Introduction to

Image
Processing &
Computer
Insert Your Picture Here
Vision
M Yogi Reddy
Assistant Professor
CSE Department
School Of Technology
GITAM(Deemed to be ) University
Hyderabad

PAGE 1
Agenda

Introduction to Image processing

Image Noise
Removal of Noise from Images
Color Enhancement
Segmentation
Edge Detection

PAGE 2
PAGE 3
Introduction to Image processing
Image processing is a method to perform some operations on an
image, in order to get an enhanced image or to extract some useful
information from it.
It is a type of signal processing in which input is an image and output
may be image or characteristics/features associated with that image.
Image processing basically includes the following three steps:
1. Importing the image via image acquisition tools;
2. Analyzing and manipulating the image;
3. Output in which result can be altered image or report
that is based on image analysis.

PAGE 4
What is image acquisition

PAGE 5
PAGE 6
Computer Vision

 To emulate human vision, including learning and being able to make inferences
and take actions based on visual inputs.
 It is concerned with the automatic extraction, analysis and understanding of useful
information from a single image or a sequence of images.

PAGE 7
Computer Vision

PAGE 8
PAGE 9
Image is defined as

An image is formed by two-dimensional analog and the digital signal

that contains color information arranged along x and y spatial axis.
The value of f(x , y) at any point is gives the pixel value at that point of
an image.
The full form of the pixel is "Picture Element." It is also known as
"PEL." Pixel is the smallest element of an image on a computer
display, whether they are LCD or CRT monitors. A screen is made up of
a matrix of thousands or millions of pixels. A pixel is represented with
a dot or a square on a computer screen.

PAGE 10
The given figure is an example of
digital image that you are now
viewing on your computer screen.
But actually , this image is nothing
but a two dimensional array of
numbers ranging between 0 and 255.
There are two types of methods used
for image processing namely,
1. Analogue image processing
2. Digital image processing

PAGE 11
 Analog image processing is applied on analog signals and it processes
only two-dimensional signals. The images are manipulated by electrical
signals. Examples of analog images are television images, photographs,
paintings, and medical images etc.

 A digital image processing is applied to digital images (a matrix of

small pixels and elements). For manipulating the images, there is a
number of software and algorithms that are applied to perform
changes. Digital image processing is one of the fastest growing industry
which affects everyone's life. Examples of digital images are color
processing, image recognition, video processing, etc.

PAGE 12
Types of images

Binary images (Black and White)

 Each pixel is just black or white
 There is only two possible values for each pixel i.e. 0 or 1

PAGE 13
Gray-scale images
 Each pixel value of gray scale images normally
from 0 (black) to 255 (white).

255 255 255

155 155 155

0 0 0

11111111 11111111 11111111

10011011 10011011 10011011

00000000 00000000 00000000

PAGE 14
Color images
In color images each pixel has a particular color ; that color
being described by the amount of red, green and blue in it.
Each of these components has a range 0 to 255.

PAGE 15
Image Noise
 Noise represents unwanted information in an image.
 Image noise is random variation of brightness or color information in the
images captured.
 It is degradation in image signal caused by external sources.

A(x, y) = H(x, y) + B(x, y)

Where,
A(x , y)= function of noisy image
H(x , y)= function of image noise
B(x , y)= function of original image

PAGE 16
Sources of Image Noise

Our main concern is to remove certain kind of noise. So we have

to first identify certain type of noise and apply different algorithms
to remove the noise.

PAGE 17
Types of image noise

PAGE 18
Photon/shot/Poisson Noise
This is a type of noise connected to the uncertainty associated with
the measurement of light.
When the number of photons sensed by the sensors from the
camera is not sufficient to get meaningful information from the
scene photon noise arises.
This noise occurs mostly in poor or low lighting conditions.

PAGE 19
Thermal/ Johnson-Nyquist/Gaussian Noise
Gaussian noise is evenly distributed over signal.
This means that each pixel in the noisy image is the sum of the true pixel
value and a random Gaussian distributed noise value.
Random Gaussian function is added to Image function to generate this
noise.
The noise is independent of intensity of pixel value at each point.

