Computers and Photographs 1) Image Processing 2) Computer Vision Henry Schneiderman.

Slides:



Advertisements
Similar presentations
Review of AI from Chapter 3. Journal May 13  What advantages and disadvantages do you see with using Expert Systems in real world applications like business,
Advertisements

Image Processing and Computer Vision Lecture 4, Multimedia E-Commerce Course November 5, 2002 Mike Christel (significant input by Henry Schneiderman,
Chapter 11 Beyond Bag of Words. Question Answering n Providing answers instead of ranked lists of documents n Older QA systems generated answers n Current.
Multimedia for the Web: Creating Digital Excitement Multimedia Element -- Graphics.
Overview of Computer Vision CS491E/791E. What is Computer Vision? Deals with the development of the theoretical and algorithmic basis by which useful.
Copyright © 2006 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill Technology Education Copyright © 2006 by The McGraw-Hill Companies,
Computing With Images: Outlook and applications
Computers and Photographs 1) Image Processing 2) Computer Vision Henry Schneiderman.
Digital Still Images ETT June Multimedia Assets Still Images Audio Video.
Introduction What is “image processing and computer vision”? Image Representation.
Object Detection Using the Statistics of Parts Henry Schneiderman Takeo Kanade Presented by : Sameer Shirdhonkar December 11, 2003.
LAPPEENRANTA UNIVERSITY OF TECHNOLOGY THE DEPARTMENT OF INFORMATION TECHNOLOGY 1 Computer Vision: Fundamentals & Applications Heikki Kälviäinen Professor.
Introduction to Computer Graphics
Adapted from CTAE Resources Network PROFITT Curriculum Basic Computer Skills Module 1 Hardware.
Digital Photography. Objectives After completing this class, you will be able to:  Explain the benefits, features, and workings of a digital camera.
Machine Learning Damon Waring 22 April of 15 Agenda Problem, Solution, Benefits Problem, Solution, Benefits Machine Learning Overview/Basics Machine.
Components Text Text--Processing Software A Word Processor is a software application that provides the user with the tools to create and edit text.
Part A Multimedia Production Rico Yu. Part A Multimedia Production Ch.1 Text Ch.2 Graphics Ch.3 Sound Ch.4 Animations Ch.5 Video.
Computer Vision Systems for the Blind and Visually Disabled. STATS 19 SEM Talk 3. Alan Yuille. UCLA. Dept. Statistics and Psychology.
Web Design, 4 th Edition 5 Typography and Images.
Goals of Computer Vision To make useful decisions based on sensed images To construct 3D structure from 2D images.
A Brief Overview of Computer Vision Jinxiang Chai.
Pro Imager A complete image and workflow management solution for the professional lab.
Modeling And Visualization Of Aboriginal Rock Art in The Baiame Cave
Graphics.
Web Design, 5 th Edition 5 Typography and Images.
Working With Images, Sound, and Video Mark Grabe.
Unit 30 P1 – Hardware & Software Required For Use In Digital Graphics
What is it a scanner? An optical input device that uses light- sensing equipment to capture an image on paper or some other subject. The image is translated.
Copyright © Texas Education Agency, All rights reserved.1 Introduction to Scanners Principles of Information Technology.
Digital Image Processing In The Name Of God Digital Image Processing Lecture1: Introduction M. Ghelich Oghli By: M. Ghelich Oghli
XP Practical PC, 3e Chapter 13 1 Working with Graphics.
The Complexities & Economics of Digitizing Microfilm
Seminar on Media Technology Computer Vision Albert Alemany Font.
CSCE 5013 Computer Vision Fall 2011 Prof. John Gauch
Graphics, Hypermedia, and Multimedia.  Prentice HallSlide 2 Focus on Computer Graphics Computer graphics include: –Painting Software –Digital Image Processing.
Compiled By: Raj G Tiwari.  A pattern is an object, process or event that can be given a name.  A pattern class (or category) is a set of patterns sharing.
Digital Watermarking Simg-786 Advanced Digital Image Processing Team 1.
Object Based Processing for Privacy Protected Surveillance Karl Martin Kostas N. Plataniotis University of Toronto Dept. of Electrical and Computer Engineering.
1 Lecture 1 1 Image Processing Eng. Ahmed H. Abo absa
Computer Science Department Pacific University Artificial Intelligence -- Computer Vision.
1 Digital Image Processing Dr. Saad M. Saad Darwish Associate Prof. of computer science.
Chapter 14 Working with Graphics. 2Practical PC 5 th Edition Chapter 14 Getting Started In this Chapter, you will learn: − About different graphics you.
A Statistical Method for 3D Object Detection Applied to Face and Cars CVPR 2000 Henry Schneiderman and Takeo Kanade Robotics Institute, Carnegie Mellon.
BY CASEY KUCERA Multimedia. Vector Graphics Composed of objects not pixels Object oriented graphics = vector graphics Stores a series of mathematical.
INTRODUCTION TO GIS  Used to describe computer facilities which are used to handle data referenced to the spatial domain.  Has the ability to inter-
The Digital Revolution Changing information. What is Digital?  Discrete values used for  Input  Processing  Transmission  Storage  Display  Derived.
1 Machine Vision. 2 VISION the most powerful sense.
Digital Video Library Network Supervisor: Prof. Michael Lyu Student: Ma Chak Kei, Jacky.
Computer Vision UNR George Bebis Computer Vision Laboratory (CVL) Department of Computer Science and Engineering University of Nevada, Reno,
Introduction to Image Processing Representasi Citra Tahap-Tahap Kunci pada Image Processing Aplikasi dan Topik Penelitian pada Image Processing.
The Complexities & Economics of Scanning Microfilmed Documents Videos
OTHER RESEARCH IN SIGNAL PROCESSING AND COMMUNICATIONS IN ECE Richard Stern Carnegie Mellon University (with Dave Casasent, Tsuhan Chen, Vijaya Kumar,
Image File Formats Harrow Computer Club – Wed, 1 Dec 2010 Bob Watson MA CMath MIMA MBCS.
  Computer vision is a field that includes methods for acquiring,prcessing, analyzing, and understanding images and, in general, high-dimensional data.
Computer Vision: 3D Shape Reconstruction Use images to build 3D model of object or site 3D site model built from laser range scans collected by CMU autonomous.
Visual Information Processing. Human Perception V.S. Machine Perception  Human perception: pictorial information improvement for human interpretation.
CONTENT INCLUDED IN POSTERS THAT WOULD BE DISPLAYED IN A GYM AND METHODS BY WHICH THESE POSTERS CAN BE CREATED.
Chapter 14 Working with Graphics
Chapter 13 Working with Graphics
DCT IMAGE COMPRESSION.
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
CMPE 101 Introduction to Information Technologies Chapter 5: Application Software: Tools for Productivity Copyright © 2012 Pearson Education, Inc. Publishing.
Chapter III, Desktop Imaging Systems and Issues: Lesson IV Working With Images
McGraw-Hill Technology Education
Digital Image Processing Introduction
Introduction Computer vision is the analysis of digital images
Building an Online Store
Presentation transcript:

