Image recognition/reproduction method and apparatus

• US 6,907,140 B2
• Filed: 10/07/2002
• Issued: 06/14/2005
• Est. Priority Date: 02/02/1994
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Matsugu, Masakazu, Iijima, Katsumi
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US10/265,923
• Publication Number:
  US 20030044073A1
• Time in Patent Office: 981 Days
• Field of Search: 382/118, 382/195, 382217-218, 382/243, 382/199, 382/165
• US Class Current: 382/195
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

An image recognition/reproduction method includes an extraction step of extracting local feature elements of an image, and a selection step of selecting a pair composed of a prescribed local feature element and position information indicative thereof, this pair being such that the distance between a pair composed of a prescribed local feature element and position information indicative thereof and a pair composed of a local feature element extracted at the extraction step and position information indicative thereof is less than a prescribed distance.

Claims

1. An object recognition method comprising the steps of:

storing a model array data of plural local feature elements constructing an object at each position of a predetermined lattice pattern space;

extracting the local feature elements from an input image and generating detecting levels of the local feature elements as array data; and

matching the array data and the model array data on the basis of a correlation of the array data extracted from the input image and the model array data,

wherein the local feature elements are geometrical elements constructing a face or a part of the face; and

wherein the local feature elements are cross patterns of an edge segment or curved lines of a predetermined curvature.

2. The method according to claim 1, wherein the detecting level of the local feature elements is a level for obtaining a region information.

3. The method according to claim 1, wherein the detecting level is a detecting level of a color information.

4. The method according to claim 1, wherein the lattice pattern space is two dimensional or three dimensional.

5. An image processing apparatus comprising:

a memory that stores characteristic models constructing an object and model array data thereof;

a generating device that extracts local feature elements resembling the characteristic models included in an input image by comparing the input image with the characteristic model stored in the memory based on a predetennined detecting level and generating array data related to a position and an arrangement of the local feature elements on a predetermined lattice pattern space; and

a recognition device that recognizes a specific object based on a correlation of the array data related to the position and the arrangement of the local feature elements generated by the generating device and the model array data stored in the memory,

wherein the local feature elements are geometrical elements constructing a face or a part of the face; and

wherein the local feature elements are cross patterns of an edge segment or curved lines of a predetermined curvature.

6. The apparatus according to claim 5, wherein the detecting level of the local feature elements is a level for obtaining a region informaiion.

7. The apparatus according to claim 6, wherein the detecting level is a detecting level of a color information.

8. The apparatus according to claim 5, wherein the lattice pattern space is two dimensional or three dimensional.

9. The apparatus according to claim 5, wherein the characteristic model is one of plural parts, or one of modified models changed sizes and/or view point directions of the plural parts.

10. An image processing apparatus comprising:

a memory that stores characteristic models constructing an object and model array data thereof;

a generating device that extracts local feature elements resembling the characteristic models included in an input image by comparing the input image with the characteristic model stored in the memory based on a predeteimined detecting level and generating array data related to a position and an arrangement of the local feature elements on a predetermined lattice pattern space; and

a recognition device that recognizes a specific object based on a correlation of the array data related to the position and the arrangement of the local feature elements generated by the generating device and the model array data stored in the memory,

wherein the local feature elements are geometrical elements constructing a face or a part of the face,

wherein the detecting level of the local feature elements is a level for obtaining a region information, and

wherein the detecting level is a detecting level of a color information.