Top Banner
Digital Image Processing: Bernd Girod, © 2013 Stanford University -- Introduction 1 Digital Image Processing EE368/CS232 Bernd Girod Information Systems Laboratory Department of Electrical Engineering Stanford University
28

Digital Image Processing - web.stanford.edu · Digital Image Processing: ... Introduction 1 Digital Image Processing EE368/CS232 . ... – Efficiently store an image in a digital

Jul 01, 2018

Download

Documents

dangtuyen
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 1

    Digital Image Processing EE368/CS232

    Bernd Girod Information Systems Laboratory

    Department of Electrical Engineering Stanford University

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 2

    What is an image?

    [Albrecht Drer, 1525]

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 3

    What is an image?

    Most images are defined over a rectangle Continuous in amplitude and space

    X

    X

    y

    y

    Image: a visual representation in form of a function f(x,y) where f is related to the brightness (or color) at point (x,y)

    [Albrecht Drer, 1525]

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 4

    Digital Images and Pixels

    Digital image: discrete samples f [x,y] representing continuous image f (x,y) Each element of the 2-d array f [x,y] is called a pixel or pel

    (from picture element)

    200x200 100x100 50x50 25x25

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 5

    Color Components

    Red R[x,y] Green G[x,y] Blue B[x,y]

    Monochrome image

    R[x,y] = G[x,y] = B[x,y] 20 m

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 6

    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

    Enhance and restore images Touch up personal photos Color enhancement for security screening

    Extract information from images Read 2-d bar codes Character recognition

    Many more ... image processing is ubiquitous

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 7

    Image Processing Examples

    source: M. Borgmann, L. Meunier, EE368 class project, spring 2000. Mosaic from 21 source images

    Mosaic from 33 source images

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 8

    Image Processing Examples Face morphing

    Source: Yi-Wen Liu and Yu-Li Hsueh, EE368 class project, spring 2000.

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 9

    Image Processing Examples Face Detection

    source: Henry Chang, Ulises Robles, EE368 class project, spring 2000.

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 10

    Image Processing Examples

    source: Michael Bax, Chunlei Liu, and Ping Li, EE368 class project, spring 2003.

    Face Detection

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 11

    Image Processing Examples

    Face Detection

    Face Blurring for Privacy Protection

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 12

    Image Processing Examples

    http://cs.stanford.edu/group/roadrunner/stanley.html

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 13

    Image Processing Examples

    Source: Huizhong Chen, Sam Tsai, Bernd Girod, Stanford, 2012

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 14

    EE368 Spring 2006 Project: Visual Code Marker Recognition

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 15

    EE368 Spring 2007 Project: Painting Recognition

    2 1 3 4

    6 5 7 8

    9 10

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 16

    EE368 Spring 2007 Project: Painting Recognition

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 17

    EE368 Spring 2008 Project: CD Cover Recognition

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 18

    CD Cover Recognition on Cameraphone

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 19

    ???

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 20

    Scope of EE368/CS232

    Introductory graduate-level digital image processing class Emphasis on general principles, signals & systems angle Prerequisites: EE261, EE278B or equivalent recommended (but not required) Topics

    Point operations, color Image thresholding/segmentation Morphological image processing Image filtering, deconvolution Feature extraction Scale-space image processing Image registration, image matching Eigenimages

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 21

    Image Processing and Related Fields

    Artificial Intelligence

    Robotics, Inspection,

    Photogrammetry

    Imaging

    Machine learning

    M-d Signal

    Processing Image coding

    Optical Engineering

    Computer Vision

    Machine Vision

    Computer Graphics

    Statistics, Information

    Theory

    Visual

    Perception

    Display

    Technology

    Computational Photography

    Image

    Processing

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 22

    ???

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 23

    EE368/CS232 Organisation

    Assistants Course assistants: David Chen, Matt Yu Administrative assistant: Kelly Yilmaz

    Office hours Bernd Girod: Tu 1:30-3:00 p.m., Packard 373 (starting 4/16) David Chen, We 5:00-7:00 p.m., Packard 021 (SCIEN Lab) Matt Yu, Th 5:00-7:00 p.m., Packard 021 (SCIEN Lab) SCPD Live Meeting session: Tu 6:00pm

    Class home page: http://www.stanford.edu/class/ee368

    Class Piazza page: http://piazza.com/class#spring2013/ee368

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 24

    EE368/CS232 Organisation (cont.) Homeworks

    Weekly assignments until midterm, require computer + Matlab Usually handed out Fridays, due one week later, solve individually First handed out on April 5

    Late Midterm 24-hour take-home exam 3 slots, May 22-25

    Final project Individual or group project, plan for about 50-60 hours per person Develop, implement and test/demonstrate an image processing algorithm Project proposal due: May 1, 11:59 p.m. Project presentation: Poster session, June 5, 4-6:30 p.m. Submission of written report and source code: June 5, 11:59 p.m.

    Grading Homeworks: 20% Mid-term: 30% Final project: 50% No final exam.

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 25

    SCIEN laboratory

    SCIEN = Stanford Center for Image Systems Engineering (http://scien.stanford.edu)

    Exclusively a teaching laboratory Location: Packard room 021 20 Linux PCs, scanners, printers etc.

    Matlab with Image Processing Toolbox Android development environment

    Access: Door combination for lab entry will be provided by TA Account on SCIEN machines will be provided to all enrolled in class

    http://scien.stanford.edu

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 26

    Mobile image processing Google gift: 40 Motorola DROID cameraphones

    Available for EE368/CS232 projects (must be returned after, sorry) Lectures on Android image processing in April Android development environment on your own computer or in SCIEN lab Programming in Java (C++ for OpenCV)

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 27

    Reading Slides available as hand-outs and as pdf files on the web Popular text books

    R. C. Gonzalez, R. E. Woods, Digital Image Processing, 3rd edition, Prentice-Hall, 2008, $186. ($147 on Amazon).

    A. K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall, Addison-Wesley, 1989, $186. ($141 on Amazon).

    Software-centric books R. C. Gonzalez, R. E. Woods, S. L. Eddins, Digital Image Processing using Matlab,

    2nd edition, Pearson-Prentice-Hall, 2009, ca. $ 140.--. G. Bradski, A. Kaehler, Learning OpenCV, OReilly Media, 2008, $ 50.00.

    Comprehensive state-of-the-art Al Bovik (ed.), The Essential Guide to Image Processing,

    Academic Press, 2009, $ 92.95. Journals/Conference Proceedings

    IEEE Transactions on Image Processing IEEE International Conference on Image Processing (ICIP) IEEE Computer Vision and Pattern Recognition (CVPR)

  • Digital Image Processing: Bernd Girod, 2013 Stanford University -- Introduction 28

    ???

    Digital Image ProcessingEE368/CS232What is an image? What is an image? Digital Images and Pixels Color ComponentsWhy do we process images?Image Processing ExamplesImage Processing ExamplesImage Processing ExamplesImage Processing ExamplesImage Processing ExamplesImage Processing ExamplesImage Processing ExamplesEE368 Spring 2006 Project:Visual Code Marker RecognitionEE368 Spring 2007 Project:Painting RecognitionEE368 Spring 2007 Project:Painting RecognitionEE368 Spring 2008 Project:CD Cover RecognitionCD Cover Recognition on CameraphoneSlide Number 19Scope of EE368/CS232Image Processing and Related FieldsSlide Number 22EE368/CS232 OrganisationEE368/CS232 Organisation (cont.)SCIEN laboratoryMobile image processingReadingSlide Number 28