Introduction & Fundamentals
Lecture 1
EEE429-Image and Video Communications / EME408-Image Processing
and Vision
Nuwan Vithanage
Introduction to the course
• LMS URL:
https://lms.sltc.ac.lk/course/view.php?id=271
https://lms.sltc.ac.lk/course/view.php?id=64
• 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 : 40%
• End of the Semester Exam: 60%
• Total: 100%
• Mode of Delivery: Online
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
How hard is computer vision?
“In 1966, Minsky hired a first-year
undergraduate student and assigned
him a problem to solve over the
summer: connect a television
camera to a computer and get the
machine to describe what it sees.”
How hard is computer vision?
“You’ll notice that Sussman never worked in vision again!”
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
