1
Shreyashi Sharma
TEXTURE FEATURE
CLUSTERING FOR
CONTENT BASED IMAGE RETRIEVAL
Abstract Content based image retrieval is the task of
retrieving images from a database based on the contents of the
image like color, texture, shape or any other information
CNT 5106C
Fall 2015
Homework Assignment 1
Due Date: October 6, 2015
Please submit the homework answers via Canvas.
Chapter 1 problems:
1. P2. d = N.L/R
The above equation gives a formula for the end-to-end delay of sending one packet of length L
over N li
EEL6825: Pattern Recognition
Homework 2
Problem 4 in Chapter 3, on Page 141 of the textbook: Richard O. Duda, Peter E.
Hart, David G. Stork, Pattern Classification, 2nd Edition, Wiley-Interscience, October
2000.
Problem 4 is given as below:
Let x be a d-d
EEL 6825
Pattern Recognition
Lecture 12
Clustering
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Clustering (1)
The objective of clustering is to partition a set of objects
into multiple groups so
EEL 6825
Pattern Recognition
Lecture 7
Graphical Models
Part I
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
(Courtesy of Christopher Bishop)
Motivation of Using Graphical Models
Graphical models
80 CHAPTER 3. MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION
We solve this equation and find
3
(1 — thll Zzik = Pit-01‘) (1— zik),
Ic=1
which can be rewritten as
2 22-15 = Phui) Z Z“: + — 13(Lu‘i) Zzik.
k:1 12:1 k=1
The final solution is then
That is, the esti
EEL6825: Pattern Recognition
Homework 4
Problem 14 in Chapter 10, on Page 587 of the following textbook: Richard O. Duda,
Peter E. Hart, David G. Stork, Pattern Classification, 2nd Edition, Wiley-Interscience,
October 2000.
Problem 14 is given as below:
L
EEL 6825
Pattern Recognition
Lecture 5
Expectation Maximization (EM) Algorithm
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Outline
Motivation: missing data estimation
EM algorithm
Gaussian mixtu
EEL 6825
Pattern Recognition
Lecture 3
Bayesian Decision Theory
Part II
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Outline
Discriminant functions: a representation
of pattern classifiers (or de
EEL 6825
Pattern Recognition
Lecture 9
Graphical Models
Part III
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
(Courtesy of Christopher Bishop)
Inference in Graphical Models
Inference on a Chain
I
EEL 6825
Pattern Recognition
Lecture 8
Graphical Models
Part II
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
(Courtesy of Christopher Bishop)
Conditional Independence
a is independent of b given
EEL 6825
Pattern Recognition
Lecture 6
Bayesian Estimation
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Definition of Bayesian Estimator
Suppose an unknown parameter is known to have a
prior dist
EEL 6825
Pattern Recognition
Lecture 10
Linear Models for Regression
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
(Courtesy of Christopher Bishop)
Linear Basis Function Models (1)
Example: Polyno
EEL 6825
Pattern Recognition
Lecture 11
Nonparametric Techniques
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Density Estimation
In Ch. 3, we assume we know the pdf p(x|) or p(|x),
then we can us
EEL 6825
Pattern Recognition
Lecture 13
Kernel Methods
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Why Use Kernel Methods?
Due to the recent explosion of data from all fields of
science, there i
EEL6825: Pattern Recognition
Homework 3
Problem 14 (a) in Chapter 3, on Page 144 of the following textbook: Richard O. Duda,
Peter E. Hart, David G. Stork, Pattern Classification, 2nd Edition, Wiley-Interscience,
October 2000.
Problem 14 (a) is given as b
EEL 6825
Pattern Recognition
Lecture 4
Maximum Likelihood Estimation
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Unknown Prior and Likelihood
In the past, we saw how we could design an optimal
c
EEL6825: Pattern Recognition
Homework 1
Problem 25 in Chapter 2, on Page 72 of the following textbook: Richard O. Duda,
Peter E. Hart, David G. Stork, Pattern Classification, 2nd Edition, Wiley-Interscience,
October 2000.
Problem 25 is given as below:
Fil
EEL 6825
Pattern Recognition
Lecture 1
Introduction to Pattern Recognition
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Outline
Syllabus
What is pattern recognition (PR)?
Types of PR problems
An
EEL 6825
Pattern Recognition
Lecture 2
Bayesian Decision Theory
Part I
Dr. Dapeng Oliver Wu
University of Florida
Department of Electrical and Computer
Engineering
Spring 2016
Outline
Basic concepts in probability theory
MAP decision rule
Bayes decision r
EEL6825 Pa*ern Recogni3on
2012 January 10
Pa*ern Recogni3on Intro
Sequences
Observa3on
Characteris3cs of Dr. McNeill
Can you make a computer do all the
pa*ern recogni3on/classica3on you
just did?
The goal of this
EEL6825
2012 January 19
Prairie Dog Language
Do prairie dogs communicate details about
predators in their warning calls?
Spectrogram of Prairie Dog Calls
[1] C.N. Slobodchiko, A. Paseka, and J.L. Verdolin, Prairie do
EEL6825
2012 January 24
Row vs Column
Matrix Inverses
doc inv in Matlab
Normal DistribuDon ProjecDons
2I
Case 1: i =
2I
Case 1: i =
2I
Case 1: i =
2I
Case 1: i =
2I
Case 1: i =
2I
Case 1: i =
EEL6825
2012 February 9
Pa3ern Rec Applica;on
h3p:/pe.usps.com/text/dmm300/102.htm
Homework #03
h3p:/www.mcneill.ece.u.edu/eel6825/HW/
EEL6825HW03.pdf
Histogram Modeling
Explain what the dierence between i and li
when calcu
* We aren't endorsed by this school
