Patent US6738491B1 successfully refreshed from Google Patents.
Patent US6678404B1 successfully refreshed from Google Patents.
US6678404B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Automatic referencing for computer vision applications
Assignee: Leica Microsystems CMS GmbH
•
Filing: 2000-10-31
•
Granted: 2004-01-13
•
Expires: 2020-10-31
Abstract
Abstract A method for creating and using reference images in a defect detection or location system which receives a plurality of learning images containing objects of interest and creates at least one reference image output. Using the reference image, the computer vision system detects discrepancies between objects of interest in an input image and the expected object from the reference images. The defect detection system generates a discrepancy image output. The computer vision system further determines the existence of the object of interest in an input image and provides the object of interest location if detected.
Inventors
- 👤 Shih-Jong J. Lee
- 👤 Seho Oh
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:19
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0004; G06T7/001; G06T7/30; G06T7/32; G06T7/35; G06T7/70; G06T7/73; G06T7/74
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
64 words
An automatic multi-resolution reference image generation method comprising: a. input a plurality of learning images; b. generate multi-resolution image representations of the plurality of learning images; c. perform alignment and accumulation of the plurality of learning images in multiple resolutions wherein the accumulation step accumulates a skewness statistic among pixels of the plurality of learning images; d. create reference images by multi-resolution image reconstruction.
Claim 2
Dependent Claim
64 words
An automatic multi-resolution reference image generation method comprising: a. input a plurality of learning images; b. generate multi-resolution image representations of the plurality of learning images; c. perform alignment and accumulation of the plurality of learning images in multiple resolutions wherein the accumulation step accumulates a skewness statistic among pixels of the plurality of learning images; d. create reference images by multi-resolution image reconstruction.
Claim 3
Dependent Claim
65 words
An automatic multi-resolution reference image generation method comprising: a. input a plurality of learning images; b. generate multi-resolution image representations of the plurality of learning images; c. perform alignment and accumulation of the plurality of learning images in multiple resolutions wherein the accumulation step accumulates a kurtosis statistic among the pixels of the plurality of learning images; d. create reference images by multi-resolution image reconstruction.
Claim 4
Dependent Claim
65 words
An automatic multi-resolution reference image generation method comprising: a. input a plurality of learning images; b. generate multi-resolution image representations of the plurality of learning images; c. perform alignment and accumulation of the plurality of learning images in multiple resolutions wherein the accumulation step accumulates a kurtosis statistic among the pixels of the plurality of learning images; d. create reference images by multi-resolution image reconstruction.
Claim 5
Dependent Claim
83 words
An automatic multi-resolution based object location method comprising: a. input a plurality of learning images; b. perform alignment and accumulation of the plurality of learning images to generate a reference image output wherein the accumulation step accumulates a skewness statistic among the pixels of the plurality of learning images; c. create multi-resolution reference images by multi-resolution image generation using the reference image output; d. acquire an input image; e. perform multi-resolution based object location using the input image and the multi-resolution reference images.
Claim 6
Dependent Claim
83 words
An automatic multi-resolution based object location method comprising: a. input a plurality of learning images; b. perform alignment and accumulation of the plurality of learning images to generate a reference image output wherein the accumulation step accumulates a skewness statistic among the pixels of the plurality of learning images; c. create multi-resolution reference images by multi-resolution image generation using the reference image output; d. acquire an input image; e. perform multi-resolution based object location using the input image and the multi-resolution reference images.
Claim 7
Dependent Claim
83 words
An automatic multi-resolution based object location method comprising: a. input a plurality of learning images; b. perform alignment and accumulation of the plurality of learning images to generate a reference image output wherein the accumulation step accumulates a kurtosis statistic among the pixels of the plurality of learning images; c. create multi-resolution reference images by multi-resolution image generation using the reference image output; d. acquire an input image; e. perform multi-resolution based object location using the input image and the multi-resolution reference images.
Claim 8
Dependent Claim
83 words
An automatic multi-resolution based object location method comprising: a. input a plurality of learning images; b. perform alignment and accumulation of the plurality of learning images to generate a reference image output wherein the accumulation step accumulates a kurtosis statistic among the pixels of the plurality of learning images; c. create multi-resolution reference images by multi-resolution image generation using the reference image output; d. acquire an input image; e. perform multi-resolution based object location using the input image and the multi-resolution reference images.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-01-12 | 2007-07-14 | 2008-01-13 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-01-12 | 2011-07-14 | 2012-01-13 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-01-12 | 2015-07-14 | 2016-01-13 | $7700.00 | Window Closed / Lapsed |