Method of forming a template of an image of an object for use in the recognition of the object

• US 5,978,507 A
• Filed: 08/09/1994
• Issued: 11/02/1999
• Est. Priority Date: 01/29/1992
• Status: Expired due to Term

• Current Assignee: British Telecommunications (BT Group Plc) (BT Group PLC)
• Original Assignee: British Telecommunications PLC (BT Group PLC)
• Inventors: Welsh, William J, Shackleton, Mark A
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): SHALWALA, BIPIN H
• Application Number:
  US08/256,835
• Time in Patent Office: 1,911 Days
• Field of Search: 382/195, 382/190, 382/201, 382/203-206, 382/209, 382/218, 382/221, 382/224
• US Class Current: 382/195
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

A method of forming a template of an image of an object includes the steps of: detecting occurrences of at least one feature type within the image which meet a respective criterion; for each such occurrence, determining a feature position which is a point within the image at which the occurrence of the feature type is to be considered as being located; and constructing a structural mesh of links between the feature positions. A method is also disclosed of forming a template derived from a plurality of templates formed from respective images of different members of the class of objects and combining the templates to form a generalized template. In particular the templates are combined using a genetic algorithm. The invention provides a method of forming a template from one or more images which does not rely on a priori assumptions about the salient features of the object for which a template is to be obtained.

Claims

1. A method of forming a template of an image of an object comprising steps of:

a) detecting occurrences of at least one feature type within the image which meet a repective criterion;

b) for each such occurrence, determining a feature position which is a point within the image at which the occurrence of the feature type is to be considered as being located; and

c) constructing a structural mesh of links between the feature positions.

2. A method as claimed in claim 1 in which step a includes, in respect of each feature type the steps of:

d) forming a representation image in which only those portions of the image which are of the feature type are enhanced;

e) thresholding the representation image to obtain an image bitmap;

f) locating areas of activity within the image bitmap; and

g) determining which of the located areas of activity meet the criterion to be detected as an occurrence of the feature type.

3. A method as claimed in claim 2 in which the step of locating areas of activity within an image bit map includes comparing the corresponding picture elements of the image bit maps of different orientations of a given feature type and retaining only the maximum valued picture elements.

4. A method as claimed in claim 2 in which the criterion is that the area of activity must be greater than a threshold size.

5. A method as claimed in claim 2 in which the feature position is the centroid of the corresponding area of activity in a modified image bitmap.

6. A method as claimed in claim 1 in which a structural mesh is constructed by Delauney triangulation.

7. A method as claimed in claim 1 in which the template is modified by deleting lengths greater than a predetermined length.

8. A method as claimed in claim 1 in which the feature types are selected from a set of feature type which includes oriented edges, oriented peaks and oriented valleys.

9. A method of forming a template comprising deriving a plurality of templates forming respective images of different members of the class of objects according to claim 1 and combining the templates to form a generalised template.

10. A method as claimed in claim 9 in which the templates are combined using a genetic algorithm.