CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

70
CS 4763 Fundamentals of Multimedia Systems - Introduction to Image Processing Qi Tian Computer Science Department University of Texas at San Antonio [email protected] http://www.cs.utsa.edu/~qitian/

Transcript of CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Page 1: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

CS 4763 Fundamentals of Multimedia Systems - Introduction to Image Processing

Qi Tian

Computer Science Department University of Texas at San Antonio

[email protected]://www.cs.utsa.edu/~qitian/

Page 2: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Processing

Manipulation of multidimensional signals− image (photo)− video− CT, MRI− Fluid flow

),( yxf),,( tyxf),,,( tzyxf),,,( tzyxv

Page 3: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

A Typical Image Processing System

object observe digitize store process Refresh/store

Record

output

DisplayImaging systems

Sample and quantize

Digital storage (disk)

Digital computer

On-line buffer

X-ary, radar imaging, infrared imaging, ultrasound imaging, medical imaging, geophysical imaging

A/D

Page 4: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Fundamentals of Image Processing

Representation– acquisition, digitization, and display to mathematical

characterization of images for subsequent processing– a prerequisite for an efficient processing techniques such as

enhancement, filtering, and restoration.

Processing Techniques– Image compression, image restoration, and image reconstruction– Statistical image processing techniques

Communications

Page 5: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Multimedia Processing Techniques

– Coding/compressionStorage and communications

JPEG, JPEG2000MPEG-1 (CD, mp3), MPEG-2 (HDTV, DVD) H.261, H.263

– Enhancement, restoration, reconstructionfeature extraction for image analysis and visual information displayremoval of degradation in an image, LS, ML, Max entropy, MAP2D -> 3D image MRI, CT, Radon transform

– Analysis, detection, recognition, understandingquantitative measurements from an image to produce a description on it

– Visualization

Page 6: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Advanced Processing Techniques

Statistical processing techniques– Hidden Markov model (HMM)

– Probabilistic graphical models

– Bayesian networks

– Markov random field

Many applications to speech recognition, pattern classification, data

compression, and channel coding, etc.

Page 7: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

History of Image/Video Coding

1950

1960

1970

1980

1990

2000+

Math PR, CV, CG

Fractal 3-D Model based coding

Signal ProcessingBased

PCM DPCM

Transform CodingVQ

Subband Coding Wavelets

Page 8: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Reference:– F. Nebeker, Signal Processing: The Emergency of a Discipline,

1948-1998– IEEE History Center, 1998

Broadband TV (NTSC)500 × 500 × 8 × 3 × 30 bits/sec≈100 Mb/sec (compression is necessary!)Modem: 56Kb/sec

Picture Element– Pixel West coast people in USC– Pel East people in MIT

Page 9: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image/Video Compression

Signal-Processing Based:Encoder

),( yxfH

),( yxgSignal Proc.

Representation ),( yxg

Decoder1H− ),(ˆ yxf),( yxg

Page 10: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image/Video Compression

3D Model-Based:Encoder

Representation P

Decoder

),( yxfH

Analysis Model Parameter P

Model

),(ˆ yxfP 3D

Model

Page 11: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image/Video Compression

Fractal-Based:Encoder

Representation S

Decoder

),( yxf System S ),( yxf

Find S for which is an Attractor.),( yxf

SAny signal

),(ˆ yxf

Iteration

Page 12: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image/Video Compression Standard

Facsimile: Fax Group 1, 2, 3, 4JBIG (Joint Bi-level Image Expert Group)

Images: JPEG (http://www.jpeg.org/)

JPEG2000

Video: H.261, H.263 P × 64 Kb/s (P =1 ~ 30)MPEG 1 1.2 Mb/s Video, CD, MP3MPEG 2 1.2 – 20 Mb/s, sports, HDTV, DVDMPEG 4 1 kb/s → 1Mb/s, very low speed video

coding, MultimediaMPEG 7 Multimedia description, audio/video

MPEG 21 Multimedia framework

Based on Wavelet Transform

Page 13: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

A de facto image for the past three decade for its rich texture

Lena

Page 14: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image
Page 15: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

What are Challenging Problems in Multimedia Processing?

Multimedia Processing is taken in a broad sense, including:Image/Video compression, enhancement, restoration, reconstruction, analysis, recognition, understanding, visualization, and synthesis/animation.

Page 16: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Examples

Face modeling, detection, and recognitionEmotion recognitionGesture recognitionGender/age/ethnicity recognitionAudio-visual speech recognitionImage/video superresolutionImage/video browsing, indexing, and retrievalBiometrics

Page 17: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Face Related Research

Face modelingFace detectionFace recognitionFacial expression recognition

Page 18: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Generic Face Model

Texture mapping

Face model morphing

Page 19: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Generic Face Model

The generic face model is generated from a MRI data set

Page 20: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Customize A Genetic Face on An Individual

Polygon Mesh: 2240 Vertices + 3946 Triangles.Polygon Mesh: 2240 Vertices + 3946 Triangles.NonNon--Uniform Rational BUniform Rational B--Splines (NURBS): 63 control points.Splines (NURBS): 63 control points.

