Department of Electronics and Communication
Engineering
Unit 1 – Introduction to Machine Vision
Mr.A.Shafeek, AP/ECE
Dr.MCET,Pollachi
1
Unit I: Introduction To Machine Vision
The nature of vision - tasks for a vision system –
The image: representations and properties -
mathematical and physical background - Data
structures for image analysis - Basic Image
Filtering Operations
Department of ECE Introduction to MVS 2
Course Outcome(CO)
CO1: Describe the fundamental concepts in machine vision
systems by studying the fundamental concepts of image
representation and its properties
Learning Outcome(LO)
LO1: Understand the concept of Machine Vision
Department of ECE Introduction to MVS 3
The nature of Vision
Image processing is a signal processing task that transforms an
input image into a more desirable output image through processes
such as noise reduction, contrast enhancement and registration
Pattern recognition is a classification task that classifies images
into predetermined categories.
Machine vision can be defined as a scientific field that extracts
information out of digital images. The type of information gained
from an image can vary from identification, space measurements for
navigation, or augmented reality applications.
Or
Machine vision is building algorithms that can understand the
content of images and use it for other applications
Introduction to MVS 4
Understanding human vision
Definition of vision
Vision comes down to two components
1) sensing device
2) interpreting device
How good is the human visual system?
Speed
Fooling humans
Lessons from nature
Introduction to MVS 5
Understanding human vision
Extracting information from images
Information gained from images in Machine vision is divided in
two categories:
measurements
semantic information
Introduction to MVS 6
Applications
Applications of computer vision
Special effects
3D urban modeling
Scene recognition
Face detection
Optical Character Recognition
Mobile visual search
Self-driving cars
Automatic checkout
Vision-based interaction Augmented Reality Virtual Reality
Introduction to MVS 7
The components of a typical
machine vision system
Introduction to MVS 8
The components of a typical
machine vision system
Introduction to MVS 9
Benefits of MVS
Strategic Goals Application
Higher Quality Inspection, Measurement, Gauging
and Assembly verification
Increased Productivity Automatic Repetitive testing
Lower production cost One vision system Vs Many human
Reduced floor space Operator space
Continuous process control Repeatability
Inventory control Recognition and identification
Prevent human contamination Clean rooms
Protect human workers Hazardous environment
Introduction to MVS 10
Challenges of MVS
Appearance Changes due to lighting Part pose distortion
Introduction to MVS 11
Types of MVS
1D vision system
2D vision system
3D vision systems
Introduction to MVS 12
1D vision system
Scan one line at a time instead of
looking all the area
This technique can be used to
identify defects on materials
manufactured in continuous
process like
Paper
Metal
Plastics etc.,
Introduction to MVS 13
2D vision system
Line scan systems have
cameras perform area scans that
involve capturing 2D snapshots in specific advantages
various resolutions over area scan systems
unwrap cylindrical
objects for inspection
add vision to space-
constrained
environments
meet high-resolution
inspection
requirements
inspect objects in
Introduction to MVS
continuous14motion
3D vision system
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
Introduction to MVS 15
Image Types
Binary Images
Grayscale Images
Color Images
Introduction to MVS 16
Sampling and Resolution
Resolution is a sampling parameter, defined in dots per inch (DPI).
The standard DPI value for screens is 72 DPI.
Pixels are quantized (i.e, all pixels (or channels of a pixel) have one
of a set numbers of values (usually [0, 255]). Quantization and
sampling loses information due to a finite precision.
Introduction to MVS 17
Image Formation
Introduction to MVS 18
Image Representation
Introduction to MVS 19
Image Formation Model
Introduction to MVS 20
Reference(s)
1. Carsten Steger, Markus Ulrich, and Christian Wiedemann,
” Machine Vision Algorithms and Applications” Wiley-VCH;
1 edition (2007)
2. E.R.DAVIES, Computer and Machine Vision: Theory,
Algorithms,Practicalities, Academic Press(2012).
Department of ECE Introduction to MVS 21
Thank you
Department of ECE Introduction to MVS 22
