0% found this document useful (0 votes)
12 views49 pages

Lec 1

Uploaded by

Ruby 2020
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
12 views49 pages

Lec 1

Uploaded by

Ruby 2020
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 49

CHAPTER 1:

INTRODUCTION

Department of Technology
Faculty of Electronic & Computer
Technology and Engineering
Technology Campus
Updated : 2023
Contents
• Outline:
– Machine vision
– Machine vision application
– Advantage of machine vision
– Digital image processing
– History of digital image processing
– Key stages in digital image processing
Machine Vision
– multidisciplinary field of artificial intelligence (AI) and computer science
that focuses on enabling computers and machines to interpret and
understand visual information from the world, just as humans do with
their eyes and brains.
– use digital cameras and image processing algorithms to extract
meaningful information and make decisions based on that information.
Key Aspect and Application
– Image Acquisition: Using digital cameras or other optical sensors.
These devices capture visual data, such as photographs, videos, or scans,
from the real world.
– Image Processing and Analysis: To enhance, filter, and preprocess the
data. These processes include noise reduction, image segmentation
(dividing an image into meaningful parts), feature extraction, and more.
– Pattern Recognition: To recognize patterns, objects, shapes, and
structures within images. This involves training algorithms to identify
specific objects or characteristics based on predefined criteria. Pattern
recognition can be used for tasks like facial recognition, object tracking,
and defect detection in manufacturing.
– Machine Learning: Incorporate machine learning techniques, such as
deep learning, to improve their ability to recognize and interpret
complex patterns. Convolutional neural networks (CNNs) are commonly
used for tasks like image classification and object detection
Key Aspect and Application
– 3D Vision: These systems can create three-dimensional representations
of objects or environments, which can be useful in robotics, autonomous
vehicles, and augmented reality applications.
– Applications: Manufacturing, healthcare, automotive, agriculture,
security, robotics, and more. Examples include quality control in
manufacturing, medical image analysis, autonomous navigation, and
facial recognition in security systems.
– Quality Control: Inspect products for defects, measure dimensions, and
ensure consistency in production processes.
– Automation: Plays a crucial role in industrial automation. It enables
robots and automated systems to perceive and interact with their
environment, making tasks like pick-and-place operations, sorting, and
assembly more efficient.
Machine Vision Application
MEASUREMENT - The gap in spark plugs:
• It has to be a certain width for optimal performance of the vehicle;
therefore it is a critical specification of the part. Each spark plug gap can
be immediately checked against pre-defined tolerances (in the region of
0.1mm). Measuring by machine eliminates the need for a human to be
there, measuring and adjusting manually. Machine vision does it more
quickly and accurately.
Machine Vision Application
COUNTING
• This simply means looking for a number of parts or features on a part. This
allows us to locate missing features quickly and assure that products are
assembled properly. A variation on the theme is the ability to check for
the absence or presence of an item.
Machine Vision Application
LOCATION
• In regards to machine vision location means the ability to check position
and orientation of a part, and then make sure that is immediately checked
to specified tolerances.
Machine Vision Application
INSPECTION
Machine Vision Architecture
Machine Vision System
Advantage of Machine Vision
Automation
• Automating tasks that require visual inspection or interpretation. It
reduces the need for human intervention in repetitive, time-
consuming, and labour-intensive processes.
Consistency
• Provide consistent and repeatable results, eliminating the
variations and errors that can occur with human visual inspection.
This consistency is crucial in manufacturing and quality control.
Speed
• process and analyze visual data much faster than humans. This
speed is valuable in applications where real-time decision-making
or rapid inspection is required.
Advantage of Machine Vision
Accuracy
• Machine vision systems can achieve high levels of accuracy and
precision in measurements, identification, and defect detection.
This is particularly important in industries like electronics
manufacturing and pharmaceuticals.
Cost Savings
• By automating visual inspection and quality control processes,
organizations can reduce labor costs and increase efficiency. Fewer
defects and errors also lead to cost savings by minimizing waste
