MTE 520 MACHINE VISION

INTRODUCTION

-
#1 lec # 8 Fall 2003 10-8-
 WHAT IS MACHINE VISION?

Machine vision is a field where sensors, cameras,

processing hardware and software algorithms are used to
automate visual inspection tasks thereby precisely guiding a
handling equipment during product assembly.

Machine vision systems rely on digital sensors usually

protected inside industrial cameras with specialized optics to
acquire images, so that computer hardware and software can
process, analyze, and measure various characteristics that will
determine decision making.
-
#2 lec # 8 Fall 2003 10-8-
 AN ANALOGY FOR MACHINE VISION?
• Machine Vision is like a “photoeye” which has only two states on or off. The
photoeye is one of the most basic sensors in industrial automation.
• The principal idea behind a photoeye is it emits a beam of light and detects
if that light is being reflected off some object.
• If the object is not present, no light reflects back into the photoeye’s
receiver.
• If an object is present, the signal turns on and can be used in a control
system to make something happen. If the object is removed, the signal
turns off.

-
#3 lec # 8 Fall 2003 10-8-
 HOW DO MACHINE VISION SYSTEMS WORK?

Basically, the way a machine vision system works

can be simplified into a three-step process:
a. Image capturing with camera and sensors and
lighting.
b. Processing of captured images.
c. Taking action based on the processing

-
#4 lec # 8 Fall 2003 10-8-
HOW DO MACHINE VISION SYSTEMS WORK?-2

-
#5 lec # 8 Fall 2003 10-8-
 IMAGE CAPTURING

Step 1: Image Capturing

The system can automatically capture images through
one /multiple instances, ultraviolet or infrared cameras
during the production process.

-
#6 lec # 8 Fall 2003 10-8-
 IMAGE PROCESSING

Step 2: Processing
Analyzing the captured image by using customized algorithms.
[verification, identification, gauging, counting, classification …etc].

-
#7 lec # 8 Fall 2003 10-8-
 TAKING ACTION
Step 3: Action
The system takes an action based on the analyzing step.

-
#8 lec # 8 Fall 2003 10-8-
 ANOTHER REPRESENTATION
A basic machine vision system.
The target is lit as it moves across the camera’s field of view, and the
data is transferred to the vision processing system.

-
#9 lec # 8 Fall 2003 10-8-
 ANOTHER REPRESENTATION-2
.AN INSPECTION SYSTEM
An inspection system not only visually inspects the target, but feeds the
acquisition system to react based on the scanned information. Objects
that don’t meet specifications are rejected from the assembly line.

-
#10 lec # 8Fall 2003 10-8-
 “STAGING” IN INSPECTION SYSTEM
• The first, and questionably most crucial, step in building an
inspection system is positioning or “staging”
.
• This is the determination of how a subject will be positioned in
front of the camera for imaging.

• No amount of processing can recover information that a sensor

did not capture at the scene.

• Figuring out how objects will be delivered to the camera and

sensor can also be the toughest part of machine vision design.

-
#11 lec # 8Fall 2003 10-8-
 CATEGORIES OF VISION SYSTEMS

Broadly speaking, there are 3 categories of

machine vision systems: 1D, 2D and 3D.

-
#12 lec # 8Fall 2003 10-8-
 1D SYSTEM
1D vision systems scan one line at a time, instead of looking at
the whole picture at once, while the process moves. In the example
below, a defect in the sheet is detected. This technique commonly
detects and classifies defects on materials manufactured in a
continuous process, such as paper, metals, plastics, and other non-
woven sheet or roll goods.

-
#13 lec # 8Fall 2003 10-8-
 2D SYSTEM

2D vision systems can produce

images with different resolutions
as shown in Figure 1
Fig. 1
Another 2D system uses line scan techniques but builds the 2D image
from the line scans one line at a time as shown in figure 2

Fig. 2
 3D SYSTEMS
3D machine vision systems typically comprise multiple cameras or one or more
laser displacement sensors.
These systems involve multiple cameras mounted at different locations and
“triangulation” on an objective position in 3-D space. (Fig. a)

Another alternative used in 3D laser displacement sensor is to use one camera but
whose location is varied . A height map is generated from the displacement of the
reflected lasers’ location on an object. (Fig. b)

Fig. a. 3D vision system employing multiple Fig. b. 3D vision system employing -

cameras. moveable single camera
#15 lec # 8Fall 2003 10-8-
 COMPARING LINE SCANS AND AREA SCANS
. Understanding the advantages of scan systems
• In certain applications, line scan systems have specific advantages
over area scan systems.
For example, inspecting round or cylindrical parts may require multiple
area scan cameras to cover the entire part surface.
• However, rotating the part in front of a single line scan camera
captures the entire surface by unwrapping the image.
• Line scan systems fit more easily into tight spaces for instances when
the camera must peek through rollers on a conveyor to view the
bottom of a part. Line scan systems can also generally provide much
higher resolution than traditional cameras.
• Since line scan systems require parts in motion to build the image,
-
they are often well-suited for products in continuous motion.
#16 lec # 8Fall 2003 10-8-
 MOST COMMON USAGE OF MACHINE VISION
. Most Common areas of Usage of Machine Vision are in
• Measurement
• Counting
• Location
• Decoding

-
#17 lec # 8Fall 2003 10-8-
 1. MEASUREMENT

E.g. measuring the gap in spark plugs

-
#18 lec # 8Fall 2003 10-8-
 2. COUNTING
E.G.
a. Counting no. of parts b. Counting no of features on a part

c. Checking absence or presence

-
#19 lec # 8Fall 2003 10-8-
 3. LOCATION AND ORIENTATION
• This is to report the location and orientation, gap or alignment
of a part.
• Machine vision systems can locate the position and orientation
of a part, compare it to a specified tolerance, and ensure it’s
at the correct angle to verify proper assembly.
• Location sensing can be used to report the location and
orientation of a part in 2D or 3D space to a robot or machine
controller, allowing the robot to locate the part or the machine
to align the part.

• Location guidance can also be used for alignment to other

machine vision tools.
-
#20 lec # 8Fall 2003 10-8-
 3. LOCATION AND ORIENTATION-2

Alignment Check Gap Check

– Looking for a unique pattern to identify part -

#21 lec # 8Fall 2003 10-8-
 4. DECODING
Decoding e.g. bar codes

Parts Verification Decoding Checking bar codes on cans

-
#22 lec # 8Fall 2003 10-8-