Gauging based on global alignment and sub-models

• US 6,993,177 B1
• Filed: 11/02/2001
• Issued: 01/31/2006
• Est. Priority Date: 11/02/2001
• Status: Active Grant

• Current Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Original Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Inventors: Bachelder, Ivan
• Primary Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US10/000,413
• Time in Patent Office: 1,551 Days
• Field of Search: 382/151, 382/103, 382/159, 382/154, 382/181, 382/155, 382/173, 382/190, 382/201, 382/206, 382/209, 382/276, 345/419, 345/427, 345/420, 345/619, 345/679, 345/680, 703/2, 700/29, 700/30, 701/59
• US Class Current: 382/151
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors

Abstract

A method for accurately and efficiently determining the location of points or entities in a machine vision image. A set of sub-models are constructed from a global training model representing objects viewed by the machine vision system. The set of sub-models are used to fix the actual location of user selected points or entities. Configuration of the sub-models is automated to ensure that the sub-models contain sufficiently stable features within optimally sized regions without requiring substantial user expertise. Located entities are compared to evaluate compliance with pre-selected tolerances.

Claims

1. A method of gauging entities in an image comprising the steps of:

constructing a model data structure;

identifying a set of gauge entities in said model;

automatically configuring sub-models according to the stability of features in said sub-models for computing position of each of said gauge entities by;

defining a set of regions for each gauge entity;

assessing each region for stable reference features;

selecting a best region for each gauge entity; and

training a sub-model representing each feature that exceeds a predetermined stability threshold within each of said best regions;

locating said sub-models in said image;

computing positions of each of said gauge entities by reference to locations of located sub-models; and

determining the spatial relationship between said gauge entities.

2. The method according to claim 1 wherein the step of assessing each region further comprises the steps of:

segmenting each region into contiguous portions containing features;

mathematically assessing the stability of each portion; and

assessing the stability of each region according to the stability of portions within its respective region that exceed a predetermined stability threshold.

3. The method according to claim 2 wherein the step of mathematically assessing the stability of each portion further comprises the steps of:

selecting degrees of freedom required to compute the spatial relationship of particular gauge entities with respect to the respective feature; and

invoking an alignment tool to compute the stability of each feature for determining the spatial relationship of said gauge entity with respect to said respective feature and said degrees of freedom.

4. The method according to claim 2 wherein the step of

mathematically assessing the stability of each portion further comprises the steps of:

constructing a portion stability matrix for each portion;

computing a condition number for said matrix; and

determining the stability of each portion according to said condition number.

5. A method of gauging entities in an image comprising the steps of:

constructing a model data structure;

identifying a set of gauge entities in said model;

automatically configuring sub-models according to the stability of features in said sub-models for computing position of each of said gauge entities;

locating said sub-models in said image;

computing positions of each of said gauge entities by reference to locations of located sub-models by interpolation with reference to said located sub-models; and

determining the spatial relationship between said gauge entities.

6. An apparatus for gauging entities in an image comprising:

an image acquisition device; and

an image analysis system in communication with said image acquisition device wherein said image analysis system operates on an acquired image to determine spatial relationship between gauge entities by;

automatically configuring sub-models according to stability of features in said sub-models for computing position of each of said gauge entities by;

defining a set of regions for each gauge entity;

assessing each region for stable reference features;

selecting a best region for each gauge entity; and

training a sub-model representing each feature that exceeds a predetermined stability threshold within each of said best regions;

locating sub-models in said image; and

computing positions of said gauge entities by reference to locations of located sub-models.

7. The apparatus according to claim 6 wherein said image analysis system assesses each region by:

segmenting each region into contiguous portions containing features;

mathematically assessing the stability of each portion; and

assessing the stability of each region according to the stability of portions within its respective region that exceeds a predetermined stability threshold.

8. The apparatus according to claim 7 wherein said image analysis system mathematically asses the stability of each portion by:

selecting degrees of freedom required to compute the spatial relationship of particular gauge entities with respect to the respective feature; and

invoking an alignment tool to compute the stability of each feature for determining the spatial relationship of said gauge entity with respect to said respective feature and said degrees of freedom.

9. The apparatus according to claim 7 wherein said image analysis system mathematically assesses the stability of each portion by:

constructing a portion stability matrix for each potion;

computing a condition number for said matrix; and

determining the stability of each portion according to said condition number.

10. An apparatus for gauging entities in an image comprising:

means for acquiring an image; and

means for analyzing said image in communication with said means for acquiring an image wherein said means for analyzing said image operates on an acquired image to determine spatial relationships between gauge entities by;

automatically configuring sub-models according to stability of features in said sub-models for computing position of each of said gauge entities, by;

defining a set of regions for each gauge entity;

segmenting each region into contiguous portions containing features;

mathematically assessing the stability of each portion; and

assessing the stability of each region according to the stability of portions within its respective region that exceeds a predetermined threshold;

locating sub-models in said image; and

computing positions of sad gauge entities by reference to locations of located sub-models.

11. The apparatus according to claim 10 wherein said means for analyzing said image mathematically assesses the stability of each portion by:

selecting degrees of freedom required to compute the spatial relationship of particular gauge entities with respect to the respective feature; and

invoking an alignment tool to compute the stability of each feature for determining the spatial relationship of said gauge entity with respect to said respective feature and said degrees of freedom.

12. The apparatus according to claim 10 wherein said means for analyzing said image mathematically assesses the stability of each portion by:

constructing a portion stability matrix for each portion;

computing a condition number for said matrix; and

determining the stability of each portion according to said condition number.