and rework.
Non-Invasive
• Machine vision is non-invasive, meaning it can inspect objects and
materials without physical contact. This is advantageous in
industries where maintaining the integrity of the inspected items is
critical, such as medical imaging.
Advantage of Machine Vision?
Increased Throughput
• Machine vision systems can significantly increase production
throughput by rapidly inspecting and sorting items. This is
beneficial in manufacturing lines with high production volumes.
Improved Quality
• Machine vision systems can detect defects and inconsistencies that
might be challenging for the human eye to identify. This leads to
higher product quality and reduced customer complaints.
24/7 Operation
• Machine vision systems can operate continuously, 24/7, without
the need for breaks, making them suitable for applications that
require round-the-clock monitoring and inspection.
Advantage of Machine Vision
Data Logging and Analysis
• Machine vision systems can collect and log large amounts of data
about the items they inspect. This data can be analyzed to gain
insights into the manufacturing process and make improvements.
Complex Tasks
• Machine vision systems can perform complex visual tasks that may
be beyond the capabilities of human operators, such as recognizing
intricate patterns or analyzing large datasets.
Safety
• In hazardous environments or situations where human safety is a
concern, machine vision can be used to perform tasks without
exposing humans to risks.
Digital Image Processing
• Digital Image Processing – Processing a given input
image to obtain a desired output image.
• focuses on the manipulation, enhancement, analysis,
and interpretation of digital images using computer
algorithms and mathematical techniques.
• It focuses on two major tasks
1. Improvement of pictorial information for human
interpretation
2. Processing of image data for storage, transmission and
representation for autonomous machine perception
Key benefits of managing images digitally
1. Ease of Storage and Accessibility:
– Digital images can be stored on various devices, such as computers,
external hard drives, cloud storage, and servers. This makes it convenient to
store, organize, and access images from anywhere with an internet
connection.
2. Space Efficiency:
– Digital images take up less physical space compared to printed photographs,
albums, and slides. This allows for a more extensive collection of images
without the need for large physical storage areas.
3. Durability and Preservation:
– Digital images can be preserved for an extended period without the
degradation that physical prints may experience due to fading, wear, or
damage. When properly stored and backed up, digital images can last
indefinitely.
Key benefits of managing images digitally
4. Search and Retrieval:
– Digital image management software often includes powerful search and
tagging features, making it easier to locate specific images. This is especially
useful when dealing with large collections.
5. Editing and Enhancement:
– Digital images can be edited, enhanced, and retouched easily using image
editing software. This allows for improvements in image quality, the
removal of imperfections, and creative adjustments.
6. Sharing and Distribution:
– Digital images can be easily shared with others via email, messaging apps,
social media, or online galleries. This simplifies the process of sharing
memories or professional work with friends, family, or colleagues.
Key benefits of managing images digitally
7. Collaboration:
– In professional settings, digital image management enables collaboration
among team members. Multiple people can access, edit, and work on the
same images, which is particularly valuable in industries like graphic design
and photography.
8. Security and Backup:
– Digital images can be protected with encryption and password security.
Additionally, regular backups can be set up to ensure image collections are
safeguarded against data loss.
9. Metadata and Organization:
– Digital images allow for the inclusion of metadata such as dates, locations,
and descriptions. This metadata enhances organization and provides
valuable context to the images.
Key benefits of managing images digitally
10. Versatility:
– Digital images can be easily converted to different formats or resolutions for
various uses, such as web publishing, printing, presentations, or archiving.
11.Remote Access:
– With cloud storage, digital images can be accessed remotely from different
devices, providing flexibility and convenience for viewing and sharing
images on the go.
12.Integration with Multimedia:
– Digital images can be integrated into multimedia presentations, websites,
and multimedia projects, allowing for more dynamic and engaging content.
Key benefits of managing images digitally

