Chapter One

Introduction to computer vision and image

processing

1
1.1 What is Computer Vision?

▪ Computer Vision is field of Ai that enables

computers and systems to derive meaningful
information from digital images , videos and
other visual inputs and take actions or make
recommendations based on that informations.
▪ CV enables computer to see, observe and
understand.
Human Visual System
▪ Input ➔ Brain ➔ Output

2
…cont’d

Computer Vision System

▪ Input ➔ Sensing Device ➔ Interpreting Device ➔Output
▪ Computer Vision uses input from sensing devices
to replicate the way the human vision system
works.
▪ It runs on algorithms that are trained on massive
amount of visual data.
▪ It recognizes patterns in this visual data and use
those patterns to determine the content of other
images.

3
1.2 What is Image?

▪ An image represents something, whether a

drawing, painting, graphic or photograph it
can be created digitally or manually.
▪ There are many types of image:
▪ A binary image is represented by only one bit.
▪ On the other hand, a gray level image is
represented by 8 bits.
▪ A raster image is a collection of dots, which
are called pixels.

4
…cont’d

▪ A vector image is a collection of connected

lines & curves, and they are used to produce
objects.
▪ Color images have Red (R), Green (G) and
Blue (B) components. Each of the three R, G,
B components is usually represented by 8 bits,
and hence 24 bits are needed for a color
image.
▪ These three primary colors are mixed in
different proportions to get different colors.

5
…cont’d

▪ For different image processing applications,

the formats RGB (Red, Green, Blue), HIS
(Hue, Saturation, Intensity), YIQ (Luminance,
In-phase, Quadrature),YCbCr, etc. are
used.
▪ A color image is a three-component function,
which is a “vector-valued” function, and it is
represented as

6
…cont’d

▪ The indexed image has an associated color

map, which is simply a list of all the colors
used in that image. Examples of this format
are PNG and GIF images.
▪ So, different types of digital images can be
listed as follows.
▪ Binary image - 1 bit/pixel
▪ Grayscale image - 8 bits/pixel
▪ True color or RGB image - 24 bits/pixel
▪ Indexed image - 8 bits/pixel

7
 1.3 Related fields in Computer
Vision
▪ The fields most closely related to CV are
▪ AI
▪ Machine Learning
▪ Cognitive Science
▪ Algorithms
▪ Image Processing and
▪ Graphics

8
 1.4 Computer Vision vs Image
Processing
▪ Computer Vision is focused on extracting
information from the input images or videos to
have a proper understanding of them to
predict the visual input like human brain.
▪ Image Processing is mainly focused on the
processing of the raw input image to enhance
them or preparing them to do other tasks.
▪ Computer Vision inputs an image outputs
task specific knowledge, such as object labels
(cat, dog, …, etc.)
9
…cont’d

▪ Image Processing – input and the output are

both images. Transform image in many ways:
smoothing, sharpening, changing brightness
and contrast, highlighting the edge, …, etc.

10
1.5 Application of Computer Vision
and Image Processing

11
 1.5.1 Application of Computer
Vision
▪ Below are some most popular applications of
computer vision:
▪ Facial recognition
▪ CV has enabled machines to detect face images
of people to verify their identity
▪ Health Care and Medicine
▪ CV provides faster and more accurate
chemotherapy response assessment (E.g.
identify cancer patients)
▪ Machine Inspection
▪ CV provides an image based automatic
inspection (E.g. detecting defects) 12
…cont’d

▪ Self Driving Vehicles

▪ CV contributed its role in self driving vehicles to
make sense of their surroundings by capturing
video from different angles around the car.
▪ Optical Character Recognition (OCR)
▪ OCR helps us extract printed or handwritten text
from visual data such as images
▪ Retail (Automated checkout)
▪ CV is implemented in the retail industry to truck
products, shelves, record product movements
into the stores, etc.
13
…cont’d

