University Institute of Engineering

DEPARTMENT OF COMPUTER
SCIENCE & ENGINEERING

Bachelor of Engineering (Computer Science & Engineering)

Subject Name : Computer Vision
Subject Code : CSH-422
Topic : Digital Image Representation
Lecture – 1.1.1
By- Er. Anju

DISCOVER.LEARN.EMPOWER
Syllabus
UNIT I
 Introduction to image processing:
Digital Image representation
Sampling & Quantization
Steps in image processing
Image acquisition
Color image representation
Intensity transform functions
Histogram processing
Spatial filtering
Fourier transforms and its properties
Frequency domain filters Hough transformation
Image noise and restoration
 UNIT II
 Color Image Processing:
Color Fundamentals

Color Models

Pseudo color image processing

Image processing using Neural network and its performance metrices (Confusion

Matrix)

Introduction to basic operation on binary and grayscale images : Dilation, Erosion

Opening & closing Morphological Algorithms : Boundary & Region Extraction,

Convex Hull, Thinning, Thickening, Skeletons, Pruning

 UNIT III
 Image Segmentation, representation and description
Point, Line, Edge and Corner detection

Thresholding

Edge and boundary linking

Region based segmentation

Boundary representations

Region representations

Boundary Descriptors

Regional Descriptors

Image Wrapping
Introduction to Computer Vision

 What is the meaning of Vision?

 What is Human Vision?
 How Human Vision works?
 What is the Computer Vision?
 How Computer Vision works?
Vision – The state of being able to see
Human Vision – is the process by which
our eyes and brain work together to see.
How Human Vision Works?

Light
Focuses Converts Sends to
Enters
Light to signal brain
Eyes

Brain
creates
images
How Human vision works?

 Light Enters Eye: Light from environment enters the eye.

 Focuses Light : The lens inside the eye focuses the light onto the retina.
 Converts to signals : The retina converts the light into electrical signals.
 Sends to brain: These signals are sent to brain via the optic nerve.
 Brain create images : The brain processes the signals to create the
images we see.
Computer Vision

“ Computer Vision is a field of computer science that

works on enabling computers to see, identify and
process images in the same way that human vision does
and provide appropriate output.”
Computer Vision

 Building machines that see

 Objectives: Machines can interact with world
 Input is digital images and videos and output is interpretations.
 Human Vision

Seeing Intelligent
Processing Decision

 Computer Vision

Camera
Image Processing Pattern recognition &
Image
Pre- processing AI algorithms
Acquisition
Decision making
 Fundamental Steps of Computer Vision

Image
Feature
Preprocessing & Classification
Extraction
Segmentation
Input Object Feature Object
image image Vector type
What is Digital Image Processing?

 What is image? : Projection of 3D scene in

Y Y
2D plane.

X
Z
X
What is Image?

 A two - dimensional function, f(x , y), where x and y are spatial

coordinates, and f at any pair of coordinates (x , y) is called the
intensity or gray level of the image at that point.
Types of images

 Two types:
(a) Analog image
(b) Digital image
What is Analog image?

 Image : A two - dimensional function, f(x , y), where x and y are

spatial coordinates, and f at any pair of coordinates (x , y) is
called the intensity or gray level of the image at that point.
 When above mathematical representation has continuous range
of values representing position and intensity, image is analog
image.
 Examples: Printed photographs
What is Digital Image?

 Image : A two - dimensional function, f(x , y), where x and y are

spatial coordinates, and f at any pair of coordinates (x , y) is
called the intensity or gray level of the image at that point.
 When x, y, and f are all finite, discrete quantities, image is a
digital image.
 Example : Scanned documents or pictures, Satellite images,
Medical imaging (X-rays, CT scans), screenshots etc.
What is Digital Image? (Cont.)

 Contains finite number of elements, each of which has a

particular location and value.
 These elements are called picture elements, image elements,
pels, or pixels. Pixel is the term used most widely to denote the
elements of a digital image.
 Advantages : Fast processing , Cost effective, Effective storage,
Effective transmission, Scope for versatile image manipulation
 Disadvantages : High memory for good quality images and
hence requires fast processor.
How to convert Analog image to Digital
image?

Analog
Sampling
Image

Digital Quantization
Image
What is Digital Image Processing?

