Download as pdf or txt
Download as pdf or txt
You are on page 1of 5

K. J.

Somaiya College of Engineering, Mumbai-77


(Autonomous College Affiliated to University of Mumbai)

Batch: B3 Roll No.:1613095


Internal Assessment No.: 02
Grade: AA / AB / BB / BC / CC / CD / DD

Signature of the Staff In-charge with Date

TITLE: Mini Project


Title of Project: Real Time Edge Detection

Software Used: Matlab

________________________________________________________________________

Description:

Edge detection is one of the most commonly used operation in image analysis, and there are
probably more techniques for image enhance and detecting edges. An edge is a boundary between
two regions with relatively distinct gray-level properties. In the following discussion, the
assumption is that the region in questions are sufficiently homogenous so that the transition
between two regions can be determined on the basis of gray-level discontinuities alone. Such
discontinuities are detected by using: First-Order derivative and Second-order derivative.

Input images which could be colour or gray scale are provided as input to the workspace block. A
colour space conversion block converts RGB to gray scale image and this data which is in 2D is
to be converted to 1D for further processing. Image Video viewer block at output signal to show
the converted image(RGB to gray scale).

Objective

SIMULINK model in this file detects sobel edges in an real time vedio. The simulink model
displays the input acquired from the device camera one of them is original image and other image
will be binary which shows the sobel black colored edges, changes can be made by applying
median filter to smoot edges on high threshold values.

Department of Electronics and Telecommunication Engineering

SSL Sem-IV/Jan-May 2019 Page No.


K. J. Somaiya College of Engineering, Mumbai-77
(Autonomous College Affiliated to University of Mumbai)

Literature survey:

To understand the basics of camera analyzing, one must know how a computer perceives an image.
Edge detection is an image processing technique for finding the boundaries of objects within
images. It works by detecting discontinuities in brightness.

1. Read the input:

The first stage of any image processing task is to have an image. One can capture it from the
camera or load a previously clicked image from the memory as we are going to perform real time
processing we will be using Matlab image acquisition to get input from the system camera. Read
the input in grayscale 2D format as soble model in Simulink do not accept 3D colored images.

2. Applying Sobel edge detection operator:

The Sobel operator, sometimes called the Sobel–Feldman operator or Sobel filter, is used in image
processing and computer vision, particularly within edge detection algorithms where it creates an
image emphasizing edges. Technically, it is a discrete differentiation operator, computing an
approximation of the gradient of the image intensity function. At each point in the image, the result
of the Sobel–Feldman operator is either the corresponding gradient vector or the norm of this
vector. The Sobel–Feldman operator is based on convolving the image with a small, separable,
and integer-valued filter in the horizontal and vertical directions and is therefore relatively
inexpensive in terms of computations. On the other hand, the gradient approximation that it
produces is relatively crude, in particular for high-frequency variations in the image.

3.Taking complement:

Taking complement is just a process of converting all the whites in the image to black or
subtracting maximum intensity with actual intensity value. Purpose of doing this is to get black
edges instead of white.

4.Output:

The Sobel-Feldman operator represents a rather inaccurate approximation of the image gradient,
but is still of sufficient quality to be of practical use in many applications. More precisely, it uses
intensity values only in a 3×3 region around each image point to approximate the corresponding
image gradient, and it uses only integer values for the coefficients which weight the image
intensities to produce the gradient approximation

Department of Electronics and Telecommunication Engineering

SSL Sem-IV/Jan-May 2019 Page No.


K. J. Somaiya College of Engineering, Mumbai-77
(Autonomous College Affiliated to University of Mumbai)

.Algorithms:

Simulink model:

Department of Electronics and Telecommunication Engineering

SSL Sem-IV/Jan-May 2019 Page No.


K. J. Somaiya College of Engineering, Mumbai-77
(Autonomous College Affiliated to University of Mumbai)

Results /graphs :

Conclusions:

The Simulink Model based Image Segmentation is a new application in image processing and
offers a model based design for processing. The filters are designed by blocks and it even support
Matlab codes through user customizable blocks. It also offers an ease of designing with GUI
environment. This tool supports software simulation which is important to avoid high level
language for coding. These features are essential in real time image processing.

The result of this detection depends on the threshold value. The major problem with thresholding
is that it considers only intensity values of the pixels and does not take into consideration any
relationship between them. Sometimes extra pixels are detected which are not the part of the
desired region, and with increase in noise these errors increases.

Department of Electronics and Telecommunication Engineering

SSL Sem-IV/Jan-May 2019 Page No.


K. J. Somaiya College of Engineering, Mumbai-77
(Autonomous College Affiliated to University of Mumbai)

Future scope:

Edge detection is used for image segmentation and data extraction in areas such as image
processing, computer vision, and machine vision.

1. Computer vision- Edge detection is the basic and important step for proceeding in computer
vision. Computer vision (image processing) can be used along with neural networks to provide an
object detection based on their shape.

2. Spy robots- The spy robots are made to identify objects in the place where they are launched.
Object‟s shape, size, color, orientation is of importance to robot.

3. Object Segregation- An object can be segregated (separated) on the basis of its shape.

References:

1. Mathworks Inc. “Simulink 3.0”,http://www.mathworks.com/products/Simulink/.


2. The Mathworks Inc., “MATLAB 7.1”, http://www.mathworks.com/products/matlab/
3. J.M.H du Buf M. Kardan and M.spann, Texture feature performance for image segmentation,
Pattern Recognition,23:291-309, 1990.

Signature of Faculty with Date:

Department of Electronics and Telecommunication Engineering

SSL Sem-IV/Jan-May 2019 Page No.

You might also like