IP Library › Granted Patent US 12,567,134
Granted Patent B2
US 12,567,134 · App. 18/264,237 · Granted Mar 3, 2026

Apparatus and methods of detecting defects in machine vision systems

Inventors: Rayal Raj Prasad Nalam Venkat (Princeton, NJ); Yao-Jen Chang (Princeton, NJ); Benjamin S. Pollack (Jersey City, NJ); Ankur Kapoor (Plainsboro, NJ)
Assignee: Siemens Healthcare Diagnostics Inc.
G06T7/0002H04N5/265H04N17/002G06T2207/20212H04N23/90
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,567,134
App. No.
18/264,237
Granted
Mar 3, 2026
Kind
B2
Abstract

Methods of identifying a defect in a machine vision system. Embodiments of the method include providing a first imaging device having a first field of view; moving a reflective tool through the first field of view; capturing a plurality of images of the reflective tool at different locations in the first field of view using the first imaging device; and analyzing at least one of the plurality of images to identify one or more defects in the machine vision system. Systems and apparatus configured to carry out the methods are provided, as are other aspects.

Claims (37)

1 . A method of identifying a defect in a machine vision system, comprising:

providing a first imaging device having a first field of view;

moving a reflective tool through the first field of view;

capturing a plurality of images of the reflective tool at different locations in the first field of view using the first imaging device;

stitching two or more of the plurality of images of the reflective tool together to generate a synthetic background; and

analyzing at least one of the plurality of images including the synthetic background to identify whether there are one or more defects in the machine vision system, wherein the plurality of images comprises pixel values, and the stitching further comprises stitching two or more of the plurality of images together to generate a synthetic background having a light intensity wherein 90% of the pixel values are within 10% of each other.

2 . The method of claim 1 , further comprising illuminating the reflective tool during the capturing.

3 . The method of claim 1 , wherein moving the reflective tool, comprises moving a tube having a reflective surface through the first field of view.

4 . The method of claim 1 , wherein moving the reflective tool comprises moving a tube through the first field of view, the tube having a label attached thereto, the label having uniform reflectance.

5 . The method of claim 1 , wherein:

the moving the reflective tool further comprises moving a tube through the first field of view, the tube having a region of interest that is reflective; and

the capturing a plurality of images of the reflective tool further comprises capturing a plurality of images of the region of interest.

6 . The method of claim 5 , wherein the region of interest is white.

7 . The method of claim 1 , wherein the analyzing further comprises analyzing a region of interest.

8 . The method of claim 1 , wherein the analyzing further comprises analyzing one or more of the plurality of images to determine whether a particle is present on a lens of the first imaging device.

9 . The method of claim 1 , wherein the analyzing further comprises analyzing one or more of the plurality of images to determine whether one or more pixels of the first imaging device are defective.

10 . The method of claim 1 , wherein the capturing further comprises capturing 10 or more images of the reflective tool at 10 or more different locations in the first field of view.

11 . The method of claim 1 , wherein the capturing a plurality of images further comprises capturing a plurality of overlapping images of the reflective tool.

12 . The method of claim 11 , wherein the plurality of images overlap each other by at least 75%.

13 . The method of claim 1 , further comprising:

providing a second imaging device having a second field of view;

moving the reflective tool through the second field of view;

capturing a plurality of second images of the reflective tool at different locations in the second field of view; and

analyzing at least one of the plurality of second images to identify one or more defects in the machine vision system.

14 . A method of identifying a defect in an optical inspection station, comprising:

providing an imaging device having a field of view;

providing a transport system configured to move specimen containers through the field of view;

moving a reflective tool through the field of view;

capturing a plurality of images of the reflective tool at different locations in the field of view using the imaging device;

stitching two or more of the plurality of images of the reflective tool together to generate a synthetic background; and

analyzing at least one of the plurality of images including the synthetic background to identify whether there are one or more defects in the optical inspection station, wherein the plurality of images comprises pixel values, and the stitching further comprises stitching two or more of the plurality of images of the reflective tool together to generate a synthetic background having a light intensity wherein 90% of the pixel values are within 10% of each other.

15 . The method of claim 14 , wherein the reflective tool has a shape of a tube.

16 . The method of claim 14 , wherein the capturing a plurality of images further comprises capturing a plurality of images of the reflective tool that overlap each other.

