Method, medium, and apparatus with object descriptor generation using curvature gabor filter

• US 20090028444A1
• Filed: 12/19/2007
• Published: 01/29/2009
• Est. Priority Date: 07/10/2007
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd. (Samsung Group)
• Original Assignee: Samsung Electronics Co. Ltd. (Samsung Group)
• Inventors: Hwang, Won-Jun, Kee, Seok-cheol, Huang, Xiangsheng
• Application Number:
  US12/002,764
• Publication Number:
  US 20090028444A1
• Time in Patent Office: Days
• US Class Current: 382/224
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/449 Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

A method, medium, and apparatus with a generated object descriptor using a curvature gabor filter, with complementary object recognition being performed by applying a general gabor filter and a curvature gabor filter having various curvatures, such that the dimension and efficiency of a feature vector can be increased by detecting correlations between features of an object searching for a parameter and its position of an optimal curvature gabor filter through boosting learning, and projecting the extracted features onto a base vector having the highest classification rate.

Claims

1. A method of generating an object descriptor, the method comprising:

extracting gabor features from an input object image by applying a predetermined curvature gabor filter to the object image; and

generating an object descriptor for object recognition by projecting the extracted gabor features onto a predetermined base vector.

2. The method of claim 1, further comprising:

extracting gabor features from a training object image by applying the curvature gabor filter to the training object image; and

selecting gabor features by performing boosting learning for object image classification with respect to the extracted gabor features and establishing a gabor feature set comprising the selected gabor features,

wherein the extracting of the gabor features comprises extracting gabor features by applying a curvature gabor filter having the established gabor feature set to the input object image.

3. The method of claim 2, further comprising generating a base vector by performing Linear Determination Analysis (LDA) of the established gabor feature set,

wherein the generating of the object descriptor comprises generating an object descriptor for object recognition by projecting the extracted gabor features onto the generated base vector.

4. The method of claim 1, wherein the curvature gabor filter has at least one curvature.

5. The method of claim 4, wherein the curvature gabor filter satisfies the equation below

6. The method of claim 2, wherein the gabor feature set comprises a parameter of the curvature gabor filter and a position of the input object image to which the curvature gabor filter is applied.

8. A computer readable recording medium storing a computer readable program for executing the method of claim 1.

7. A method of generating an object descriptor, the method comprising:

extracting first gabor features from a training object image by applying a curvature gabor filter to the training object image;

selecting gabor features by performing boosting learning for object image classification with respect to the extracted gabor features and establishing a gabor feature set comprising the selected gabor features;

generating a base vector by performing Linear Determination Analysis (LDA) of the established gabor feature set;

extracting second gabor features from an input object image by applying a curvature gabor filter having the established gabor feature set to the input object image; and

generating an object descriptor for object recognition by projecting the extracted second gabor features onto the generated base vector.

9. An apparatus for generating an object descriptor, the apparatus comprising:

a first feature extractor to extract gabor features from an input object image by applying a predetermined curvature gabor filter to the object image; and

an object descriptor generator to generate an object descriptor for object recognition by projecting the extracted gabor features onto a predetermined base vector.

10. The apparatus of claim 9, further comprising:

a second feature extractor to extract gabor features from a training object image by applying the curvature gabor filter to the training object image; and

a selector to select gabor features by performing boosting learning for object image classification with respect to the extracted gabor features and to establish a gabor feature set comprising the selected gabor features,

wherein the first feature extractor extracts gabor features by applying a curvature gabor filter having the established gabor feature set to the input object image.

11. The apparatus of claim 10, further comprising a base vector generator to generate a base vector by performing Linear Determination Analysis (LDA) of the established gabor feature set,

wherein the object descriptor generator generates an object descriptor for object recognition by projecting the gabor features extracted by the first feature extractor onto the generated base vector.

12. The apparatus of claim 9, wherein the curvature gabor filter has at least one curvature.

13. The apparatus of claim 12, wherein the curvature gabor filter satisfies the equation below

14. The apparatus of claim 10, wherein the gabor feature set comprises a parameter of the curvature gabor filter and a position of the input object image to which the curvature gabor filter is applied.