 The analysis and manipulation of a digitized image, especially in

order to improve its quality.
 Processing of digital images by means of digital computer.
Advantages of Digital Image Processing

 Humans are limited to the visual band of the electromagnetic

(EM) spectrum.
 But imaging machines cover almost the entire EM spectrum,
ranging from gamma to radio waves.
 Thus operate on images generated by sources that humans are not
capable to see to sense.
 These include ultrasound, electron microscopy, and computer-
generated images.
Scope of Digital Image Processing

 No general agreement where image processing stops and other

related areas , such as image analysis and computer vision, start.
 Distinction sometimes is made as a discipline in which both the
input and output of a process are images.
 But this is a limiting and somewhat artificial boundary.
 For example, task of computing the average intensity of an image
(single number) would not be considered as an image processing
operation.
Scope of Digital Image Processing (Cont.)

 There are fields like computer vision which use computers to

emulate human vision, including learning and being able to make
inferences and take actions based on visual inputs.
 Thus it is a branch of artificial intelligence (AI) whose objective
is to emulate human intelligence.
 Hence, the area of image analysis (also called image
understanding) is in between image processing and computer
vision.
Useful Paradigm in the World of Images

 Considering three types of computerized processes:

(a) Low-level processes,
(b) Mid-level processes,
(c) High-level processes.
Low-level processes

 Low level processes involves primitive operations such as image

preprocessing to reduce noise, contrast enhancement, and image
sharpening.
 Thus , a low-level process is characterized by the fact that both its
inputs and outputs are images.
Mid-level Processes

 Mid-level processes involves tasks such as segmentation,

description of those objects to reduce them to a form suitable for
computer processing, and classification of individual objects.
 Thus, a mid-level process is characterized by the fact that its
inputs generally are images, but its outputs are attributes
extracted from those images (e.g. edges, contours, and the
identity of individual objects).
High-level Processes

 High-level processes involves “making sense” of an ensemble of

recognized objects, as in image analysis, and at the far end
performing the functions normally associated with vision.
Fundamental steps in Digital Image
Processing
Fundamental steps in Digital Image
Processing (Cont.)
 Image Acquisition : This involves capturing an image using a digital
camera or scanner, or importing an existing image into a computer.
 Image Enhancement : This involves improving the visual quality of
an image, such as increasing contrast, reducing noise, and removing
artifacts.
 Image Restoration : This involves removing degradation from an
image, such as blurring, noise, and distortion.
 Color Image Processing: It involves working with images to
enhance, modify, or extract useful information from them while
considering the color aspects.
Fundamental steps in Digital Image
Processing (Cont.)
 Wavelets & Multiresolution processing : Wavelets are like tiny
waves that help break down an image into simpler parts, capturing
details at different scales. They allow us to see both the location and
the frequency information of an image. Multiresolution processing
involves looking at an image at different levels of detail, like
zooming in and out. You create multiple versions of an image at
different resolutions, each showing varying levels of detail. This
helps in tasks like image compression, where you want to keep the
important details while reducing file size, and noise reduction,
where you filter out unwanted details without losing key features.
Fundamental steps in Digital Image
Processing (Cont.)
 Image Compression : Image compression is a technique used to
reduce the file size of an image. This is done by removing or
simplifying some of the image data while trying to keep the quality
as high as possible.
 Morphological processing : Morphological processing refers to a
set of techniques used primarily in image analysis and computer
vision to process and analyze shapes and structures within images.
 Segmentation: This involves dividing an image into regions or
segments, each of which corresponds to a specific object or feature
in the image.
Fundamental steps in Digital Image
Processing (Cont.)
 Representation & Description : This involves representing an
image in a way that can be analyzed and manipulated by a
computer, and describing the features of an image in a compact
and meaningful way.
 Object recognition: Object recognition is a computer vision task
that involves identifying and classifying objects within an image
or video.
 Overlapping Fields with Image Processing
 According to block 1,if input is an image and
we get out image as a output, then it is termed
as Digital Image Processing.
According to block 2,if input is an image and
we get some kind of information or description
as a output, then it is termed as Computer
Vision.
According to block 3,if input is some
description or code and we get image as an
output, then it is termed as Computer Graphics.
According to block 4,if input is description or
some keywords or some code and we get
description or some keywords as a output,then it
is termed as Artificial Intelligence.
THANK YOU