Machine Vision for the Life Sciences

geckokittenΤεχνίτη Νοημοσύνη και Ρομποτική

17 Οκτ 2013 (πριν από 3 χρόνια και 11 μήνες)

86 εμφανίσεις

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



Machine Vision for
the Life Sciences
Track, Trace & Control Solutions



Presented by:
Niels Wartenberg
June 12, 2012
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan




Niels Wartenberg
Microscan Sr. Applications
Engineer, Clinical

Senior Applications Engineer on Microscan's Clinical
Team and regular instructor of identification technology
courses, Mr. Wartenberg has been part of the Microscan
Team since 2000.

Prior to joining Microscan he gathered over 8 years
experience implementing solutions in clinical laboratory
systems.
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


is increasingly
adopted as an
effective means of
automating critical
processes and
increasing laboratory
throughput

Machine Vision
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


More Repeatable
Faster

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Machine Vision and Auto ID Converge
 Microscan legacy:

30+ years in Auto ID

30+ years in Machine Vision

 Read bar codes, PLUS:

Measure Vials

Check Fill Level

Verify Cap Alignment

…and More
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Agenda
 Machine Vision Basics

Definitions

Uses in the Life Sciences



 System Configurations

Smart Cameras

PC-based Systems


 Software Tools

Image Processing

Image Analysis


 Typical Applications

Identification

Inspection

Measurement

Robotic Guidance


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


The automatic extraction
of information from
digital images.
MACHINE VISION
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Examples of Useful Information
 Presence/Absence of a
Component
 Location/ Orientation of an
Object
 Reading of a Human or
Machine Readable Code

Non-Contact Measurement of
a Dimension

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Application Examples

Reading 1D symbols on microplates

Reading 2D symbols on vials/racks

Detecting correct orientation of slides

Inspecting print quality on tubes

Inspecting drops of dispensed liquid

Guiding a lab robot to pick & place
specimen tubes

Check presence/absence of
consumables (e.g. pipette tips, vials or
other labware)
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



System
Configurations
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


PROCESSING
SENSOR
LIGHTING
LENS
COMMUNICATION

PART

PART
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Lighting
 Proper lighting is essential to a
successful machine vision application

Reveals features we want to
detect/analyze

Minimizes everything else
 Key choices

Type of light

Light placement with respect to the part
and camera

Surface geometry & texture of part are
key factors in determining lighting

Generally, if the feature cannot
be seen, it cannot be analyzed
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Lens
 Gather light & deliver to the image sensor
 Determine:

Focal Point

Field of View
(FOV)

Depth of Focus
Lens & extension
tubes
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Lens Configurations
 Fixed, interchangeable lenses

C-Mount standard

Used with standard or smart
cameras

 Autofocus lenses

Mechanical or
liquid lens autofocus

Used in fully integrated
imagers
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Image Sensors
 Captures light and converts it
to a digital image
 More pixels = more detail
 Higher resolution required
when:

Resolving the narrow line in a
small bar code

Seeing small defect on a part

Making a precise dimensional
measurement
Sensor is inside
the camera
2MP sensor
.3MP sensor
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


 Digital cameras

Most modern machine vision cameras

Alternative standards
 Camera Link
 Firewire (IEEE 1394)
 USB (2.0 and 3.0)
 GigE
Machine Vision Cameras
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


GigE Vision
®
Standard
 GigE Vision standard

Developed by the Automated Imaging
Association (AIA)

Adopted by industry

Advantages over other standards

 GigE Vision advantages

High bandwidth for fast transfer of large
images

Uncompromised transfer up to 100
meters

Standard h/w & cables for easy, low cost
integration

Standard h/w to connect multiple cameras
to single/multiple computers

Highly scalable to follow Ethernet
bandwidth to 10GigE & beyond


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



Software
Tools
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Vision Processing Steps
 Modify the image to make features stand out
Acquire
Image
Image
Processing
Image
Analysis
Decision
Logic
Communicate
Results
 Extract features from the image
 Measure features and compare to specification
 Communicate Pass/Fail decisions and other data
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Image Processing vs. Image
Analysis Tools
 Image Processing

Original Image -> New Image

Used to make image easier to interpret or analyze

 Image Analysis

Image -> Features

Typical features include an edge, line, object, etc.



