150819 Intro to Machine Vision Slides
Transcript of 150819 Intro to Machine Vision Slides
-
7/25/2019 150819 Intro to Machine Vision Slides
1/49
Introduction to Machine Vision
Samantha Frost
Product Marketing Manager, Vision
-
7/25/2019 150819 Intro to Machine Vision Slides
2/49
2 | 2015 Cognex Corporation
Agenda
What is machine vision?Why use machine vision?
Machine vision applications
Types of machine vision systemsVision system components
Machine vision terms
Improving vision system performance
Summary
Q&A
-
7/25/2019 150819 Intro to Machine Vision Slides
3/49
What is machine vision?
-
7/25/2019 150819 Intro to Machine Vision Slides
4/49
4 | 2015 Cognex Corporation
A simple concept
Formal definition:
Machine vision is the use of devices for optical non-
contact sensing to automatically receive and interpret an
image of a real scene in order to obtain information
and/or control machines or processes.- from the Society of Manufacturing Engineers
or more simply:Capturing an image from an industrial camera for
inspection or process control of manufactured products.
-
7/25/2019 150819 Intro to Machine Vision Slides
5/49
5 | 2015 Cognex Corporation
Evolution of machine vision
Proprietary Box Embedded
Boards
Modular
Vision
Barcode
Readers
PC Vision
Vision
Sensors
1982 Today
3D Displacement
Sensors
-
7/25/2019 150819 Intro to Machine Vision Slides
6/49
6 | 2015 Cognex Corporation
Simple examples
Machine vision systems analyze images Then makes decisions and/or returns numeric results
about each image it gets
6
The center tab on this bracket is
37.255 mm wide
Good Oil
Filter all
holes are
open
Reject oil
filter some
holes are
blocked
-
7/25/2019 150819 Intro to Machine Vision Slides
7/497 | 2015 Cognex Corporation
Image analysis
The primary purpose of machine vision is imageanalysis
Image
Decision
Answer
Location
-
7/25/2019 150819 Intro to Machine Vision Slides
8/498 | 2015 Cognex Corporation
Poll question #1
What is your level of machine vision experience?a. Im completely new to machine vision and have
never used it before
b. Im a beginner with limited machine vision
experience
c. Im an intermediate user, familiar with different
types of machine vision technology
d. Im an advanced user, but theres always more tolearn
-
7/25/2019 150819 Intro to Machine Vision Slides
9/499 | 2015 Cognex Corporation
Where is machine vision used?
Automotive Industry
Graphic Arts/ Packaging
Consumer Products
SemiconductorIndustry
Shipping/Transportation
Electronics/Computer
Industry
Medical/Pharmaceutical
Food Packaging
Industry
-
7/25/2019 150819 Intro to Machine Vision Slides
10/49
Why use machine vision?
-
7/25/2019 150819 Intro to Machine Vision Slides
11/4911 | 2015 Cognex Corporation
A critical role in achieving strategic goals
High speed production lines
Clean room environments
Hazardous environments
Microscopic inspection
Closed-loop process control
Robot guidance
Precise non-contact measurement
-
7/25/2019 150819 Intro to Machine Vision Slides
12/4912 | 2015 Cognex Corporation
Benefits of machine vision
Strategic Goal Machine Vision Applications
Higher Quality Inspection, measurement, gauging, andassembly verification
Increased Productivity Repetitive tasks formerly done manually are
now done by MVS
Production Flexibility Measurement and gauging / Robot guidance /
Prior operation verificationLess Machine Downtime and
Reduced Setup Time
Changeovers programmed in advance
More Complete Information
and Tighter Process Control
Manual tasks can now provide computer data
feedback
-
7/25/2019 150819 Intro to Machine Vision Slides
13/4913 | 2015 Cognex Corporation
Benefits of machine vision
Strategic Goal Machine Vision Applications
Lower Capital EquipmentCosts Adding vision to a machine improves itsperformance, avoids obsolescence
Lower Production Costs One vision system vs. many people / Detection
of flaws early in the process
Scrap Rate Reduction Inspection, measurement, and gauging
Inventory Control OCR and Identification
Reduced Floorspace Vision System vs. Operator
-
7/25/2019 150819 Intro to Machine Vision Slides
14/49
14 | 2015 Cognex Corporation
Poll question #2
What is your principal objective for attending this
webinar?