PAGE 20
Impulse/salt and Pepper Noise
 Salt Noise: Salt noise is added to an image by addition of random bright (with
255 pixel value) all over the image.
 Pepper Noise: Salt noise is added to an image by addition of random dark (with
0 pixel value) all over the image.
 Salt and Pepper Noise: Salt and Pepper noise is added to an image by addition
of both random bright (with 255 pixel value) and random dark (with 0 pixel
value) all over the image.

PAGE 21
Speckle Noise
 Speckle noise can be generated by multiplying random pixel values with
different pixels of an image.
 P = I + n * I Where P is the speckle noise distribution image, I is the input
image and n is the uniform noise image by mean o and variance v.
 Speckle is a granular noise that inherently exists in an image and degrades its
quality.

PAGE 22
Removal of Noise from Images
Image de-noising is very important task in image processing for the
analysis of images.
One goal in image restoration is to remove the noise from the image in
such a way that the original image is discernible.
Image de-noising is often used in the field of photography or publishing
where image was somehow degraded but needs to be improved before
it can be printed.
There are two types of noise removal approaches
1. Linear Filtering
2. Non Linear Filtering
PAGE 23
Linear Filtering:
 Linear filters are used to remove certain types of noise.
 These filters remove noise by convolving the original image with a
mask filters also tend to blur the sharp edges, destroy the lines and
other fine details of the image
Non-Linear Filtering:
 Non- linear filter is a filter whose output is not a linear function of
its inputs.
 The general idea in non-linear image filtering is that instead of using
the spatial mask in a convolution process, the mask is used to
obtain the neighboring pixel values, and then ordering mechanisms
produce the output pixel.
PAGE 24
Different types of linear and non-linear filters:

Mean Filter

Median Filter

Adaptive Filter

Gaussian Filter

Weinier Filter
PAGE 25
Image Enhancement

• Image enhancement is the process of adjusting digital images so that the results are

more suitable for display or further image analysis. For example, you can remove

noise, sharpen, or brighten an image, making it easier to identify key features.

• Here are some useful examples and methods of image enhancement:

Filtering with morphological operators

Histogram equalization

Noise removal
PAGE 26
Image enhancement algorithms include de-blurring, filtering, and
contrast methods

PAGE 27
Color Enhancement

 Color enhancement refers to any type of process or treatment that modifies or

enhances the color of a natural image.

PAGE 28
Color Enhancement can be done by adjusting the red/green/blue values for a pixel
as follows:
1. find the maximum of the three input values
2. scale RGB values downward by taking a power of their fraction of this maximum.
3. Multiply the result value maximum of three input values

So, for instance, if the three values are

red: 140 green: 105 blue: 201
the "enhancement factor" is 2.0, then
Red -> ((140/201)^2.0) * 201 = 97
Green -> ((105/201)^2.0) * 201 = 55
Blue -> ((201/201)^2.0 )* 201 = 201

and the pixel goes from somewhat blue to very blue.

The visual affect is to "enhance" the color without changing very much the perceived
intensity.
PAGE 29
Segmentation
 Image segmentation is the process of partitioning a digital image into multiple
segments (sets of pixels, also known as image objects).
 The goal of segmentation is to simplify and/or change the representation of an
image into something that is more meaningful and easier to analyze.

PAGE 30
Some of the practical applications of image segmentation are:
 Object detection
 Pedestrian detection
 Face detection
 Brake light detection
 Locate objects in satellite images (roads, forests, crops, etc.)
 Recognition Tasks
 Face recognition
 Fingerprint recognition
 Iris recognition
 Traffic control systems
 Video surveillance
 Video object co-segmentation and action localization

PAGE 31
Edge Detection
 Edge detection is the process of finding the set of pixels that represent the boundary of disjoint
regions in an image.

 Edge detection is important for image segmentation, since many image processing algorithms are first
required to identify the objects and then process them.

