Device and method to detect dislocation of object image data

• US 5,793,901 A
• Filed: 10/02/1995
• Issued: 08/11/1998
• Est. Priority Date: 09/30/1994
• Status: Expired due to Term

• Current Assignee: Omron Corporation
• Original Assignee: Omron Corporation
• Inventors: Matsutake, Osamu, Iida, Junko
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): MEHTA, BHAVESH M
• Application Number:
  US08/537,333
• Time in Patent Office: 1,044 Days
• Field of Search: 382/151, 382/141, 382/142, 382/143, 382/144, 382/145, 382/216, 382/287, 382/288, 382/289, 382/291, 382/294, 382/296, 382/297, 382/293, 382/295, 382/218, 348/94, 348/95
• US Class Current: 382/294
• CPC Class Codes: G06T 7/75 involving models

Abstract

This invention provides a device and method to detect a degree of misregistration and angle of misrotation of an object image, a device to measure an object using such a degree of misregistration and an angle of misrotation and a device to record data representing a model. A model of the object used is imaged and at least two regions are established in the image data of the model. Delimiting values which are extracted from geometric features of these regions are stored as reference values. The same regions are then extracted from an image of the object, and similar delimiting values are obtained from their geometric features. The conditions so obtained are compared with the stored standard reference values. The degree of misregistration of the object to be processed with respect to the object used as the standard of comparison is calculated from the difference between these two values.

Claims

1. A method of detecting a dislocation of an object image with respect to a model image, the object image being represented by object image data and the model image being represented by standard image data, the method comprising the steps of:

establishing two standard image regions in the standard image data;

generating a plurality of rotated standard image regions for each of the two standard image regions;

generating a standard delimiting value based on geometric characteristics of the two standard image regions;

extracting two object image regions from the object image data corresponding to the two standard image regions and the plurality of rotated standard image regions;

generating an object delimiting value based on geometric characteristics of the two object image regions;

comparing the object delimiting value with the standard delimiting value to detect a dislocation of the object image with respect to the standard image.

2. The method of claim 1, wherein the dislocation of the object image comprises a degree of misregistration represented in two directions and an angle of misrotation with respect to the standard image.

3. The method of claim 1, further comprising the steps of:

after the establishing step, generating geometric characteristics of each standard image region based on that region'"'"'s center of gravity; and

after the extracting step, generating geometric characteristics of each object image region based on that region'"'"'s center of gravity.

4. A device for detecting a dislocation of an object image, comprising:

means for generating standard image data representing a model image of the object image;

a first memory that stores image data of two standard image regions of the standard image data and the standard delimiting value;

a first calculation unit that generates a standard delimiting value based upon geometric characteristics of the two standard image regions of the standard image data;

wherein the first memory stores the standard delimiting value;

an image rotating unit that generates a plurality of processed standard image regions wherein each of the successive processed image data represents the respective standard image region rotated by a different incremental angular amount;

second memory that stores the plurality of processed standard image data;

an extracting unit that extracts two object image regions from object image data by matching the object image data with each of the processed standard image regions;

a second calculation unit that calculates an object delimiting value based upon geometric characteristics of the object image regions; and

a comparison unit that compares the object delimiting value with the standard delimiting value to determine the dislocation of the object image.

5. The device of claim 4, wherein the means for generating standard image data comprises a scanner.

6. The device of claim 4, wherein the dislocation of the object image comprises a degree of misregistration in two directions and an angle of misrotation with respect to the standard image data.

7. The device of claim 4, wherein:

each geometric characteristic used by the first calculation unit is the center of gravity of the respective standard image region, and

each geometric characteristic used by the second calculation unit is the center of gravity of the respective object image region.

8. The device of claim 4, wherein:

the geometric characteristics of each standard image region comprise two corners of the standard image region, and

the geometric characteristics of each object image region comprise two corners of the object image region.

9. The device of claim 4, wherein:

the standard delimiting value is defined by an angle formed between a line linking the two standard image regions and a reference line,

the object delimiting value is defined by an angle formed between a line linking the two object image regions and the reference line, and

the angle of misrotation is defined by the difference between the angle of the standard delimiting value and the angle of the object delimiting value.

10. The device of claim 4, wherein:

the standard delimiting value is defined by a coordinate of the first standard image region and a coordinate of the second standard image region,

the object delimiting value is defined by a coordinate of the first object image region and a coordinate of the second object image region, and

degree of misregistration is defined by difference between said coordinates for the first standard image region and the first object image region and between said coordinates for the second standard image region and the second object image region.

11. A device for detecting a dislocation of an object image, the object image being represented by object image data, the device comprising:

means to generate standard image data, the standard image data representing a model of the object image;

a first extracting unit that extracts two standard image regions from the standard image data;

a first delimiting value unit that obtains a standard delimiting value from geometric characteristics of the two standard image regions;

a first memory unit that stores the two standard image regions and said delimiting value;

a second memory unit that stores a plurality of processed standard image data regions, each processed standard image data region representing one of the two standard image regions rotated by different incremental angular amounts;

a second extracting unit that extracts two object image regions from the object image data by matching the object image data with the standard image regions,

a second delimiting value unit that generates an object delimiting value based upon geometric characteristics of the two object image regions; and

a calculation unit that calculates a dislocation of the object image by comparing the object delimiting value with the standard delimiting value.

12. The device of claim 11, wherein the calculation unit calculates the dislocation of the object image as a degree of misregistration in two directions and an angle of misrotation with respect to the standard image.

13. The device of claim 11, further comprising a model generator that generates the plurality of processed standard image data by executing an affine transformation.

14. An image processing device for recognizing a standard image in an object image, comprising:

a dislocation detecting device, comprising;

means for generating standard image data representing the standard image;

a first memory that stores image data of two standard image regions of the standard image,

a delimiting value unit for determining a standard delimiting value from geometric characteristics of each of the two standard image regions,

wherein the first memory stores the standard delimiting value;

a second memory that stores a plurality of processed standard image data regions, wherein each successive processed standard image data region is misrotated by successive incremental angular amount;

an extracting unit that extracts two object image regions from object image data by matching the object image data with each of the plurality of processed standard image data;

a calculation unit that calculates an object delimiting value from the geometric characteristics of each of the object image regions and calculates a dislocation of the object image by comparing the object delimiting value with the standard delimiting value; and

an image matching unit that matches the object image data with the standard image data using the dislocation of the object image.

15. A method for detecting a dislocation of a circular object image, the object image being represented by object image data, comprising the steps of:

generating standard image data representing a model of the object image to be detected;

establishing a standard image coordinate system for the standard image data with an image origin;

establishing four standard image regions, each region positioned at an intersection of an axis of the standard image coordinate system and a boundary of the standard image data;

determining a standard image reference coordinate from an intersection of two line segments created by joining opposing standard image regions;

extracting four object image regions, each region positioned oppositely from another region on a boundary of the object image data;

determining an object image reference coordinate from an intersection of two line segments created by joining opposing object image regions, using the same origin used for the standard image coordinate system; and

determining a degree of dislocation of the object image data by comparing the coordinates of the object image reference coordinate with the coordinates of the standard image reference coordinate.