zfirst graduate course on image/video processing digital ... · enee631 digital image processing...
TRANSCRIPT
11
ENEE631 Digital Image Processing (Spring'06)
Digital Image and Video Processing Digital Image and Video Processing ––An IntroductionAn Introduction
Spring ’06 Instructor: K. J. Ray LiuECE Department, Univ. of Maryland, College Park
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [2]
Scope of ENEE631Scope of ENEE631
First graduate course on image/video processing
Prerequisites: ENEE620 and 624, or by permission– Not assume you have much exposure on image processing at
undergraduate level– Random processes and DSP are required background
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 recognitionmultimedia communications and security
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [3]
TextbooksTextbooks
Primary– A.K. Jain: Fundamentals of Digital Image Processing, Prentice-Hall,
1989. (blue cover)– R.C. Gonzalez and R.E. Woods: Digital Image Processing, Prentice Hall,
2001. (black cover)
– Y. Wang, J. Ostermann, Y-Q. Zhang: Digital Video Processing and Communications, Prentice-Hall, 2001.
References – A.Bovik & J.Gibson: Handbook Of Image & Video Processing,
Academic Press, 2000.
Other references– Will be announced in lectures
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [4]
Introduction to Image and Video ProcessingIntroduction to Image and Video ProcessingU
MC
P EN
EE63
1 Sl
ides
(cre
ated
by
M.W
u ©
2001
)
22
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [5]
A picture is worth 1000 words.A picture is worth 1000 words.
Rich info. from visual dataExamples of images around usnatural photographic images; artistic and engineering drawingsscientific images (satellite, medical, etc.)
“Motion pictures” => videomovie, TV program; family video; surveillance and highway/ferry camera
A video is worth 1000 sentences?A video is worth 1000 sentences?
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
http://marsrovers.jpl.nasa.gov/gallery/press/opportunity/20040125a.htmlJPL Mars’ Panorama captured by the Opportunity
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [6]
Why Do We Process Images?Why Do We Process Images?
Enhancement and restoration– remove artifacts and scratches from an old photo/movie– improve contrast and correct blurred images
Transmission and storage– images from oversea via Internet, or from a remote planet
Information analysis and automated recognition– providing “human vision” to machines
Security and rights protection– encryption and watermarking
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [7]
Why Digital?Why Digital?
“Exactness”– Perfect reproduction without degradation– Perfect duplication of processing result
Convenient & powerful computer-aided processing– Can perform rather sophisticated processing through hardware or
software– Even kindergartners can do it!
Easy storage and transmission– 1 CD can store hundreds of family photos!– Paperless transmission of high quality photos through network within
seconds
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [8]
List of Image and Video Processing ExamplesList of Image and Video Processing Examples
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
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
33
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [9]
CompressionCompression
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 bytescompression ratio ~ 16:1
Movie – 720x480 per frame, 30 frames/sec,
24 bits/pixel– Raw video ~ 243M bits/sec– DVD ~ about 5M bits/sec– Compression ratio ~ 48:1
“Library of Congress” by M.Wu (600x800)
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [10]
DenoisingDenoising
From X.Li http://www.ee.princeton.edu/~lixin/denoising.htm
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [11]
DeblurringDeblurring
http://www.mathworks.com/access/helpdesk/help/toolbox/images/deblurr7.shtml
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [12]
MorphingMorphing
Princeton CS426 face morphing exampleshttp://www.cs.princeton.edu/courses/archive/fall98/cs426/assignments/morph/morph_results.html
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
44
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [13]
Visual Visual MosaicingMosaicing– Stitch photos together without thread or scotch tape
R.Radke – IEEE PRMI journal paper draft 5/01
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [14]
Face DetectionFace Detection
Face detection in ’98 @ CMU CS, http://www.cs.cmu.edu/afs/cs/Web/People/har/faces.html
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [15]
Visible Digital WatermarksVisible Digital Watermarks
from IBM Watson web page“Vatican Digital Library”
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [16]
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
Invisible Watermark Invisible Watermark
– 1st & 30th Mpeg4.5Mbps frame of original, marked, and their luminance difference– human visual model for imperceptibility: protect smooth areas and sharp edges
55
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [17]
Data Hiding for Annotating Binary Line DrawingsData Hiding for Annotating Binary Line Drawings
originaloriginal marked w/ marked w/ ““01/01/200001/01/2000””
pixelpixel--wise wise differencedifference
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [18]
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
Error ConcealmentError 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
Examples were generated using the source codes provided by W.Zeng.
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [19]
What is An Image?What is An Image?Grayscale image– A grayscale image is a function
I(x,y) of the two spatial coordinates of the image plane.
– I(x,y) is the intensity of the image at the point (x,y) on the image plane.
I(x,y) takes non-negative values
assume the image is bounded by a rectangle [0,a]×[0,b]
I: [0, a] × [0, b] → [0, inf )
Color image– Can be represented by three functions, R(x,y) for red, G(x,y) for green, and B(x,y) for blue.
y
x
020
4060
80
0
50
1000
50
100
150
200
250
columnsrows
inte
nsity
y x
I(x,y)
UM
CP
ENEE
408G
Slid
es (c
reat
ed b
y M
.Wu
& R
.Liu
©20
02)
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [20]
Sampling and QuantizationSampling and Quantization
Computer handles “digital” 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)
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
66
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [21]
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
Examples of SamplingExamples of Sampling
256x256
64x64
16x16
ENEE631 Digital Image Processing (Spring'06) Lec1 – Introduction [22]
UM
CP
ENEE
631
Slid
es (c
reat
ed b
y M
.Wu
©20
01)
Examples of Examples of QuantizaionQuantizaion
8 bits / pixel
4 bits / pixel
2 bits / pixel