image search and retrieval system adapted for implementing a method as claimed in claim 1.

5. A computer system programmed to operate according to a method as claimed in claim 1.

6. A computer-readable storage medium storing computer-executable process steps for implementing a method as claimed in claim 1.

7. The method of claim 1 wherein other images in the image sequence do not include the object.

3. A method of representing an object appearing in an image to index the respective image or sequence of images of which it is a part for searching purposes, the method comprising deriving a plurality of view descriptors corresponding to a plurality of two-dimensional outlines of the object in different views, by processing signals corresponding to the outlines, and associating the view descriptors to form an object descriptor which is a single indexable entity for said respective image or image sequence, wherein the view descriptors are derived using a curvature scale space representation.