a. I am looking for a basic introduction to machine
vision
b. I want to know what kind of problems machinevision can solve
c. I want to know the basic components of a vision
system and understand how they work togetherd. I want to know which basic vision concepts I need
to master
-
7/25/2019 150819 Intro to Machine Vision Slides
15/49
Machine vision applications
-
7/25/2019 150819 Intro to Machine Vision Slides
16/49
16 | 2015 Cognex Corporation
Think: GIGI
Guidance Inspection Gauging Identification
-
7/25/2019 150819 Intro to Machine Vision Slides
17/49
17 | 2015 Cognex Corporation
Guidance
Determines part position (x, y, and angle)
Automates handling of parts for machines:
Alignment & Placement
2D & 3D Picking
Eliminates need for fixturing & improves robot
flexibility Vision tool alignment, fixturing
Locate at least one feature on a part for the
purpose of calculating the (x, y) position and
rotation of the part to position other vision tools
precisely
*First step in every vision application is to
find the part or features of interest
http://localhost/var/www/apps/conversion/tmp/scratch_7/Delta%20Robot%20-%20PackExpo%2003.mpg -
7/25/2019 150819 Intro to Machine Vision Slides
18/49
18 | 2015 Cognex Corporation
Trained Part
Out of focus
180 Rotation
Reversed Polarity Occlusion
Scale ChangeDim Lighting
Confusing Background
Geometric pattern matching
-
7/25/2019 150819 Intro to Machine Vision Slides
19/49
19 | 2015 Cognex Corporation
Part location challenges
Appearance changes
-
7/25/2019 150819 Intro to Machine Vision Slides
20/49
20 | 2015 Cognex Corporation
Part location challenges
Presentation / Distortion effects
2
-
7/25/2019 150819 Intro to Machine Vision Slides
21/49
21 | 2015 Cognex Corporation
Inspection
Broad category of vision applications:
Correct location Orientation
Skew
Quality
Defect Detection Surface Inspection
Contaminants
Completeness Fill Level
Feature Presence
Counting
Assembly Verification
-
7/25/2019 150819 Intro to Machine Vision Slides
22/49
22 | 2015 Cognex Corporation
Gauging
Precise dimensioning
Automated metrology and data recording
Ensure tolerances
Diameters, Gaps, Bushings, Threads, etc.
-
7/25/2019 150819 Intro to Machine Vision Slides
23/49
23 | 2015 Cognex Corporation
Identification
Read codes
Bar codes & 2-D Matrix
Labels & direct part mark
Read characters OCR / OCV
Recognize objects
Based on color, shape, or size
-
7/25/2019 150819 Intro to Machine Vision Slides
24/49
Types of machine vision systems
-
7/25/2019 150819 Intro to Machine Vision Slides
25/49
25 | 2015 Cognex Corporation
1-D machine vision
100% continuous web
inspection and classificationUses line-scan cameras
Materials inspected include:
Metals
Non-wovens
Plastics
Paper
-
7/25/2019 150819 Intro to Machine Vision Slides
26/49
26 | 2014 Cognex Corporation
2-D machine visionArea scan
480
768
1200
640 1024 1600
-
7/25/2019 150819 Intro to Machine Vision Slides
27/49
27 | 2014 Cognex Corporation
2-D machine visionLine scan
Built Image
Line Acquired
In-Sight
5604
Line Light
Conveyor
Belt
Movement
Encoder Shaft
Image is built line by line
Movement is neededRequires encoder to track movement
Short exposure times
-
7/25/2019 150819 Intro to Machine Vision Slides
28/49
28 | 2014 Cognex Corporation
Four reasons to use Line scan
1. Unwrap cylindrical objects for
inspection
2. Add vision to space-constrained
environments
3. Meet high-resolution inspection
requirements
4. Inspect objects in continuous
motion
-
7/25/2019 150819 Intro to Machine Vision Slides
29/49
29 | 2015 Cognex Corporation
3-D machine vision
-
7/25/2019 150819 Intro to Machine Vision Slides
30/49
Machine vision system components
f h
-
7/25/2019 150819 Intro to Machine Vision Slides
31/49
31 | 2014 Cognex Corporation
Key parts of a machine vision system
POWER
A-BALLEN-BRADLEY
INPUT
1
0
2
3
4
56
7
SLC5/04CPU
RUN
FLTBAT
FORC
DH+RS232
RUN REMPROG
INPUT
1
0
2
3
4
56
7
OUTPUT
1
0
2
3
4
56
7
Display
Inputs/Outputs: switches, PLCs, robots, lights
Light Source
Vision System
Vision Software
I/O
Comm.
CameraLens
i i ll h
http://www.sensource.biz/PDF/BR-Photoelectric.pdf -
7/25/2019 150819 Intro to Machine Vision Slides
32/49
32 | 2015 Cognex Corporation
Putting it all together
Camera
Monitor
Operator Pointing Device
(Trackball, Mouse, Touchscreen)
Parts
Light Source
Vision System
Output:
SerialParallel
ISA, PCI, VME bus
Input:
Serial
Parallel
ISA, PCI, VME bus
Lens
H h k
-
7/25/2019 150819 Intro to Machine Vision Slides
33/49
33 | 2015 Cognex Corporation
How the system works
3. Strobe is flashed to
illuminate part
2. Sensor detects part and sends a trigger to the vision system
1. Part arrives at inspection
station
4. Vision System acquires the image from the sensor.
5. Software algorithms running on vision system
performs image processing and/or image analysis
on acquired image
6. Vision system sends signal along a discrete output line
which activates a diverter if the part is bad
7. Operator can view rejected parts and ongoing statistics on display,
and can take system off-line if necessary
FAIL!