▪ 3D Models Building
▪ CV plays its role in constructing 3D computer
models from existing objects
▪ Medical Imaging
▪ CV helps medical professionals make better
decisions regarding treating patients by
developing visualization of specific body parts
(CT scan and RMI)
▪ Surveillance
▪ Nowadays, CCTV cameras are almost fitted in
every places to spot various criminal activities
14
…cont’d

▪ Finger Print Recognition and Biometrics

▪ CV detects finger prints and biometrics to validate
a user’s identity

15
 1.5.2 Applications of Image
Processing
▪ Image sharpening and restoration: improving
the quality and clarity of old or blurry images.
▪ Medical field: diagnosing diseases, analyzing
medical images, and assisting surgeries.
▪ Remote sensing: capturing and interpreting
images of the earth's surface from satellites
or aerial vehicles.
▪ Machine/Robot vision: enabling machines or
robots to perceive and interact with their
environment.
16
…cont’d

• Color processing: adjusting the color,

contrast, and brightness of images.
• Pattern recognition: identifying and classifying
objects, faces, or texts in images.
• Video processing: editing, compressing, or
transmitting video signals.

17
 1.6 Different Image Processing
Examples
▪ Some of the most common image processing
examples:
▪ Image Enhancement – improving the quality of
image( e.g. adjusting brightness and contrast

18
…cont’d

▪ Image restoration – the operation of taking

corrupt/noisy image and estimating the clean,
original image

19
…cont’d

▪ Image Segmentation – the process of

partitioning an image into multiple segments or
regions. Each segment represents different
object in the image

20
…cont’d

▪ Object detection – the task of identifying object

in an image.

21
▪ Image Generation – synthesis of new images.
▪ Image manipulation – the process of altering
an image to change its appearance (e.g.
removing unwanted objects)
▪ Image compression – the process of reducing
the file size of image while still trying to
preserves the quality of the image.

22
1.7 Fundamental Steps in Image
Processing

23
…cont’d

▪ Image Acquisition
▪ The first step in digital image processing
▪ It is basically capturing an image.
▪ Involves preprocessing, such as scaling.
▪ Image Enhancement
▪ The process of filtering image(removing noise,
increasing contrast, etc) to improve the quality.
▪ Enhancement is based on human subjective
preferences regarding what constitutes a
“good” enhancement result.
24
…cont’d
▪ Image Restoration
▪ Deals with improving the appearance of an
image.
▪ Restoration techniques tend to be based on
mathematical or probabilistic models of image
degradation.
▪ Color Image Processing
▪ This processing is focused on how humans
perceive color, that is, how we can arrange the
colors of images as wanted.
▪ We can do color balancing, color correction, and
auto-white balance with color processing. 25
…cont’d
▪ Color is used also as the basis for extracting
features of interest in an image.
▪ Wavelets
▪ The foundation for representing images in
various degrees of resolution.
▪ Used for image data compression and for
pyramidal representation, in which images are
subdivided successively into smaller regions.
▪ Compression
▪ Deals with techniques for reducing the storage
required to save an image, or the bandwidth
required to transmit it. 26
…cont’d

▪ Morphological Processing
▪ Deals with tools for extracting image
components that are useful in the
representation and description of shape.
▪ Segmentation
▪ Partitions an image into its constituent parts or
objects.
▪ Autonomous segmentation is one of the most
difficult tasks in digital image.

27
…cont’d

▪ Feature Extraction
▪ Follows the output of a segmentation stage,
which usually is raw pixel data, constituting
either the boundary of a region (i.e., the set of
pixels separating one image region from
another) or all the points in the region itself.
▪ It consists of feature detection and feature
description.
▪ Feature detection refers to finding the features in
an image, region, or boundary.

28
…cont’d

▪ Feature description assigns quantitative attributes

to the detected features. For example, we might
detect corners in a region, and describe those
corners by their orientation and location; both of
these descriptors are quantitative attributes.
▪ Image pattern classification
▪ Is the process that assigns a label to an object
based on its feature descriptors.
▪ Knowledge Base
▪ Knowledge about a problem domain is coded
into an image processing system in the form of
a knowledge database. 29