PAGE 32
PAGE 33
Optical Character Recognition

 Optical Character Recognition (OCR) defines the process of mechanically or

electronically converting scanned images of handwritten, typed or printed text into
machine-encoded text.
 It will learn and recognize the letters, but not the meaning of the word.

PAGE 34
WHAT IS OCR TECHNOLOGY?
 OCR technology deals with the problem of recognizing all kinds of different
characters.
 Both handwritten and printed characters can be recognized and converted into a
machine-readable, digital data format.

PAGE 35
Three basic steps of optical character recognition(OCR)

Step 1: Image Pre-Processing in OCR

Step 2: Character Recognition in OCR

Step 3: Post-Processing in OCR

PAGE 36
Step 1: Image Pre-Processing in OCR
 OCR software often pre-processes images to improve the chances of successful recognition.
 The aim of image pre-processing is an improvement of the actual image data.
 In this way, unwanted distortions are suppressed and specific image features are enhanced.

Step 2: Character Recognition in OCR

 For the actual character recognition, it is important to understand what “feature extraction” is.
 When the input data is too large to be processed, only a reduced set of features is selected.
 The features selected are expected to be the important ones while those that are suspected to be
redundant are ignored.
 For the process of OCR, the algorithm has to detect specific portions or shapes of a digitized
image or video stream.

Step 3: Post-Processing in OCR

 Post-processing is another error correction technique that ensures the high accuracy of OCR.
 The accuracy can be further improved if the output is restricted by a lexicon.
PAGE 37
Applications of OCR:
Identification Processes
Payment Processes
• License Plate Scanning
• Passport /Driver’s License Scanning
• Serial Number Scanning
• Document Scanning
• Vehicle Identification Number Scanning
• Barcode Scanning

PAGE 38
Feature Detection
 In computer vision and image processing feature detection includes methods for
computing abstractions of image information and making local decisions at every
image point whether there is an image feature of a given type at that point or not.
 The resulting features will be subsets of the image domain, often in the form of
isolated points, continuous curves or connected regions.
Definition of Feature:
 a feature is typically defined as an "interesting" part of an image, and features are
used as a starting point for many computer vision algorithms.

PAGE 39
Main Component of Feature
Detection

Detection: Identify the Interest Point

Description: The local appearance around each feature point is described in some
way that is (ideally) invariant under changes in illumination, translation, scale,
and in-plane rotation. We typically end up with a descriptor vector for each
feature point.

PAGE 40
Types of Image Features:
1. Edges
 Edges are points where there is a boundary (or an edge) between two image regions.
 In general, an edge can be of almost arbitrary shape, and may include junctions. In
practice, edges are usually defined as sets of points in the image which have a strong
gradient magnitude.
 Locally, edges have a one-dimensional structure.

2. Corners / interest points

 The terms corners and interest points are used somewhat interchangeably and refer
to point-like features in an image, which have a local two dimensional structure.
 The name "Corner" arose since early algorithms first performed edge detection, and
then analysed the edges to find rapid changes in direction (corners).
PAGE 41
3. Blobs / regions of interest points
 Blobs provide a complementary description of image structures in terms of regions,
as opposed to corners that are more point-like.
 Nevertheless, blob descriptors may often contain a preferred point (a local
maximum of an operator response or a center of gravity) which means that many
blob detectors may also be regarded as interest point operators.
 Blob detectors can detect areas in an image which are too smooth to be detected by
a corner detector.

PAGE 42
Recognition
 Image recognition is the ability of a system or software to identify objects, people,
places, and actions in images.
 It uses machine vision technologies with artificial intelligence and trained algorithms
to recognize images through a camera system.
 While human and animal brains recognize objects with ease, computers have
difficulty with the task. Software for image recognition requires
deep machine learning. Performance is best on Convolutional Neural Network
(CNN) processors.

PAGE 43
Google, Facebook, Microsoft, and Apple are among the many companies
that are investing significant resources and research into image
recognition and related applications.

PAGE 44
Save Trees
And
Save Power
PAGE 45