Final Lab Report

Department of Computer Science & Engineering
Jahangirnagar University
4th year 1st semester Final Exam-2020
FINAL LAB REPORT

Course code: CSE-408
Course title: DIGITAL IMAGE PROCESSING LABORATORY
Submitted to:
Dr. Liton Jude Rozario
Professor
CSE, JU
Submitted by:
Name - Rumana Yasmin
Roll - 341
Exam Roll - 170464
Registration no. - 44097
Session: 2016-17
Submission Date: 09-09-2021

Experiment Title:
Write a complete program in Python/MATLAB that reads a grayscale image from a
dataset, apply edge detection operation (e.g., using Sobel operator/Laplacian
operator/etc.).
Working Principle:
Edge detection is a technique in image processing which is used to identify points
in a digital image with discontinuities. This technique detects sharp changes in
the image brightness. These points where the image brightness varies sharply are
called the edges (or boundaries) of the image.
Here, I have used Sobel operator, Prewitt operator and Roberts Cross Gradient
operator to detect edges.
Sobel Edge Detector operator: When using Sobel Edge Detection, the image is
processed in the X and Y directions separately first, and then combined together to
form a new image which represents the sum of the X and Y edges of the image.
Sobel convolutional kernels are:
The gradient magnitude is given by:
Approximate magnitude is computed using:
Page 2 of 7
Prewitt Edge Detector operator:
When we apply this mask on the image it prominent vertical edges. It simply works
like as first order derivate and calculates the difference of pixel intensities in an edge
region. As the center column is of zero so it does not include the original values of
an image but rather it calculates the difference of right and left pixel values around
that edge. This increases the edge intensity and it becomes enhanced comparatively
to the original image.
Prewitt convolutional kernels are:
-1 0 1
Gx =
-1 0 1
-1 0 1
-1 -1 -1
Gy = 0 0 0
1 1 1
Gradient magnitude calculation:
Roberts Cross Gradient Detector:

The Roberts Cross operator performs a simple, quick to compute, 2-D spatial
gradient measurement on an image. It thus highlights regions of high spatial
frequency which often correspond to edges. In its most common usage, the input to
the operator is a grayscale image, as is the output.
Page 3 of 7
Roberts convolutional kernels are:
The gradient magnitude is given by:
Approximate magnitude is computed using:
Code in python:
import skimage.io as io
import skimage.filters as fl
import matplotlib.pyplot as plt
import skimage.exposure as ex
f = io.imread('D:\\Dataset\\7.1.05.tiff')
edge_s=fl.sobel(f)
edge_p=fl.prewitt(f)
edge_r=fl.roberts(f)
Page 4 of 7
plt.subplot(2,2,1)
plt.axis('off')
plt.title('Original image')
plt.imshow(ex.rescale_intensity(f,out_range=(0.0,1.0)),cmap='gray')
plt.subplot(2,2,2)
plt.axis('off')
plt.title('Image filtered with Sobel operator')
plt.imshow(ex.rescale_intensity(edge_s,out_range=(0.0,1.0)),cmap='gray')
plt.subplot(2,2,3)
plt.axis('off')
plt.title('Image filtered with Prewitt operator')
plt.imshow(ex.rescale_intensity(edge_p,out_range=(0.0,1.0)),cmap='gray')
plt.subplot(2,2,4)
plt.axis('off')
plt.title('Image filtered with Roberts operator')
plt.imshow(ex.rescale_intensity(edge_r,out_range=(0.0,1.0)),cmap='gray')
plt.show()
Page 5 of 7
Snapshot of input image:
Snapshot of output:
Page 6 of 7
Short Discussion:
The gradient differentiation operators like Prewitt, Sobel and Roberts share the same
principle of work. All of them use a separable kernel to calculate the gradient
approximation.
The main difference is that the Prewitt filter uses the same weight for all the pixels
that fall under the masks. Unlike Prewitt, Sobel operator give less weight to points
far from the center pixel. The major difference is that in Sobel operator the
coefficients of masks are not fixed and they can be adjusted according to our
requirement.
The Sobel operator is more sensitive to the diagonal edge is than to the horizontal
and vertical edges. On the contrary, Prewitt operator is more sensitive to horizontal
and vertical edges. Whereas, the results of Roberts cross gradient operation will
highlight changes in intensity in a diagonal direction.
Page 7 of 7

Final Lab Report

Uploaded by

Copyright:

Available Formats

Final Lab Report

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Final Lab Report

Uploaded by

Copyright:

Available Formats

Department of Computer Science & Engineering

FINAL LAB REPORT

Submission Date: 09-09-2021

The gradient magnitude is given by:

Approximate magnitude is computed using:

Gradient magnitude calculation:

Roberts Cross Gradient Detector:

The gradient magnitude is given by:

Approximate magnitude is computed using:

You might also like