The digital nature of images makes them


highly amenable to processing and analysis
using computer systems and processors.
Digital Image Processing
• The continuum from image processing to
computer vision can be broken up into low-, mid-
and high-level processes
Image Processing Image Analysis Computer Vision
(Low Level Process) (Mid Level Process) (High Level Process)
Input: Image Input: Image Input: Attributes Output:
Output: Image Output: Attributes ( Understanding
features, texture,
Examples: Noise shape.) Examples: Scene
removal, image understanding,
sharpening Examples: Object autonomous navigation
recognition, (face, fingerprint, Tracking
segmentation moving object etc.)

In this course we will stop here


History of Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

• Early 1920s: One of the first applications of


digital imaging was in the news-
paper industry
– The Bartlane cable picture
transmission service Early digital image

– Images were transferred by submarine cable


between London and New York
– Pictures were coded for cable transfer and
reconstructed at the receiving end on a telegraph
printer
History of DIP (cont…)
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

• Mid to late 1920s: Improvements to the


Bartlane system resulted in higher quality
images
– New reproduction
processes based
on photographic
techniques
– Increased number Improved
of tones in digital image Early 15 tone digital
image
reproduced images
History of DIP (cont…)
• 1960s: Improvements in computing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

technology and the onset of the space race


led to a surge of work in digital image
processing
– 1964: Computers used to
improve the quality of
images of the moon taken
by the Ranger 7 probe
– Such techniques were used
in other space missions A picture of the moon taken
by the Ranger 7 probe
including the Apollo landings minutes before landing
History of DIP (cont…)
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

• 1970s: Digital image processing begins to be


used in medical applications
– 1979: Sir Godfrey N.
Hounsfield & Prof. Allan M.
Cormack share the Nobel
Prize in medicine for the
invention of tomography,
the technology behind
Computerised Axial Typical head slice CAT
Tomography (CAT) scans image
History of DIP (cont…)
• 1980s - Today: The use of digital image
processing techniques has exploded and they
are now used for all kinds of tasks in all kinds
of areas
– Image enhancement/restoration
– Artistic effects
– Medical visualisation
– Industrial inspection
– Law enforcement
– Human computer interfaces
Examples: Image Enhancement
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

• One of the most common uses of DIP


techniques: improve quality, remove noise etc
Examples: The Hubble Telescope
• Launched in 1990 the Hubble
telescope can take images of
very distant objects
• However, an incorrect mirror
made many of Hubble’s
images useless
• Image processing
techniques were
used to fix this
Examples: Artistic Effects
• Artistic effects are
used to make
images more
visually appealing,
to add special
effects and to make
composite images
Examples: Medicine
• Take slice from MRI scan of canine heart, and
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

find boundaries between types of tissue


– Image with gray levels representing tissue density
– Use a suitable filter to highlight edges

Original MRI Image of a Dog Heart Edge Detection Image


Examples: GIS
• Geographic Information Systems
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

– Digital image processing techniques are used


extensively to manipulate satellite imagery
– Terrain classification
– Meteorology
Examples: Industrial Inspection
• Human operators are
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

expensive, slow and


unreliable
• Make machines do the
job instead
• Industrial vision systems
are used in all kinds of
industries
• Can we trust them?
Examples: PCB Inspection
• Printed Circuit Board (PCB) inspection
– Machine inspection is used to determine that all
components are present and that all solder joints are
acceptable
– Both conventional imaging and x-ray imaging are used
Examples: Law Enforcement
• Image processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

techniques are used


extensively by law
enforcers
– Number plate
recognition for speed
cameras/automated toll
systems
– Fingerprint recognition
– Enhancement of CCTV
images
Examples: HCI
• Try to make human computer
interfaces more natural
– Face recognition
– Gesture recognition
• Does anyone remember the
user interface from “Minority
Report”?
• These tasks can be extremely
difficult
Image Processing Techniques
• Image Enhancement
– Brings out detail that is obscured or simply highlights certain
features of interest in a image.
– A familiar example of enhancement is increasing the contrast
of an image.
• Image Restoration
– Attempts to reconstruct or recover an image that has been
degraded by using a priori knowledge of the degradation
phenomenon.
• Image Compression
– Deals with techniques for reducing the storage required to save
an image or the bandwidth required to transmit it.
Image Analysis Task
• Image Segmentation
– Concerned with procedures that partition an image into its
constituent parts or objects.
• Image Representation and Description
– Converts the output of a segmentation stage to a form suitable
for computer processing. Also call feature selection, deals with
extracting attributes that result in some quantitative
information of interest or a basic for differentiating one class of
objects from another.
• Image Recognition
– Process that assigns a label to an object based on its
descriptors.
Key Stages in Digital Image Processing

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
Key Stages in Digital Image Processing
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain
& Description
Colour Image Image
Processing Compression
THE END

You might also like