P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Image Processing Tool Examples
 Image arithmetic

 Image warping
 Binary & grayscale
morphology


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



Rotate text viewed at an
angle
Image Warping
 Often used prior to OCR (Optical Character
Recognition)

Unwrap text printed on an
arc or a circle

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Morphology
 Transforms the image to make certain features stand
out
 Use to expand, separate, merge, clean
 Does not extract features
Erode black pixels:
Create separation and then count
Dilate white pixels:
Increase Data Matrix cell size
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Image Analysis Tool Examples
 The Blob Tool
 Edge Detection
 Pattern Matching
 1D & 2D Symbols
 OCR & OCV
 Dynamic ROI Location

Measurement Resolution



P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


The Blob Tool
 A blob is a group of connected pixels within a size
range

similar color (shade of gray)

differ from surrounding area

 Typical applications

Count number of parts

Locate position of a part

Measure size of a part

Compare to a tolerance
Measure
:
Check size to ensure parts are not broken
Count
: Verify that all wires are installed
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Edge Detection
 Edge tools scan an image along a
user-specified direction

Detect transitions between two
regions of different intensity

Fit a line, circle or ellipse to the edge
data
 Applications

Detect or locate an object

Measure a distance

Locate a corner

Measure an angle
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Vector Edge Detection
 Edges can be
detected along
user defined
directions
(vectors)
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Edge Tool Usage
Measure
: Measure fill level of a
container or detect cap tightness
Locate
: Use two
Edge tools to find a
corner
Locate
: Check label placement
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Finding Patterns in an Image
 Normalized correlation based template matching

Scans template across image and identifies best match

Affected if part of what is in the template is missing from
the image being analyzed

 Geometric edge pattern matching

Matches patterns of edges in the image and the template

Is not affected if part of the template is missing in the
image or if the polarity of the image is reversed
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Pattern Matching
Intellifind Tool Example
 Pattern matching tools
learn the outline of a part
of pattern
 Scans across image and
identifies best match
 Locates pattern with sub-
pixel accuracy
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



1D & 2D Symbols
 Linear (1D) Bar Code Symbols

Limited data storage

Height provides redundancy

Requires higher contrast
 2D Symbols (ie, Data Matrix)

Data encoded in both height & width

Readable 360 °

Contrast as low as 20%

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


OCR - Optical Character Recognition
 Decodes human readable text

Can handle dot matrix
& dot peen printing

Noisy backgrounds

Uneven lighting

 Trainable

Neural Network based

Character addition/deletion

Tolerates scale changes


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


OCV – Optical Character Verification
 Typical Application

Checking correctness and
legibility of a printed label or
text

 Detects printing defects
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


OCR vs. OCV
 Terms often used incorrectly – NOT the same

OCR: Optical Character Recognition

OCV: Optical Character Verification

 OCR – an automatic identification tool

Intended to decode human readable information

 OCV – a print quality inspection tool

Intended to flag & reject poor quality text

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Dynamic ROI Location
 Relocating regions of interest (ROI) to compensate
for part position and rotation
ROIs After
Part Motion
ROIs Corrected For
Part Movement
ROIs
Positioned
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Nominal Measurement Resolution
Example:
Example:
Paper Clip = 1.0 "
Image width = 1280 Pixels
Resolution =
1.0 " /1280 Pixels
= .0008 " /Pixel
Car = 13.5’
Image width = 1280 Pixels
Resolution =
13.5’ / 1280 Pixels
162’’ /1280 Pixels
= .127" /Pixel
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Actual Measurement Resolution
 Depends on:

Sensor resolution

Field of View(FOV)

Sub-pixel capability of vision processing tools

P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



Typical
Applications
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Automatic Identification Applications
 Specimen ID
 Reagent ID
 Tube carrier ID
 Microtiter plate ID
 Microtiter vial ID
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Cap Color Detection
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan



Tube & Cap
Inspection
 Application requirements

Rack location

Bar code reading

Tube/cap inspection
 Solution

Camera

Custom GUI


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Absence/Presence with compact
Smart Camera
P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


 Application requirements

Determine object location &
orientation

Calibration in real world units

Robust & accurate pattern
matching
 Application examples

Robotic tube pick & place
 Colony picking


Vision Guided Motion Applications


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Machine Vision
 Automate critical
processes
 Increase throughput
 Achieve verifiable
process repeatability


P 800.762.1149 | www.Microscan.com
| Copyright 2012 Microscan


Thank You

 If you have questions regarding this
webinar or topic, please an e-mail to
info@microscan.com
.

 For further information about
machine vision, visit our website at
www.microscan.com
.