Approaches to Representing and Recognizing Objects Visual Classification CMSC 828J – David Jacobs.

Slides:



Advertisements
Similar presentations
Introduction to Pre-calculus Math.  Confidently solve problems  Communicate and reason mathematically  Increase mathematical literacy  Make connections.
Advertisements

HOW MIGHT WE SUPPORT TEACHERS AS THEY DEEPEN THEIR OWN UNDERSTANDING AND EXPLORE STUDENT THINKING RELATED TO THE K-6 GEOMETRY PROGRESSION? GINI STIMPSON.
Math Xa Introduction to Functions and Calculus Fall 2008 Introductory Meeting John Hall.
AIM for Success: Getting Started. Motivate Yourself Prepare to succeed. –Stay motivated! –Actively pursue success! List two reasons why you want to succeed.
CPSC 425: Computer Vision (Jan-April 2007) David Lowe Prerequisites: 4 th year ability in CPSC Math 200 (Calculus III) Math 221 (Matrix Algebra: linear.
Article Critique Morgan Coates Jenn Hartnett. Overview  Algebra concepts should be incorporated with elementary and middle school mathematics  Math.
Lecture 1: Basics of Math and Economics AGEC 352 Spring 2011 – January 12 R. Keeney.
UMass Lowell Computer Science Analysis of Algorithms Prof. Karen Daniels Fall, 2001 Lecture 1 (Part 1) Introduction/Overview Tuesday, 9/4/01.
CSCD 555 Research Methods for Computer Science
UMass Lowell Computer Science Analysis of Algorithms Prof. Karen Daniels Fall, 2002 Lecture 1 (Part 1) Introduction/Overview Tuesday, 9/3/02.
CEP Welcome September 1, Matthew J. Koehler September 1, 2005CEP Cognition and Technology Who’s Who?  Team up with someone you don’t.
UMass Lowell Computer Science Geometric Modeling Prof. Karen Daniels Spring, 2009 Lecture 1 Course Introduction.
CS503: First Lecture, Fall 2008 Michael Barnathan.
SLIDE 1IS 202 – FALL 2003 Lecture 26: Final Review Prof. Ray Larson & Prof. Marc Davis UC Berkeley SIMS Tuesday and Thursday 10:30 am - 12:00.
Glenn Ledder Department of Mathematics University of Nebraska-Lincoln Designing Math Courses:
Math 105: Problem Solving in Mathematics. Course Description This course introduces students to the true nature mathematics, what mathematicians really.
CS503: Tenth Lecture, Fall 2008 Review Michael Barnathan.
© 2004 by Davi GeigerComputer Vision January 2004 L1.1 Introduction.
ECS 298 Photorealistic Image Synthesis course overview Brian Budge Center for Image Processing and Integrated Computing Computer Science Department University.
MATH 330: Ordinary Differential Equations Fall 2014.
Fall 2004 Cognitive Science 207 Introduction to Cognitive Modeling Praveen Paritosh.
MTH 110 or MTH 112? An Information Guide For Students, Instructors, and Counselors Version 2.0.
Algebra 1 Ch 4.2 – Graphing Linear Equations. Objective Students will graph linear equations using a table. Students will graph linear equations using.
EECS 395/495 Algorithmic Techniques for Bioinformatics General Introduction 9/27/2012 Ming-Yang Kao 19/27/2012.
Test Preparation Strategies
CS Machine Learning. What is Machine Learning? Adapt to / learn from data  To optimize a performance function Can be used to:  Extract knowledge.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean Hall 5409 T-R 10:30am – 11:50am.
CMSC 426: Image Processing (Computer Vision) David Jacobs.
James Matte Nicole Calbi SUNY Fredonia AMTNYS October 28 th, 2011.
Welcome to your child’s 6 th Grade Math Class On Team (6B) Welcome to your child’s 6 th Grade Math Class On Team (6B) Where we try to make sense of numbers.
Teaching Teaching Discrete Mathematics and Algorithms & Data Structures Online G.MirkowskaPJIIT.
COMP Introduction to Programming Yi Hong May 13, 2015.
CS6501 Information Retrieval Course Policy Hongning Wang
Research and Instructional Practices National Math Panel Meeting Stanford, CA November 6, 2006 James Hiebert, University of Delaware.
Big Ideas & Better Questions, Part II Marian Small May, ©Marian Small, 2009.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
WEEK 1. ( a time for more computations ) MATH 070.
Course description ATS 441 / 541 Refer to syllabus.
STANDARDS FOR MATHEMATICS 1. Uses a variety of strategies in the PROBLEM- SOLVING PROCESS 2. Understands and applies basic and advanced properties of the.
Math 105: Problem Solving in Mathematics
Science Fair How To Get Started… (
Annotating Texts and Taking Notes
1 Machine Learning (Extended) Dr. Ata Kaban Algorithms to enable computers to learn –Learning = ability to improve performance automatically through experience.
CSE 3802 / ECE 3431 Numerical Methods in Scientific Computation
Fall 2014 MATH 250: Calculus III. Course Topics Review: Parametric Equations and Polar Coordinates Vectors and Three-Dimensional Analytic Geometry.
AP World History Review Project
Unwrapping the Standards. The power standards are the fence posts. They provide the curricular focus and teachers need to dig deeper to assure student.
Common Core Leadership in Mathematics Project, University of Wisconsin-Milwaukee, Summer Institute 2012 What are Fractions? Part 1 Common Core Leadership.
CPSC : Data-driven Computer Graphics Jinxiang Chai.
Expectations in a College Math Class How does taking math in college differ from taking math in high school? What is your instructor thinking?
Tracy Guerrera Jasmine Rivera Jodi-Ann Martells. Brief Overview Purpose Present a transformations activity for students to complete Get feedback from.
Choosing a Topic and Forming a Research Question Introduction Choosing and narrowing a topic Forming a research question Talk About It Your Turn Tech Tools.
Psychology 417A: Psychology and Developing Societies May 28 Class Meeting 8 Topic Placement Preparation: Socioeconomic Privilege and Service Learning as.
1 Some Guidelines for Good Research Dr Leow Wee Kheng Dept. of Computer Science.
1 Computational Vision CSCI 363, Fall 2012 Lecture 1 Introduction to Vision Science Course webpage:
Math Menu: Differentiated Instruction in Mathematics Tuesday, November 24, 2009 St. Roch S.S. Room 215.
Now what? 1.  I have short-listed projects I am interested in  I know the types of projects I would like to pursue  I have an idea of the resources.
CSE 5559 Computational Topology: Theory, algorithms, and applications to data analysis Lecture 0: Introduction Instructor: Yusu Wang.
UMass Lowell Computer Science Analysis of Algorithms Prof. Karen Daniels Fall, 2001 Review Lecture Tuesday, 12/11/01.
INFOMGP Student names and numbers Papers’ references Title.
Enacting variation theory in the design of task sequences in mathematics education Anne Watson VT SIG Oxford 2014 University of Oxford Dept of Education.
Exploring Similarity and Algebra Marian Small February, 2016.
13 strategies to use Powerpoint to support active learning in classroom.
IMS 4212: Course Introduction 1 Dr. Lawrence West, Management Dept., University of Central Florida ISM 4212 Dr. Larry West
HUT – DEPARTMENT OF MATH. APPLIED MATH 1 FUNCTION.
CS6501 Advanced Topics in Information Retrieval Course Policy
Advanced Image Processing
ECE 533 Digital Image Processing
CMSC201 Computer Science I for Majors Lecture 11 – Program Design
Foundations of Visualization 8/30/05 Lecture Notes
Presentation transcript:

