Introduction to Artificial

Intelligence
Lecture 1
ECS4300/ECS3300-Artificial Intelligence and Computer Vision
Nuwan Vithanage
Introduction to the course
• LMS URL:
https://lms.sltc.ac.lk/course/view.php?id=535

• Office Hours:
Wednesday 03.00pm -06.00 pm (Online only – Appointment via email / Whatsapp)
Email: [email protected]

• Textbooks:
• Computer Vision and Image Processing: Fundamentals and Applications by Manas
Kamal Bhuyan
• Computer Vision: Algorithms and Applications by Richard Szeliski
Introduction to the course
• Grading
• Assignments, Labs and Quizzes : 20%
• Mid-semester : 20%
• End of the Semester Exam: 60%
• Total: 100%

• Mode of Delivery: Online

Why study Artificial Intelligence?

Search engines
Science

Medicine/
Diagnosis

Labor
What else?
Appliances
Honda Humanoid Robot

Walk

Turn

http://world.honda.com/robot/ Stairs
Sony AIBO

http://www.aibo.com
Natural Language Question Answering
What is Artificial Intelligence?
Acting Humanly: The Turing Test
• Let’s Alan Turing's 1950 article Computing Machinery and Intelligence
discussed conditions for considering a machine to be intelligent
• “Can machines think?” “Can machines behave intelligently?”
• The Turing test (The Imitation Game): Operational definition of intelligence.

• Computer needs to posses: Natural language processing, Knowledge

representation, Automated reasoning, and Machine learning
• Are there any problems/limitations e to the Turing Test?
What tasks require AI?
• “AI is the science and engineering of making intelligent machines which can
perform tasks that require intelligence when performed by humans …”

• Tasks that require AI:

• Solving a differential equation
• Brain surgery
• Inventing stuff
• Playing Jeopardy
• Playing Wheel of Fortune
• What about walking?
• What about grabbing stuff?
• What about pulling your hand away from fire?
• What about watching TV?
• What about day dreaming?
Acting Humanly: The Turing Test
• “Can machines think?” “Can machines behave intelligently?”
• The Turing test (The Imitation Game): Operational definition of intelligence

• Computer needs to posses: Natural language processing, Knowledge

representation, Automated reasoning, and Machine learning
• Problem: 1) Turing test is not reproducible, constructive, and amenable to
mathematic analysis. 2) What about physical interaction with interrogator
and environment?
• Total Turing Test: Requires physical interaction and needs perception and
actuation
What would a computer need to pass the Turing
test?
• Natural language processing: to communicate with examiner.
• Knowledge representation: to store and retrieve information
provided before or during interrogation.
• Automated reasoning: to use the stored information to answer
questions and to draw new conclusions.
• Machine learning: to adapt to new circumstances and to detect and
extrapolate patterns.
• Vision (for Total Turing test): to recognize the examiner’s actions and
various objects presented by the examiner.
• Motor control (total test): to act upon objects as requested.
• Other senses (total test): such as audition, smell, touch, etc.
Thinking Humanly: Cognitive Science
• 1960 “Cognitive Revolution”: information-processing psychology
replaced behaviorism

• Cognitive science brings together theories and experimental

evidence to model internal activities of the brain
• What level of abstraction? “Knowledge” or “Circuits”?
• How to validate models?
• Predicting and testing behavior of human subjects (top-down)
• Direct identification from neurological data (bottom-up)
• Building computer/machine simulated models and reproduce results (simulation)
Thinking Rationally: Laws of Thought
• Aristotle (~ 450 B.C.) attempted to codify “right thinking” What are correct
arguments/thought processes?
• E.g., “Socrates is a man, all men are mortal; therefore Socrates is mortal”

• Several Greek schools developed various forms of logic: notation plus rules
of derivation for thoughts.

