Intro to Computer Vision

By: Assistant Professor Dr. Ali R Hasoon

CSD-CCS&IT-UOK 2025-2026
Semester Description
• Recognize and describe both the theoretical and practical
aspects of computing with images. Connect issues from
Computer Vision to Human Vision.
• Describe the fundamentals of image formation and image
analysis. Understand the basics of 2D and 3D Computer
Vision.
• Become familiar with the recent and common technical
approaches involved in computer vision.
References:
Main Textbooks:
• Rick Szeliski, Computer Vision: Algorithms and Applications 2nd edition.

• Scott Krig, Computer Vision Metrices: Survey, Taxonomy, and Analysis.

• th edition.
Why study Computer Vision?
• One can the (and avoid bad things...)!
• Images and movies are everywhere; fast-growing collection of
useful applications building representations of the 3D world
from pictures automated surveillance doing what)
movie post-processing face finding
Greater understanding of human vision.
Various deep and attractive scientific mysteries how does
object recognition work.
Some of the latest CV technology
(a) optical character recognition (OCR),
(b) mechanical inspection,
(c) warehouse picking,
(d) medical imaging,
(e) self-driving cars,
(f) drone-based photogrammetry.
History of Computer Vision
Some early examples of computer vision algorithms
Examples of computer vision algorithms from 1980s
Examples of computer vision algorithms from 1990s
Examples of computer vision algorithms 2000s
Examples of computer vision algorithms 2010s
Every image tells a story
• Goal of computer vision:

the picture
• Compute properties of the
world
– 3D shape
– Names of people or objects
– What happened?
The goal of computer vision
Can computers match human perception?
• Yes and no (mainly no)
– computers can be better at

–
things

• But huge progress

– Accelerating in the last five
years due to deep learning
–
changing
 Current models still make very silly mistakes

[Tomer Ullmann, The Illusion-Illusion: Vision Language Models See Illusions Where There are None, arXiv 2024]
Human perception has its shortcomings

[Link]
Humans can tell a lot about a scene from a little
The goal of computer vision
The goal of computer vision
• Compute the 3D shape of the world

ZED 2i Camera
The goal of computer vision
• Recognize objects and people

Terminator 2, 1991
slide credit: Fei-Fei, Fergus & Torralba
 sky
building

flag

face
banner
wall
street lamp
bus bus

cars slide credit: Fei-Fei, Fergus & Torralba

The goal of computer vision
•
The goal of computer vision
• Forensics

Source: Nayar and Nishino, “Eyes for Relighting”

Source: Nayar and Nishino, “Eyes for Relighting”
Source: Nayar and Nishino, “Eyes for Relighting”
April 10, 2019
The goal of computer vision
•

Super-resolution (source: 2d3)

Low-light photography
(credit: Hasinoff et al., SIGGRAPH ASIA 2016)

Inpainting / image completion

Depth of field on cell phone camera (image credit: Hays and Efros)
(source: Google Research Blog)
Why study computer vision?
• Billions of images/videos captured per day

• Huge number of potential applications

• The next slides show the current state of the art
Optical character recognition (OCR)
If you have a scanner, it probably came with OCR software

License plate readers

[Link]
[Link]

Sudoku grabber
[Link]

Automatic check processing

Face detection

• Nearly all cameras detect faces in real time

– (Why?)
Face analysis and recognition
Vision-based biometrics

Source: S. Seitz
Who is she?
Vision-based biometrics

How the Afghan Girl was Identified by Her Iris Patterns story

Source: S. Seitz
Login without a password

Fingerprint scanners on
most of the new Face unlock
smartphones
New York Times, Jan. 18, 2020
by Kashmir Hill
Bird identification

Merlin Bird ID (based on Cornell Tech technology!)

Special effects: shape capture

The Matrix movies, ESC Entertainment, XYZRGB, NRC

Source: S. Seitz
Special effects: motion capture

Pirates of the Carribean, Industrial Light and Magic Source: S. Seitz

3D face tracking w/ consumer cameras

Snapchat Lenses

Face2Face system (Thies et al.)

Image synthesis

Karras, et al., Progressive Growing of GANs for Improved Quality, Stability, and Variation, ICLR 2018
Which face is real?

[Link]
Image synthesis

Zhu, et al., Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV 2017
Sports

Sportvision first down line

Explanation on [Link]
 Smart cars

• Tesla Autopilot - How It Works?

• [Link]
Self-driving cars

Waymo
Robotics

Amazon Picking Challenge

[Link] [Link]

Amazon Prime Air Amazon Scout

Medical imaging

Skin cancer classification with deep learning

[Link]
3D imaging
(MRI, CT)
Virtual & Augmented Reality

6DoF head tracking Hand & body tracking

3D scene understanding 3D-360 video capture

Current state of the art
• You just saw many examples of current systems.
– Many of these are less than 5 years old

• Computer vision is an active research area, and rapidly changing

– Many new apps in the next 5 years
– Deep learning powering many modern applications

• Many startups across a dizzying array of areas

– Deep learning, robotics, autonomous vehicles, medical imaging,
Why is computer vision difficult?

Viewpoint variation

Credit: Flickr user michaelpaul

Scale
Illumination
Why is computer vision difficult?

Motion (Source: S. Lazebnik)

Intra-class variation

Background clutter Occlusion

Challenges: local ambiguity

slide credit: Fei-Fei, Fergus & Torralba

Source: S. Lazebnik
Bottom line
• Perception is an inherently ambiguous problem
– Many different 3D scenes could have given rise to a given 2D image

Artist Julian Beever with his anamorphic Coke bottle

–
Image source: F. Durand
1. Low-level vision
• Basic image processing and image formation

* =
Filtering, edge detection

Feature extraction Image formation

Project: Hybrid images from image pyramids

G 1/8

G 1/4

Gaussian 1/2
Project: Feature detection and matching
2. Geometry

Image credit: IDS Imaging

Projective geometry Stereo vision

Multi-view stereo Structure from motion

Project: Creating panoramas
Project: 3D reconstruction
3. Recognition

Image classification

Object detection

Convolutional Neural Networks

Convolutional Neural Networks
Geometric primitives form the basic building blocks
used to describe three-dimensional shapes
 Image Coordinate Systems
• Spatial Coordinates: Cartesian x and y coordinates, In a spatial
coordinate system, locations in an image are positions on a
continuous plane.

• Polar coordinate is a two-dimensional coordinate system in

which each point on a plane is determined by a distance from a
reference point and an angle from a reference direction.
 De-Aging Harrison Ford

• [Link]
Thank you