Approaches to Representing and Recognizing Objects Visual Classification CMSC 828J – David Jacobs

What the course is about Visual Classification –Recognizing nouns and verbs from images. This is one of the key problems of vision/cognition. –~ half of cerebral cortex is vision. –Vision divides roughly into what and where. This class is about what.

This is very hard What is a class? –Ill-defined. –Tremendous variability. And how do we relate images to objects or actions? Current solutions grossly inadequate.

So how do we have a class about this? 1.Learn some fundamental things relevant to visual classification. 2.See how researchers have tried to apply these to visual classification.

Fundamental things Mostly lectures (but also discussion of some important papers). Much of it mathematical and computational –Geometry of projection and invariance; PCA; shape spaces and shape matching; wavelet representations of images; stochastic models of classes; learning theory. But we draw from other fields too: –Philosophy: what is a class? –Biology: how does shape vary in nature? –Psychology: How do people do classification?

Application of these ideas to visual classification Read papers and discuss. Shows how fundamental ideas can be used. How math and computation interact. Don’t solve big problem, but often useful for smaller problems.

Class Goal: Prepare us to solve problems of visual classification Learn fundamental concepts important for vision. Get us to think about what classification is. Understand state-of-the-art attempts to solve it.

Approaches to Visual Classification Definitional: a class is defined by the presence or absence of properties (a point in feature space). A class is a subspace of images. Class is determined by similarity of images. Class represented by a generative model. Classes and generic learning.

A tour of the syllabus Note no classes 10/14, 10/16.

How this might change Probably way too much material. Lectures may be longer than indicated. May merge classes: –16 & 17 (wavelets). –26 & 27 (linear separators).

Requirements (1) Read papers before they are presented. Paper reviews. –On classes where papers are presented, by me or students, you must turn in a 1 page review of one paper before class. –One paragraph summarizing main points. Doing this well is enough for a B. –One paragraph critiquing ideas, suggesting new directions. Do this well for an A. –20% of grade.

Requirements (2) Presentations –Students will be assigned in pairs to present and lead class discussion of two papers. –I will try to scare you into doing a good job. –Each student goes once (maybe twice). –Sign up for this by next Tuesday. –20% of grade.

Requirements (3) Midterm and Final –Will cover materials in lectures. –40% of grade.

Requirement (4) Project. Choose 1 –5 page research proposal. Extend or build on work discussed in class. Can focus on approaches you presented. –Programming project and write-up. Discuss with me first. Implement some method (eg., winnow, deformable template matching) and try on some data. Should be like long problem set, not like a big project. No incompletes.

Number of Credits 3 credits, do all 4. 2 credits, do credit, do 1-2.

Your Background Calculus, linear algebra, probability is essential. Math that makes you really learn these topics is important. Other math very helpful: functional analysis (fourier transforms), wavelets, geometry, stochastic processes, optimization. Knowledge of vision may help a little.

First Homework Readings for Thursday. Review is due. Choose papers to present by Tuesday 9/9.