Académique Documents
Professionnel Documents
Culture Documents
Lectures
Monday and Wednesday 11am-12:15pm, CSI 2120
Office Hours
Dr. Min Wu (minwu@eng.umd.edu)
Scope of ENEE631
First graduate course on image/video processing Prerequisites: ENEE620 and 630, or by permission
Not assume you have much exposure on image processing at undergraduate level Require and build on background in random process and DSP
image analysis, computer vision, pattern recognition multimedia communications and security
Lec1 Introduction [3]
R.C. Gonzalez and R.E. Woods: Digital Image Processing, Prentice Hall, 3rd Edition, 2008. (yellow cover)
Grading
Assignments and class participation Projects Exams 20% 45% 35%
Projects
Put theories and principles in use and learn from doing; critical thinking
Exams
In-class mid-term exam: on basic concepts, theories, and approaches Final exam: apply theories and principles to image/video proc tasks
M. Wu: ENEE631 Digital Image Processing (Spring'09) Lec1 Introduction [5]
Computer codes
You should write your own codes unless otherwise stated DO NOT COPY other students codes Clearly state the code modules obtained elsewhere and consult instructor for permission to use in your project
First Edition (1768-1771) A dictionary of arts and sciences by a Society of Gentlemen in Scotland 3 volumes, ~ 2600 pages illustrated with 160 copperplates 11th Edition (1911) last time to encapsulate ALL human knowledge one picture every 4 pages 1999 Edition 32 volumes; in CD and DVD 73,000 articles; 30,000 photos and illustrations Now online: http://www.britannica.com/
Lec1 Introduction [10]
Composition (for magazines and movies), Display, Printing Transmission and storage
images from oversea via Internet, or from a remote planet
Why Digital?
UMCP ENEE631 Slides (created by M.Wu 2001)
Exactness
Perfect reproduction without degradation Perfect duplication of processing result
Applications
Visual mosaicing and virtual views Face detection Visible and invisible watermarking Error concealment and resilience in video transmission
Compression
Denoising
UMCP ENEE631 Slides (created by M.Wu 2001)
Deblurring
UMCP ENEE631 Slides (created by M.Wu 2001)
http://www.mathworks.com/access/helpdesk/help/toolbox/images/deblurr7.shtml
Visual Mosaicing
Stitch photos together without thread or scotch tape
UMCP ENEE631 Slides (created by M.Wu 2001)
Face Detection
UMCP ENEE631 Slides (created by M.Wu 2001)
Image enhancement, feature extractions, and statistical modeling are often important steps in computer vision tasks
See more image understanding examples by Prof. Chellappas research group (http://www.cfar.umd.edu/~rama/research.html)
General Illumination Correction and Its Application to Face Normalization, J. Zhu et al, ICASSP 2003
M. Wu: ENEE631 Digital Image Processing (Spring'09) Lec1 Introduction [20]
Invisible Watermark
UMCP ENEE631 Slides (created by M.Wu 2001; 2009)
Original, marked, and their amplified luminance difference human visual model for imperceptibility: protect smooth areas and sharp edges
M. Wu: ENEE631 Digital Image Processing (Spring'09) Lec1 Introduction [23]
original
marked w/ 01/01/2000
pixel-wise difference
Error Concealment
(a) original lenna image
UMCP ENEE631 Slides (created by M.Wu 2001)
Research frontiers ranging from traditional image processing applications to evolving multimedia and video technologies Areas of interest include but are not limited to: Image/Video Coding and Transmission: Still image coding, video coding,
stereoscopic and 3-D coding, distributed source coding, . . . Image/Video Processing: filtering, restoration, enhancement, segmentation, video segmentation and tracking, morphological processing, stereoscopic and 3-D processing, feature extraction and analysis, interpolation and super-resolution, motion detection and estimation, . . . Image Formation: Biomedical imaging, remote sensing, geophysical and seismic imaging, optimal imaging, synthetic-natural hybrid image systems Image Scanning, Display, and Printing: Scanning, sampling, quantization and halftoning, color reproduction, image representation and rendering, Image/Video Storage, Retrieval, and Authentication: Image/video databases, image/video indexing and retrieval, multimodality image/video indexing and retrieval, authentication and watermarking Applications: biomedical sciences, geosciences and remote sensing, . . .
M. Wu: ENEE631 Digital Image Processing (Spring'09) Lec1 Introduction [27]
What is an Image?
What we perceive as a grayscale image is a pattern of light intensity over a 2-D plane (aka image plane)
Described by a nonnegative real-valued function I(x,y) of two continuous spatial coordinates on an image plane. I(x,y) is the intensity of the image at the point (x,y). An image is usually defined on a bounded rectangle for processing
I: [0, a] [0, b] [0, inf )
x
Color image
Can be represented by three functions:
R(x,y) for red, G(x,y) for green, B(x,y) for blue.
y
M. Wu: ENEE631 Digital Image Processing (Spring'09) Lec1 Introduction [30]
In 3-D (x,y, z) plot with z=I(x,y); red color for high value and blue for low
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.
=> Stay tuned for the theories on these in future weeks.
M. Wu: ENEE631 Digital Image Processing (Spring'09)
255 (white)
0 (black)
-s
B s=2/T
B s=2/T
Examples of Sampling
UMCP ENEE631 Slides (created by M.Wu 2001)
Examples of Quantizaion
UMCP ENEE631 Slides (created by M.Wu 2001)
Course organization and policies Background and examples of digital image processing Sampling and quantization concepts for digital image
Next time
Color and Human Visual System
Gonzalez-Wood book, Chapter 1 Boviks Handbook Section 1 Introduction (see course web) Go over mathematical preliminaries
Linear system and basics of 1-D signal processing FT and ZT Matrix and linear algebra Probability
Color of Light
UMCP ENEE408G Slides (created by M.Wu & R.Liu 2002)
Chrominance Hue
Saturation
describe how pure the color is depend on the spread (bandwidth) of light spectrum reflect how much white light is added
HSV circular cone is from online documentation of Matlab image processing toolbox http://www.mathworks.com/access /helpdesk/help/toolbox/images/col or10.shtml
Lec1 Introduction [43]
Seeing yellow figure is from B.Liu ELE330 S01 lecture notes @ Princeton; primary color figure is from Chapter 6 slides at Gonzalez/ Woods DIP book website