Scribd
Upload
37 views10 pages

Deep Learning

The document discusses spatial filtering techniques in digital image processing. It describes common filtering operations like highpass filtering, lowpass filtering, and smoothing filters. It also covers concepts like convolution, correlation, and separable filters that are important to spatial filtering.

Uploaded by

DSEC-MCA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
37 views10 pages

Deep Learning

The document discusses spatial filtering techniques in digital image processing. It describes common filtering operations like highpass filtering, lowpass filtering, and smoothing filters. It also covers concepts like convolution, correlation, and separable filters that are important to spatial filtering.

Uploaded by

DSEC-MCA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

DEEP LEARNING

Spatial Filtering

SIVAHARI R
II-MCA
810422621054
WHAT IS SPATIAL FILTERING?
Spatial filtering term is the filtering operations
that are performed directly on the pixels of an
image.

The concept of filtering has its roots


in the use of the Fourier transform for
signal processing in the so-called
Frequency Domain.
Filtering is a fundamental signal processing
operation, and often a pre-processing operation
before further processing.
Background Highpass Filtering

Filter term in “Digital Image The Highpass Filter will


Processing” is referred to the sub-image. highlight all the high
frequencies.
There are other term to call sub-
image such as mask,kernel, template Lowpass Filtering
or window.
The Lowpass Filter is a
different configuration of
The value in a filter sub-image are
weights
referred as coefficients, rather than that aims to create an image
pixels. represented by the low
frequencies.
Mechanics of Spatial Filtering

The process consists simply of moving the


filter mask from point to point in an image.

At each point (x , y) the response of the filter


at that point is calculated using a predefined
relationship.
Concepts of Image Filtering
Convolution
The filtered image is the convolution of the
original image with the filter impulse response
(or “mask”).
So, if f(x , y) denotes the original image and w(x , y)
the filter impulse response, then their convolution is:
Correlation
The book mention the concept of correlation,
which is somewhat similar to convolution.
Mathematically is

Differences to statistics:
This is called cross-correlation in statistics.
Here, the normalizing factor can be neglected.
This concept is important for application such as
matched filtering.
Separable Filters

Separable filters represent a subset of all possible


linear filters.
An image filter is separable if it can be express as
the outer product of two vectors.
Example :
Smoothing Filters

Averaging Filters

Basic idea: replace each pixels by the average of the


pixels in a square window surrounding pixels.
 Example: for a 3x3 averaging filter.
Sharpening Filters
Image Sharpening
The main idea of sharpening is the enhance line
structures of the detailed in an image.
Thus, the enhance image contains the original
image with the line structures and edges in the
image emphasized.
Line structures and edges can be
obtained by applying a difference operator
(an high-pass filter) on the image.

Resulting operation is a weighted


averaging operation, in which some
weights will be negative.
Thank you

You might also like