Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
107 views

015 Image-Smoothing-Basic-Concepts

Neighborhood operations operate on pixels within a rectangular region surrounding the center pixel. Common neighborhood operations include setting the pixel value to the minimum, maximum, or mean value within the neighborhood. Spatial filtering replaces each pixel value with a weighted average of its neighborhood. This smoothing reduces noise but can blur edges. Larger neighborhoods cause more detail loss. Weighted averaging filters give closer pixels more influence to reduce blurring compared to uniform averaging filters. Median filters sometimes perform better than averaging for noise removal. Edges require special handling since neighborhoods extend beyond the image bounds.

Uploaded by

Hilbert
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
107 views

015 Image-Smoothing-Basic-Concepts

Neighborhood operations operate on pixels within a rectangular region surrounding the center pixel. Common neighborhood operations include setting the pixel value to the minimum, maximum, or mean value within the neighborhood. Spatial filtering replaces each pixel value with a weighted average of its neighborhood. This smoothing reduces noise but can blur edges. Larger neighborhoods cause more detail loss. Weighted averaging filters give closer pixels more influence to reduce blurring compared to uniform averaging filters. Median filters sometimes perform better than averaging for noise removal. Edges require special handling since neighborhoods extend beyond the image bounds.

Uploaded by

Hilbert
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Image Smoothing

Neighbourhood Operations
What are Neighbourhood Operations

 Neighbourhood operations simply operate on Origin x


a larger neighbourhood than pixel itself

 Neighbourhood are mostly a rectangle


around a centre pixel
(x, y)
Neighbourhood
 This rectangle can be of any size

y Image f (x, y)
Simple Neighbourhood Operations

 These include:
 Min: Set the pixel value to the minimum in the neighbourhood

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

 Mean: Set the pixel value to the neighbourhood mean

 Weighted Mean: Set pixel value to weighted neighbourhood mean


The Spatial Filtering Process
Origin x
a b c r s t
d
g
e
h
f
i
* u
x
v
y
w
z
Original Image Filter
Simple 3*3 Pixels
e 3*3 Filter
Neighbourhood
eprocessed = v*e +
r*a + s*b + t*c +
u*d + w*f +
y Image f (x, y) x*g + y*h + z*i

The above process is repeated for each and every pixel to get filtered image
Smoothing Spatial Filters
 One of the simplest spatial filtering operations we can perform is a un-
weighted smoothing process
 Simply average all of the pixels in a neighbourhood around a central value
 Especially useful in removing noise from images but may lead to edge blurring
 Also useful for highlighting gross detail

1/ 1/ 1/
9 9 9

Simple Averaging
1/ 1/ 1/
Filter 9 9 9

1/ 1/ 1/
9 9 9
Image Smoothing Example

 The image at the top left is an original image of


size 500*500 pixels

 The subsequent images show the image after


filtering with an un-weighted averaging filter of
increasing rectangular filter sizes
 3, 5, 9, 15 and 35

 Notice how detail begins to disappear with


increase in neighbourhood size
Weighted Smoothing Filters

 More effective smoothing filters can be generated by allowing different pixels


in the neighbourhood different weights in the averaging function
 Pixels closer to the central pixel are more important

 Often referred to as a weighted averaging 1/ 2/ 1/


16 16 16
 Less blurring compared to un-weighted filter
2/ 4/ 2/
16 16 16

1/ 2/ 1/
16 16 16

Weighted averaging
filter
Averaging Filter Vs. Median Filter Example

Original Image Image After Image After


With Noise Averaging Filter Median Filter

 Filtering is often used to remove noise from images

 Sometimes a median filter works better than an averaging filter


Strange Things Happen At The Edges!
However strange things happen at the edges of an image since we are missing
pixels to form a neighbourhood

Origin x
e e

e e e
y Image f (x, y)

You might also like