17 . A machine vision system, comprising:

an imaging device having a field of view and configured to capture a plurality of images of a reflective tool at different locations in the field of view;

a transport system configured to move specimen containers and the reflective tool through the field of view; and

a computer configured to stitch two or more of the plurality of images of the reflective tool together to generate a synthetic background and analyze at least one of the plurality of images including the synthetic background to determine whether a defect exists in an optical chain of the machine vision system, wherein the plurality of images comprises pixel values, and the stitching further comprises stitching two or more of the plurality of images together to generate a synthetic background having a light intensity wherein 90% of the pixel values are within 10% of each other.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 25, 2023
From: NALAM VENKAT, RAYAL RAJ PRASAD; CHANG, YAO-JEN; KAPOOR, ANKUR
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 065344/0247 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 25, 2023
From: SIEMENS MEDICAL SOLUTIONS USA, INC.
To: SIEMENS HEALTHCARE DIAGNOSTICS INC.
Reel/Frame 065345/0924 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 25, 2023
From: POLLACK, BENJAMIN S.
To: SIEMENS HEALTHCARE DIAGNOSTICS INC.
Reel/Frame 065347/0504 →
Continuity (2)
Provisional Application 63145953 · Feb 4, 2021
Related Publication 20240037723A1 · Feb 1, 2024
References Cited (41)
US 5771068A · Sali et al. · 1998 [cited by applicant]
US 5826916A · Phillips · 1998 [cited by applicant]
US 5909504A · Whitman · 1999 [cited by examiner]
US 6940554B2 · Robins et al. · 2005 [cited by applicant]
US 8854431B2 · Song et al. · 2014 [cited by applicant]
US 9796089B2 · Lawrence, III et al. · 2017 [cited by applicant]
US 10453215B2 · Park et al. · 2019 [cited by applicant]
US 10697900B2 · Zhang · 2020 [cited by examiner]
US 11624711B2 · Hewicker · 2023 [cited by examiner]
US 11935216B2 · Lu · 2024 [cited by examiner]
US 20040169663A1 · Bernier · 2004 [cited by applicant]
US 20080187181A1 · Meadow et al. · 2008 [cited by applicant]
US 20110273569A1 · Douady et al. · 2011 [cited by applicant]
US 20130271755A1 · Lindner · 2013 [cited by applicant]
US 20140198202A1 · Kim · 2014 [cited by applicant]
US 20140368668A1 · Sasabuchi et al. · 2014 [cited by applicant]
US 20140374480A1 · Pollack · 2014 [cited by applicant]
US 20160321796A1 · Dordoni et al. · 2016 [cited by applicant]
US 20170255766A1 · Kaehler · 2017 [cited by applicant]
US 20190128908A1 · Nakagawa et al. · 2019 [cited by applicant]
CN 106796179A · 2017 [cited by applicant]
CN 107340297A · 2017 [cited by applicant]
CN 107923837A · 2018 [cited by applicant]
CN 108603802A · 2018 [cited by applicant]
DE 102014203798A1 · 2015 [cited by applicant]
JP H05302898A · 1993 [cited by applicant]
JP H06148083A · 1994 [cited by applicant]
JP H0868617A · 1996 [cited by applicant]
JP 2000241345A · 2000 [cited by applicant]
JP 2003259358A · 2003 [cited by applicant]
JP 2008014768A · 2008 [cited by applicant]
JP 2008032653A · 2008 [cited by applicant]
JP 2008241650A · 2008 [cited by applicant]
JP 2015509202A · 2015 [cited by applicant]
JP 2016224707A · 2016 [cited by applicant]
WO 2014034526A1 · 2014 [cited by applicant]
WO 2017132162A1 · 2017 [cited by applicant]
WO 2018089935A1 · 2018 [cited by applicant]
WO 2020061365A1 · 2020 [cited by applicant]
PCT International Search Report and Written Opinion dated May 11, 2022 (11 Pages). [cited by applicant]
Tsai, Du-Ming et al: “The evaluation of normalized cross correlations for defect detection”, Pattern Recognition Letters, Elsevier, Amsterdam, NL, vol. 24, No. 15, Nov. 1, 2003 (Nov. 1, 2003), pp. 2525-2535, XP004443620… [cited by applicant]