1. Image and Video Processing – An Introduction
9/18/2018
Image and Video Processing – An Introduction
Fall ‘13 Instructor: Dr. Engr. Junaid Zafar Electrical Engineering Department
Government College University, Lahore

2. 9/18/2018
Scope of EE-7105
First graduate course on image/video processing
Not assume you have much exposure on image processing at undergraduate level
Require and build on background in random process and DSP
Emphasis on fundamental concepts
Provide theoretical foundations on multi-dimensional signal processing built upon pre-requisites
Coupled with assignments and projects for hands-on experience and reinforcement of the concepts
Follow-up courses
image analysis, computer vision, pattern recognition
multimedia communications and security

3. Textbooks and References
9/18/2018
Textbooks and References
R.C. Gonzalez and R.E. Woods: Digital Image Processing, Prentice Hall, 3rd Edition, 2008.
J. G. Proakis and D.G Manolakis: Digital Signal Processing, Principles, Algorithms & Applications, 4th Edition.
Related technical publications (will be announced in class).
Other related textbooks
Y. Wang, J. Ostermann, Y-Q. Zhang: Digital Video Processing and Communications, Prentice Hall, 2001.
A. K. Jain: Fundamentals of Digital Image Processing, Prentice Hall, 1989.
John W. Woods: Multidimensional Signal, Image, and Video Processing and Coding, Academic Press, 2006.
A. Bovik: Handbook Of Image & Video Processing, 2nd Edition, Academic Press, 2005.

4. Image and Video Processing: An Introduction and Overview
9/18/2018
Image and Video Processing: An Introduction and Overview

5. Why Do We Process Images?
9/18/2018
Why Do We Process Images?
Enhancement and restoration
Remove artifacts and scratches from an old photo/movie
Improve contrast and correct blurred images
Composition (for magazines and movies), Display, Printing …
Transmission and storage
images from oversea via Internet, or from a remote planet
Information analysis and automated recognition
Providing “human vision” to machines
Medical imaging for diagnosis and exploration
Security, forensics and rights protection
Encryption, hashing, digital watermarking, digital fingerprinting …

6. Why Digital? 9/18/2018 “Exactness”
Perfect reproduction without degradation
Perfect duplication of processing result
Convenient & powerful computer-aided processing
Can perform sophisticated processing through computer hardware or software
Even kindergartners can do some!
Easy storage and transmission
1 CD can store hundreds of family photos!
Paperless transmission of high quality photos through network within seconds

7. Examples of Digital Image & Video Processing
9/18/2018
Examples of Digital Image & Video Processing
Compression
Manipulation and Restoration
Restoration of blurred and damaged images
Noise removal and reduction
Morphing
Applications
Visual mosaicing and virtual views
Face detection
Visible and invisible watermarking
Error concealment and resilience in video transmission

8. Compression 9/18/2018 Movie ~ Image Sequence
Color image of 600x800 pixels
Without compression
600*800 * 24 bits/pixel = 11.52K bits = 1.44M bytes
After JPEG compression (popularly used on web)
only 89K bytes
compression ratio ~ 16:1
Movie ~ Image Sequence
720x 480 per frame, 30 frames/sec, 24 bits/pixel
Raw video ~ 243M bits/sec
DVD ~ about 5M bits/sec
Compression ratio ~ 48:1

9. 9/18/2018
Denoising

10. 9/18/2018
Deblurring

11. 9/18/2018
Visual Mosaicing

12. 9/18/2018
Face Detection
Image enhancement, feature extractions, and statistical modeling are often important steps in computer vision tasks

13. Visible Digital Watermarks
9/18/2018
Visible Digital Watermarks

14. Invisible Watermark 9/18/2018
Original, marked, and their amplified luminance difference
human visual model for imperceptibility: protect smooth areas and sharp edges

15. 9/18/2018
Error Concealment
25% blocks in a checkerboard pattern are corrupted
corrupted blocks are concealed via edge-directed interpolation
(a) original lenna image
(c) concealed lenna image
(b) corrupted lenna image

16. Different Ways to View an Image
9/18/2018
Different Ways to View an Image
Intensity visualization over 2-D (x,y) plane
In 3-D (x,y, z) plot with z=I(x,y); red color for high value and blue for low
Equal value contour in (x,y) plane

17. Sampling and Quantization
9/18/2018
Sampling and Quantization
Computer handles “discrete” data.
Sampling
Sample the value of the image at the nodes of a regular grid on the image plane.
A pixel (picture element) at (i, j) is the image intensity value at grid point indexed by the integer coordinate (i, j).
Quantization
Is a process of transforming a real valued sampled image to one taking only a finite number of distinct values.
Each sampled value in a 256-level grayscale image is represented by 8 bits.
0 (black)
255 (white)

18. 9/18/2018
Examples of Sampling
256x256
64x64
16x16

19. Examples of Quantizaion
9/18/2018
Examples of Quantizaion
8 bits / pixel
4 bits / pixel
2 bits / pixel