Download presentation
1
Chapter 5: Neighborhood Processing
Point processing: applies a function to each pixel Neighborhood processing: applies a function to a neighborhood of each pixel
2
○ Neighborhood (mask) -- can have different shapes and sizes
3
○ Function + Mask = Filter
Input signal Output signal Filter
4
1D 2D
5
◎ Linear filter: linear combination of the gray
values in the mask
7
。 Example
8
○ Processing near image boundaries
Ignore the boundary Pad with zeros (c) Copy boundary ○ Values outside the range 0-255 Clip values Scale values
9
◎ Convolution 5-9
10
Discrete: Compared with Linear filtering:
11
◎ Correlation
12
◎ Smoothing Filters ○ Averaging filters Input X X X7
13
○ Gaussian filters (1-D): (2-D):
14
Averaging filters Gaussian filters
15
○ Separable filters e.g., Laplacian filter
16
n × n filter: 2 (n × 1) filters:
17
Frequency domain filters:
19
can be written in complex form
where The relationships between their coefficients 3-19
22
Frequency: a measure by which gray
values change with distance
23
Low pass filter High frequency components, e.g., edges, noises
Low frequency components, e.g., regions Frequency domain Spatial domain Fourier transform Low pass filter High pass filter
24
Fourier transform Input image Low pass High pass
25
Output ○ In spatial domain Low pass filter High pass filter e.g., LoG
e.g., Averaging filter High pass filter e.g., LoG
26
◎ Edge Sharpening or Enhancement
○ Unsharp masking
27
。 Idea of unsharp masking
(a) Edge (b) Blurred edge (a) – k × (b)
28
。 Perform using a filter
。 Alternatives (a) (b) The averaging filter can be replaced with any low pass filters
29
。 Example: (a) Original (b) Unsharp Masking
30
○ High-boost filter high boost = A(original) – (low pass) = A(original) – ((original) - (high pass) = (A-1)(original) + (high pass) 。 Alternatives: (a) (A/(A-1))(original) + (1/(A-1))((low pass) (b) (A/(2A-1))(original) + ((1-A)/(2A-1))((low pass)
31
。 Example: (a) (A/(A-1))(original) + (1/(A-1))((low pass)
(b) (A/(2A-1))(original) + ((1-A)/(2A-1))((low pass)
32
◎ Non-linear smoothing filters
: mask elements 。 Maximum filter: 。 Minimum filter:
33
。 Median filter 。 K-nearest neighbors (K-NN) 。 Geometric mean filter 。 Alpha-trimmed mean filter i) Order elements ii) Trim off m end elements iii) Take mean
34
◎ Region of Interest Processing
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.