MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING

kettledoctorΤεχνίτη Νοημοσύνη και Ρομποτική

15 Οκτ 2013 (πριν από 4 χρόνια και 25 μέρες)

104 εμφανίσεις

1

MACHINE LEARNING TECHNIQUES

IN IMAGE PROCESSING


By Kaan Tariman

M.S. in Computer Science

CSCI 8810 Course Project

2

Outline


Introduction to Machine Learning


The example application


Machine Learning Methods


Decision Trees


Artificial Neural Networks


Instant Based Learning


3

What is Machine Learning


Machine Learning (ML) is constructing
computer programs that develop solutions
and improve with experience


Solves problems which can not be solved
by enumerative methods or calculus
-
based
techniques


Intuition is to model human way of solving
some problems which require experience


When the relationships between all system
variables is completely understood ML is
not needed

4

A Generic System

System





Input Variables:

Hidden Variables:

Output Variables:

5

Learning Task


Face recognition
problem: Whose face is
this in the picture?


Hard to model
describing face and its
components


Humans recognize with
experience: The more
we see the faster we
perceive.



6

The example


Vision module for Sony Aibo Robots that we
have developed for Legged Robot
Tournament in RoboCup 2002.


Output of the module is

distance and
orientation of the target objects:


the ball,


the players


the goals


the beacons
-

used for localization of the robot.

7

Aibo’s View

8

Main ML Methods


Decision Trees


Artificial Neural Networks (ANN)


Instant
-
Based Learning


Bayesian Methods


Reinforcement Learning


Inductive Logic Programming (ILP)


Genetic Algorithms (GA)


Support Vector Machines (SVM)

9

Decision Trees


Approximation of
discrete functions
by a decision tree.


In the nodes of
trees are attributes
and in the leaves
are values of
discrete function


Ex: A decision tree
for “play tennis”

10

Algorithm to derive a tree


Until each leaf node is populated by
as homogeneous a sample set as
possible:


Select a leaf node with an
inhomogeneous sample set.


Replace that leaf node by a test node
that divides the inhomogeneous sample
set into minimally inhomogeneous
subsets, according to an entropy
calculation.

11

Color
Classification


Data set includes
pixel values labeled
with different colors
manually


The tree classifies a
pixel to a color
according to its
Y,U,V values.


Adaptable for
different conditions.


12

How do we construct the data set?

1) Open an image taken by the robot

13

How do we construct the data set?

2) Label the pixels with colors

[Y,U,V,color] entries are created for each pixel labeled

14

How do we construct the data set?

3) Use the ML method and display results

15

The decision tree
output


The data set is divided
into training and
validation set


After training the tree
is evaluated with
validation set.


Training should be
done carefully,
avoiding bias.

16

Artificial Neural Networks (ANN)


Made up of interconnected processing
elements which respond in parallel to a set
of input signals given to each



17

ANN Algorithm


Training algorithm adjusts the
weights reducing the error
between the known output values
and the actual values


At first, the outputs are arbitrary.


As cases are reintroduced
repeatedly ANN gives more right
answers.


Test set is used to stop training.


ANN is validated with unseen data
(validation set)

18

ANN output for our example

19

Face Recognition with ANN


Problem: Orientation of face


Input nodes are pixel values
of the image. (32 x 32)


Output has 4 nodes (right,
left, up, straight)


6 hidden nodes

20

Face Recognition with ANN


Hidden nodes normally does not infer
anything, in this case we can observe some
behavior.

21

Instance Based Learning


A learn
-
by
-
memorizing method:
K
-
Nearest
Neighbor


Given a data set {X
i
, Y
i
} it estimates values
of Y for X's other than those in the sample.


The process is to choose the
k

values of X
i

nearest the X and average their Y values.


Here k is a parameter to the estimator. The
average could be weighted, e.g. with the
closest neighbor having the most impact on
the estimate.

22

KNN facts


Database of
knowledge about
known instances is
required


memory
complexity


“Lazy learning”, no
model for the
hypothesis


Ex: Color classification


A voting method is
applied in order to
output a color class for
the pixel.


23

Summary


Machine Learning is an interdisciplinary
field involving programs that improve by
experience


ML is good for pattern recognition, object
extraction and color classification etc.
problems in image processing problem
domain.


3 methods are considered:


Decision Trees


Artificial Neural Networks


Instant Based Learning



24

Thank you!