• Problems:
• Uncertainty: Not all facts are certain (e.g., the flight might be delayed).
• Resource limitations: There is a difference between solving a problem in
principle and solving it in practice under various resource limitations such
as time, computation, accuracy etc. (e.g., purchasing a car)
Acting Rationally: The Rational Agent
• Rational behavior: Doing the right thing!
• The right thing: That which is expected to maximize the expected
return
• Provides the most general view of AI because it includes:
• Correct inference (“Laws of thought”)
• Uncertainty handling
• Resource limitation considerations (e.g., reflex vs. deliberation)
• Cognitive skills (NLP, AR, knowledge representation, ML, etc.)
• Advantages:
• More general
• Its goal of rationality is well defined
How to achieve AI?
• How is AI research done?
• AI research has both theoretical and experimental sides
• The experimental side has both basic and applied aspects.
• There are two main lines of research:
• One is biological, based on the idea that since humans are intelligent, AI
should study humans and imitate their psychology or physiology.
• The other is phenomenal, based on studying and formalizing common sense
facts about the world and the problems that the world presents to the
achievement of goals.
• The two approaches interact to some extent, and both should
eventually succeed. It is a race, but both racers seem to be walking
[John McCarthy]
How to achieve AI?
Branches of AI
• Logical AI
• Search
• Natural language processing
• pattern recognition
• Knowledge representation
• Inference From some facts, others can be inferred.
• Automated reasoning
• Learning from experience
• Planning To generate a strategy for achieving some goal
• Epistemology This is a study of the kinds of knowledge that are required for
solving problems in the world
Branches of AI
AI Pre-history
AI History
AI State of the art
• Have the following been achieved by AI?
• World-class chess playing
• Playing table tennis
• Cross-country driving
• Solving mathematical problems
• Discover and prove mathematical theories
• Engage in a meaningful conversation
• Understand spoken language
• Observe and understand human emotions
• Express emotions
Why do we process images?
• Acquire an image
• Correct aperture and color balance
• Reconstruct image from projections
• Prepare for display or printing
• Adjust image size
• Color mapping, gamma-correction, halftoning
• Facilitate picture storage and transmission
• Efficiently store an image in a digital camera
• Send an image from space
Why do we process images?
• Enhance and restore images
• Touch up personal photos
• Color enhancement for security screening
• Extract information from images
• Read 2D bar codes
• Character recognition
• Depth estimation
• Many more ...
Image Processing Examples
Image Processing Examples
Image Processing Examples
Image Processing Examples
Image Processing Examples
Image Processing Examples
Image Processing Examples
Image Processing Examples
Style Transfer
What is image processing?
• Process digital images by means of computer, it covers low-, mid-,
and high-level processes
• Low-level: inputs and outputs are images
• Noise removal, Image sharpening, Edge detection, Image transformation …etc
• Mid-level: outputs are attributes and/or images extracted from input images
• Object recognition, segmentation, motion and color detection ..etc
• High-level: an ensemble of recognition of individual objects
• Scene understanding, autonomous navigation
Why study Computer Vision?
• Images (and movies) have become important in both production and
consumption
• Therefore applications to manipulate images(movies) are becoming
core
• As are systems that extract information from imagery
• Surveillance
• Building 3D representations
• Motion capture assisted
• But most of all… It is a really cool set of problems!
Every picture tells a story

• Goal of computer vision is to

write computer programs that
can interpret images
Making sense of a picture
• We want to extract meaning out of an
image/sequence of images
• This is different from image
processing, which is mainly concerned
with transforming images
• Image processing operations such as
blurring, thresholding etc… are often
used as part of computer vision
algorithms
Making sense of a picture

• What items could you identify? How

did you recognize them?
• What about other objects/spaces/time
of day etc.?
Computer Vision
Computer Vision

• Low Level Vision

• Measurements
• Enhancements
• Region segmentation
• Features
Computer Vision
• Measurement
Brightness
Computer Vision
• Measurement
Length
Computer Vision
• Image Enhancement
Computer Vision
• Region Segmentation
Computer Vision

• Mid Level Vision

• Reconstruction
• Depth calculation
• Motion Estimation
Computer Vision
• Reconstruction
Computer Vision
• Reconstruction
Google’s 3D Maps Structure estimation from tourist photos
Computer Vision
• Reconstruction
Apple’s 3D maps

http://www.youtube.com/watch?v=InIVv-LsgZE
Computer Vision

• High Level Vision

• Category detection
• Activity recognition
• Deep understandings
• Pose estimation
Computer Vision
• Category detection
Face detection
Computer Vision
• Activity recognition
Vision-based interaction: Xbox Kinect
Why vision is so hard?
• Challenges 1: view point variation
Why vision is so hard?
• Challenges 2: illumination
Why vision is so hard?
• Challenges 3: occlusion
Why vision is so hard?
• Challenges 4: scale
Why vision is so hard?
• Challenges 5: background clutter
Why vision is so hard?
• Challenges 6: object intra-class variation
Why vision is so hard?
• Challenges 7: local ambiguity
Summary
• We have looked at:
• Why do we process images?
• What is image processing?
• Why study Computer Vision?
• Why vision is so hard?
• Next time we will start to see the representation of digital image and
key digital image processing techniques