Page 21: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

The iFACE system in a distributed collaborative environment. (a) Avatar in the head mounted display, (b) avatar in the desk screen of

MIC3E, (c) avatar in the main screen of MIC3E

Avatar – talking head

University of Illinois at Urbana-Champaign

Page 22: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Text-Driven Face Animation

“We strive to make the meter on animation production, and are always looking for new technology that will enable faster, more appealing character creation,”

said Joel Kransove, Digital Director of Nickelodeon. (Source: Digital Producer)

Page 23: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Speech-Driven Face Animation

“Game characters have become synthetic actors and dialogue is an essential element of the effect we create. The quality of the lip-synching can make or break the sense of reality,”

said Scott Cronce, vice president and CTO at Electronic Art (Source: Gamepro)

Page 24: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Video-Driven Face Animation

Page 25: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Emotion Recognition

Page 26: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Emotion Recognition

Page 27: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Emotion Recognition

Page 28: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Face Detection Techniques

Page 29: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Face Detection Techniques

Page 30: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Face Recognition: Why it is easy?

Page 31: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Face Recognition: Why it is hard?

Page 32: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Beauty Check

What Are the Causes and Consequences of Human Facial Attractiveness?

Babyfaceness

Symmetry

Social perception

Universities of Regensburg, Germany

Page 33: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Which is more attractive?

Universities of Regensburg, Germany

Page 34: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

BabyfacenessLarge head

Large curved forehead

Facial elements (eyes,

nose, mouth) located

relatively low

Large, round eyes

Small, short nose

Round cheeks

Small chinKate Moss4-year old girl

Include mature female features: high, prominent cheek bones and concave cheeks

Page 35: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Which one is cuter?

Page 36: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Miss Germany (2002)

Page 37: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

A selection of the 22 contestants of the final round of the contest

Page 38: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Real vs. Virtual Miss Germany

Page 39: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Analysis

Texture synthesis and transferImage Super-resolutionImage RepairsIllumination/Lighting changes and transfer

Page 40: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Texture Synthesis and Transfer

+

SIGGRAPH’01 Effros & Freeman, MIT, 2001

synthesis

transfer

Page 41: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Texture Synthesis and Transfer

Page 42: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Superresolution

True Sub-sampled

Intelligent guess about details of texture

Page 43: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Superresolution

Gaussian filter Bicubic interpolation

Page 44: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Superresolution

Median filter Wiener filter

Page 45: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Superresolution

Dynamic resolution enhancement Amos Storkey

True

Page 46: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Repairs

Page 47: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Repairs

Original Image

Result

Segmentation

Image synthesis based on Tensor Voting

Curve connection

Page 48: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image Repairs

Page 49: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Illumination Effects on Images

Page 50: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Relighting – Basic Algorithm

Step 2: Approximate radiance environment map

Step 3: Synthesize novel appearance by adjusting the 9 spherical harmonic coefficients

Step 1: Align image with generic 3D face model

Page 51: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Lighting Transfer

input target results

Page 52: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Image/Video Retrieval

Image database

Page 53: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

CBIR based on color, texture, shape/structure

MARS: Multimedia Analysis and Retrieval System

metadata

User Interface

Similarity ranking

memory

Feature weighting

Visual C++

Feature Extraction

C/C++ Color

Texture

structure

Page 54: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

State-of-the-artCBIR Systems

QBIC (IBM), PhotoBook (Media Lab), Netra (UCSB), VisualSeek (Columbia), PicHunter (NEC-NJ), Amore (NEC-CA), EI Niňo (Praja), MARS (UIUC), Virage (Virage Inc.), CORE, PictoSeek, Piction, InfoScope …

Research CommunitiesComputer Vision, Image/Video Processing, Library and Information Science, Database and Management Systems

Leading Journals & StandardPAMI, ACM Multimedia, IJCV, CVIU

MPEG-7

Page 55: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

MARS using global features

Page 56: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometrics

Security Threats:We now live in a global society of increasing desperate and dangerous people whom we can no longer trust based on identification documentswhich may have been compromised.

A challenging Pattern Recognition ProblemEnabling technology to make our society safer, reduce fraud and offer user convenience.

Page 57: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Too many passwords to remember

Page 58: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Identification Problems

Identity Theft: Identity thieves steal PIN (e.g., date of birth) to open credit card account, withdraw money from accounts and take out loans

3.3 million identity thefts in U.S. in 2002; 6.7 million victims of credit card fraud

Surrogate representations of identity such as password and ID cards no longer suffice

Page 59: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometrics

Automatic recognition of people on their distinctive anatomical (e.g., face, fingerprint, iris, retina, hand geometry) and behavioral (e.g., signature, gait) characteristics.

Person identification is now an integral part of the infrastructure needed for diverse business sectors such as banking, border control, law enforcement…

Page 60: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometric Applications

Page 61: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometric Applications

There are ~500 million border crossing/year (each way) in the US

Page 62: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Want to charge it?

Page 63: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometric Characteristics

Page 64: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Biometric Market Growth

International Biometric Group

Page 65: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

“State-of-the-art” Error Rate

False accept rate (FAR):Proportion of imposters accepted

False reject rate (FRR):Proportions of genuine users rejected

Page 66: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Multibiometrics

Page 67: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Soft Biometrics

Page 68: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Privacy Concerns

Page 69: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image

Tracking

Page 70: CS 4763 Fundamentals of Multimedia Systems -Introduction to Image