M hi i i l i h
-
7/25/2019 150819 Intro to Machine Vision Slides
34/49
34 | 2014 Cognex Corporation
Machine vision algorithms
Transforms raw numbers into
useful higher level features Raw numbers turned into edges, colors,
characters, and other characteristics
then makes decisions Returns answers such as position, similarity,
distance, presence, quality
All within just tens to hundreds of milliseconds!
P ll ti #3
-
7/25/2019 150819 Intro to Machine Vision Slides
35/49
35 | 2015 Cognex Corporation
Poll question #3
What would you say are the principal challenges to
implementing successful machine vision on yourassembly/production line?
a. The management of my organization does not realize thevalue of machine vision
b. Our line moves really fast and we have not found a vision
system that can keep up with itc. We have variable lighting and/or environmental conditions
that make it difficult to capture a consistent image
d. The conditions of the attributes we need to analyze (e.g.,codes, markings, etc.) are often so degraded that wecannot read them
e. None of the above
-
7/25/2019 150819 Intro to Machine Vision Slides
36/49
Machine vision terms
Vi i d fi iti
-
7/25/2019 150819 Intro to Machine Vision Slides
37/49
37 | 2014 Cognex Corporation
Vision definitions
Field of View (FOV)
The part which can be
seen by the machine
vision system at one
moment. The field of view
depends from the lens ofthe system and from the
working distance between
object and camera.
5 x 7
Fi ld f i
-
7/25/2019 150819 Intro to Machine Vision Slides
38/49
38 | 2014 Cognex Corporation
Field of view
What is my field of view?3
4
8
15
W ki di t d l ti
-
7/25/2019 150819 Intro to Machine Vision Slides
39/49
39 | 2014 Cognex Corporation
Working distance and resolution
Working Distance (WD)
Distance between the FRONTof
the lens and the target
Resolution
The minimum feature size ofthe object under inspection.
10
Workin Distan e and FOV are Interrelated
-
7/25/2019 150819 Intro to Machine Vision Slides
40/49
40 | 2014 Cognex Corporation
Working Distance and FOV are Interrelated
Depth of field
-
7/25/2019 150819 Intro to Machine Vision Slides
41/49
41 | 2014 Cognex Corporation
Depth of field
Depth of Field (DOF)
The distance in front of
and behind the object
which appears to be in
focus
3
More DOF with a small aperture
(high f/number) than with a
large aperture (low f/number)
-
7/25/2019 150819 Intro to Machine Vision Slides
42/49
Improving vision system performance
Different lens same image?
-
7/25/2019 150819 Intro to Machine Vision Slides
43/49
43 | 2014 Cognex Corporation
Different lens same image?
Lighting
Depth of field
Working distance
Line speed
Exposure time
Aperture
Budget
Lighting techniques
-
7/25/2019 150819 Intro to Machine Vision Slides
44/49
44 | 2015 Cognex Corporation
Lighting techniques
4
Bright Field
Dark FieldBack Lighting
Diffuse Dome
Axial Diffuse
Light can be structured in different ways. Angle and direction of the light
determine how the mark and space is seen by the camera.
Structured
To learn more about choosing the
right lighting go to Cognex.com >Resources > White Papers and
Articles
Optics
-
7/25/2019 150819 Intro to Machine Vision Slides
45/49
45 | 2015 Cognex Corporation
Optics
To learn more about choosing theright optics go to Cognex.com >
Resources > On-Demand Webinars
Filtering techniques
-
7/25/2019 150819 Intro to Machine Vision Slides
46/49
46 | 2015 Cognex Corporation
Filtering techniques
Control quality and quantity
of light
Block all unwanted
ambient lighting
Pass only the output of
lighting used for inspection
Increase contrast
and resolution
For more on optical filters, go toCognex.com > Resources > On-
Demand Webinars
Image pre processing tools
-
7/25/2019 150819 Intro to Machine Vision Slides
47/49
47 | 2015 Cognex Corporation
Image pre-processing tools
To learn more about image pre-processing, goto Cognex.com > Resources > On-Demand
Webinars
Summary
-
7/25/2019 150819 Intro to Machine Vision Slides
48/49
48 | 2014 Cognex Corporation
Summary
Make products better, faster, and less expensivelyGauging, Inspection, Guidance, and Identification are
the key applications
Key components are the lens, camera, lighting, visionsoftware and communications
Learn more about optics, lighting, filters and image pre-
processing to improve system performance
Dont go it aloneget help from experts!
-
7/25/2019 150819 Intro to Machine Vision Slides
49/49
Thank you for your time