Introduction to Artificial

Intelligence
CT098-3-M Ver 1.0

Computer Vision
 Topic & Structure of the Lesson

• What is Computer Vision?

• How Does Computer Vision Work?
• What are Computer Vision Applications?
• What are the Challenges of Computer
Vision?
• Computer Vision Applications

Module Code and Module Title Title of Slides Slide ‹#› of 13

Module Code and Module Title Title of Slides Slide ‹#› of 13
 Computer Vision

• Can analyses images and videos to produce the desired

results in real time
• Computer vision is a branch of artificial intelligence that
enables computers to see and identify images,
processing them as humans would.
• Using images from cameras and videos, deep learning
models enable machines to accurately identify and
classify the objects.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 How Does Computer Vision
Work?
• computer vision is a more high-level process. It deals
with the analysis of an image.
• the input is an image while the output is the
interpretation of an image.
• Computer vision works by identifying different
components in the image.

• What is Computer Vision?

https://www.youtube.com/watch?v=xXgnmKcnyTg
How is it to work?
• https://www.youtube.com/watch?
v=OcycT1Jwsns&t=117s
Module Code and Module Title Title of Slides Slide ‹#› of 13
 Essential – 5 stages

1. image acuquistion – digitization

2 .Signal Processing
3. edge detection
4. Object recognition (pattern matching)
5. Image understanding

Module Code and Module Title Title of Slides Slide ‹#› of 13

Module Code and Module Title Title of Slides Slide ‹#› of 13
 Components are then analysed.

• A simple application sees computer vision identifying the

edges in an image.
• Computer vision enables pattern recognition or shapes
to be identified.
• More advanced applications allow for animals or people
to be recognised.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 What are Computer Vision
Applications?
• Applications of computer vision range from automation in
self-driving vehicles to developing accurate
• facial recognition software to inspecting bottles in a
manufacturing production line to controlling robots, to
organizing information for example indexing databases
of images.
• China using face recognition systems
• https://www.youtube.com/watch?v=pNf4-d6fDoY
• Next-Level Surveillance: China Embraces Facial
Recognition
• https://www.youtube.com/watch?v=Fq1SEqNT-7c

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Other areas

• Augmented and mixed reality technologies are

increasingly being implemented in smartphones and
tablets.

• Additionally, smart glasses are also becoming more

widely available.

• All of this requires computer vision to help determine the

location, detect objects and establish the depth or
dimensions of the virtual world.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Why country using face
recognition
• China using face recognition systems
• https://www.youtube.com/watch?v=pNf4-
d6fDoY
• Next-Level Surveillance: China Embraces
Facial Recognition
• https://www.youtube.com/watch?v=Fq1SE
qNT-7c

Module Code and Module Title Title of Slides Slide ‹#› of 13

 How China use to fight corona?

• Biggest country that uses face recognition

system is china

• https://www.youtube.com/watch?
v=1MLGQL5pbbM&t=125s

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Image Processing

• Image processing transformations such as

sharpening, smoothing , stretching and
contrasting on an image

• https://www.youtube.com/watch?v=9-8Js6
2wzQs&t=24s

Module Code and Module Title Title of Slides Slide ‹#› of 13

Module Code and Module Title Title of Slides Slide ‹#› of 13
 Computer Vision & Image
Processing
• Using both in retail healthcare and many other industries
has delivered positive results
• These technologies can evolve business operations that
include visual aspect.
• These technologies can simply business process like
quality control , inventory management and medical
imaging
• But companies must be aware of their difference to use
them wisely

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Computer vision in these 3 industries

• Applications of computer vision range from helping in

medical diagnostics and inspecting products for quality
control to optimizing crop yields and monitoring livestock
health, showcasing the promise of the technology.

• Computer vision includes three steps –

1.capturing images/videos in real-time,
2 .processing the acquired content machine learning
3 . taking actions based on processing results

Module Code and Module Title Title of Slides Slide ‹#› of 13

Module Code and Module Title Title of Slides Slide ‹#› of 13
 Retailers - 1

• Introducing Amazon Go and the world’s most advanced

shopping technology
https://www.youtube.com/watch?time_continue=2&v=NrmM
k1Myrxc&feature=emb_logo

Computer vision plays an important role in facial recognition,

cashierless stores, inventory visibility, and visual search, four vital
areas retailers are already putting the technology to work in.

The Go stores use a mix of next-gen technology, with computer vision

at the forefront, to track customer movement in the store (thanks to
hundreds of camera strategically placed throughout) and recognize
when a product is selected and charge the customer’s account when
they exit the store.
Module Code and Module Title Title of Slides Slide ‹#› of 13
 Retailer - 2

• Savvy retailers are turning to robotics powered by

computer vision technology to take over mundane store
monitoring tasks.
• By deploying robots at the store level tasked with
scanning shelves for both inventory and product
compliance retailers can not only free up associates for
customer-facing tasks, but they can greatly improve
inventory accuracy.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 CaliBurger uses facial recognition software to identify registered customers and
pull up their loyalty information. – Retailer 3

Visual Search at eBay – Retailer - 4

https://www.youtube.com/watch?v=iYtjs32vh4g

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Conclusion Retailer

• As retailers search for solutions to blur the lines between

physical and digital retail, computer vision fits the bill. In
addition, whether it’s in self-driving vehicles making
deliveries, robots taking inventories,
• AI-driven security scans, or robots frying up tater tots to
help humans avoid hot oil injuries, computer vision is an
essential part of digitizing the retail workforce as well.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Healthcare

• Digital technology helps the healthcare industry to

precisely diagnose and treat diseases, helping patients
to recover quickly. One such technology, computer
vision, is set to revolutionize the way hospitals have
been diagnosing and treating their patients
• Research reading
https://www.winniepalmerhospital.com/content-hub/winnie-
palmer-hospital-launches-invests-in-new-ai-technology-to

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Healthcare - 2

• Research in Focus: Project InnerEye –

Assistive AI for Cancer Treatment
• https://www.youtube.com/watch?
v=jaFTXi56bFI

Module Code and Module Title Title of Slides Slide ‹#› of 13

Module Code and Module Title Title of Slides Slide ‹#› of 13
 Is computer vision really AI?

• ability to learn : YES - some systems are able to improve their

recognition capability with time - the more "trees" they see examples
of, the more likely they are to recognise another "tree" in the future;
• use of language : NO
• vision : obviously YES!
• problem solving : NO - although the purpose of vision systems is to
make it possible for computer systems to operate in problem-solving
environments independently of humans;
• adapting to new situations : YES - the ideal vision system would be
able to cope with completely unfamiliar scenes, just as the human
eye and brain can.

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Tutorial

1)How is an image captured in vision system?

2)What features of vision system enable them to recognize image
3)How are artificial neural systems used with vision system?
4)What advantages do vision systems bring to the production line?
5)Describe a military use of vision systems
6)How are vision systems used with expert system in the analysis of
satellite images?
7)How can vision systems combine with expert systems to help in the
field of medicine

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Research

• Look for articles how this AI area used in

the industry you are working in

• 1 hour – present your idea and opinion

Module Code and Module Title Title of Slides Slide ‹#› of 13

 Question and Answer Session

Q&A

Module Code and Module Title Title of Slides Slide 18 of 19