Computers and Photographs 1) Image Processing 2) Computer Vision Henry Schneiderman

Outline Digital Cameras Emerging Technology Research in Image Processing and Computer Vision Automatically Finding Faces and Cars in Photographs

Digital Cameras = Convenience Easy to capture photos Easy to store and organize photos Easy to duplicate photos Easy to edit photos

Digital Camera Usage Lyra research report, 1999 Exposures in billions

State of the Art: Digital Cameras Film is currently better in resolution and color. –Professional photographers Digital for low quality newspaper adds Film for portrait photos Computer storage limitations: 1 high resolution digital image = 25 MegaBytes Printing –home printers not comparable to commercial printers

Future of Digital Cameras Improved resolution and color “Smart” cameras More programmable features –Auto-focus on object of interest –“Everything in focus” photo –Capture photo when event X occurs

Photographs: Migration to Digital Format Others means of digitizing imagery –Scanners (photo and film) –Frame-grabber for video

Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games,...

Optical Character Recognition (OCR) First patent in OCR in 19 th century First applications in post-office and banks State of the art not perfect. Examples of errors:

Handwriting Recognition Works if constraints on writer, e.g. palm pilot

Other document processing Not just for text... Examples: –Engineering document to CAD file –Maps to GIS format –Music score to MIDI representation

Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc

Biometrics Technology for identification –Finger/palm print –Iris –Face

Fingerprints Minutae – spits and merges of ridges

Face Identification Not quite reliable yet. –Performance degrades rapidly with uncontrolled lighting, facial expression, and size of database Several companies exist: –Visionics (Rockfeller Univesity spin-off) –EyeMatic (USC spin-off) –Miros (MIT spin-off) –Banque-Tec Intl (Australia) –C-VIS Computer Vision (Germany) –LAU Technologies Commercial systems installed in London and Brazil to catch criminals

Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc

Management of images on computers Compression – reducing storage size needed for images Watermarking – Protecting copyright Microsoft, Bell Labs, NEC, etc. Visible watermark

Photo-manipulation Adobe Photoshop, Corel PhotoPaint, Pixami, PhotoIQ, etc. –More automatic features

Searching Digital Image Collections Large collections of images exist –Corbis 67 million images –Getty 70 million stock photography images –AP collects 1000s of digitized images per day Search methods are inadequate –Rely on captions and colors IBM’s Query by Image Content (QBIC) system

Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc

Inspection for Manufacturing Occum – inspection of printed circuit boards ($100M / year) Cognex – Do-it-yourself toolkits for inspection (400 employees)

Automatic Target Recognition (ATR) Finding mines, tanks, etc. Billion dollar a year industry –Martin-Lockheed, TSR, Northrup-Grumman, other aerospace contractors. Various types of imagery: –Synthetic Aperture Radar (SAR), Sonar, hyper- spectral imagery (more than 3 colors)

Aerial Photo Interpretation / Automated Cartography Classification of land-use: forest, vegetation, water Identification of man-made objects: buildings, roads, etc

Better Security Cameras Cameras that are responsive to the environment –Track and zoom on moving objects –Automatic adjustment of contrast

Human-Computer Interaction Computer games that involve interaction with user Intelligent teleconferencing

Medical imagery Medical image libraries for study and diagnosis Image overlay to guide surgeons

History 1980’s ~100 companies – manufacturing applications mostly Early 1990’s less than 10 companies Late 1990’s ~100 companies – face recognition, intelligent teleconferencing, inspection, digital libraries

Computer Vision and Image Processing Research

Image processing Computer vision chair, face, shape, etc. “Symbolic” descriptionimage

1. Image Processing: Filtering

2. Image Processing: Compression Lossless – No loss in quality, gif, tiff Lossy – Original image cannot be reconstructed, jpeg

3. Image Processing: Watermarking Information hiding –Protecting Copyright

4. Image Processing: Transformation Transforming image can make it easier to analyze Wavelet transform of image

Decomposition in Resolution/Frequency fine coarseintermediate

Wavelet Decomposition Vertical subbands (LH)

Wavelet Decomposition Horizontal subbands (HL)

1. Computer Vision: 3D Shape Reconstruction Use images to build 3D model of object or site 3D site model built from laser range scans collected by CMU autonomous helicopter

2. Computer Vision: To guide Motion Visually guided locomotion –robotic vehicles Visually guided manipulation –Hand-eye coordination CMU NavLab II

3. Computer Vision: Recognition and Classification

Challenges in Object Recognition

Challenges in Object Detection Intra-class variation

Lighting variation

Geometric variation

Simpler Problem: Classification Fixed size input Fixed object size, orientation, and alignment “Object is present” (at fixed size and alignment) “Object is NOT present” (at fixed size and alignment) Decision

1) Apply Local Operators f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723

2) Look-Up Probabilities f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723 P 1 ( #5710, 0, 0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214, 0, 1 | obj) = 0.57 P 1 ( #3214, 0, 1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = 0.19

Probabilities Estimated Off-Line f 1 (0, 0) = #567H 1 (#567, 0, 0) = H 1 (567, 0, 0) + 1 f k (n, m) = #350H k (#350, 0, 0) = H k (#350, 0, 0) + 1 P 1 (#567, 0, 0) =  H 1 (#i, 0, 0) H 1 (#567, 0, 0) P k (#350, 0, 0) =  H k (#i, 0, 0) H k (#350, 0, 0)

3) Make Decision P 1 ( #5710, 0, 0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214, 0, 1 | obj) = 0.57 P 1 ( #3214, 0, 1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = * 0.57 *... * * 0.48 *... * 0.19 >

Overall Algorithm f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723 P 1 ( #5710,0,0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214,0,1 | obj) = 0.57 P 1 ( #3214,0,1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = * 0.57 *... * * 0.48 * … * 0.19

Detection: Apply Classifier Exhaustively Search in position Search in scale

View-based Classifiers Face Classifier #1 Face Classifier #2 Face Classifier #3

2 classifiers trained for faces. 8 classifiers trained for cars.

Training Classifiers Cars: images per viewpoint Faces: 2,000 images per viewpoint ~1,000 synthetic variations of each original image –background scenery, orientation, position, frequency 2000 non-object images –Samples selected by bootstrapping Minimization of classification error on training set –AdaBoost algorithm (Freund & Shapire ‘97, Shapire & Singer ‘99) Iterative method Determines weights for samples

Applications of Face Detection Automatic red-eye removal from photographs Automatic color balancing in photo- finishing Intelligent teleconferencing Component in face identification system

Difficulty Increases with Complexity of Object 2D vs. 3D Specific objects – e.g. my coffee mug A category of objects – e.g. all coffee mugs Amount of intra-category variation –Rigid or semi-rigid structure, e.g. face –Articulated objects, e.g. human body –Functionally defined objects, e.g. chairs

Summary: Image Processing & Computer Vision Not as mature as speech recognition –Technology not as reliable –Fewer companies, fewer products Success on limited problems, e.g., documents More applicable to fault tolerant problems Technology will grow –Emergence of digital camera –Improved methods