Sayısal Görüntü İşleme Teknikleri

Sayısal Görüntü İşleme Teknikleri

Doç. Dr. Mehmet Serdar Güzel

Slides are mainly adapted from the following course page:

http://www.comp.dit.ie/bmacnamee

Lecturer



Instructor: Assoc. Prof Dr. Mehmet S Güzel

 Office hours: Tuesday, 1:30-2:30pm

 Open door policy – don’t hesitate to stop by!



Watch the course website

 Assignments, lab tutorials, lecture notes

•slide 2

Interesting article in the March, 2006

issue of Wired magazine

Read it here

Image Enhancement

(Spatial Filtering 1)

Contents



In this lecture we will look at spatial filtering techniques:

 Neighbourhood operations

 What is spatial filtering?

 Smoothing operations

 What happens at the edges?

 Correlation and convolution

Neighbourhood Operations



Neighborhood operations merely operate on a larger neighborhood of pixels than point operations



Neighborhoods are regularly a rectangle around a central pixel



Any size rectangle and any shape filter are possible

Origin x

y Image f (x, y)

(x, y)

Neighbourhood

Simple Operations



Some simple neighbourhood operations given as:

 Min: Set the pixel value to the minimum along the neighbourhood

 Max: Set the pixel value to the maximum along the neighbourhood

 Median: The median value of a set of numbers is the midpoint value in that set (e.g. from the set [11, 27, 35, 48, 54] 35 is the median). The median usually works better than the average

The Spatial Filtering Process

r s t

u y w

x y z

Origin x

y Image f (x, y)

e

= y *x +

r *a + s *b + t *c +

u *d + w *f +

x *g + y *h + z *i

Filter

3*3

Neighbourhood e 3*3 Filter

a b c

d x f

g h i

Original Image Pixels

*

This process is repeated for every pixel in the original

image to produce the enhanced image

Smoothing Spatial Filters

1

/

/

/

1

/

/

/

1

/

/

/

 Average Filtering

 Simply average all of the pixels in a neighbourhood around a central value

 Particularly useful in eliminating noise from images

 Also useful for highlighting unrefined feature

Averaging filter

example

Smoothing Spatial Filtering

1

/

/

/

1

/

/

/

1

/

/

/

Origin x

y Image f (x, y)

e =

/

*306 +

1

/

*194 +

/

*100 +

/

*108 +

1

/

*99 +

/

*98 +

1

/

*65 +

/

*70 +

/

*35 =

Average Filter

Simple 3*3

Neighbourhood ¹⁰⁶

104 99 95

100 108 98 90 85

1/₉ ¹/₉ ¹/₉

1/₉ ¹/₉ ¹/₉

1/₉ ¹/₉ ¹/₉

3*3 Smoothing Filter

194 100 108 99 306 98 65 70 35

Image Pixels

*

Weighted Smoothing Filters

2

/

/

/

4

/

/

/

2

/

/

/

 Pixels closer to the central pixel are more significant

 It is called as weighted averaging

Weighted

averaging filter