Chapter 1 Introduction to Computer Vision and Image Processing .pdf

Getnet T. Email: getnet6202@gmail.com , College of Informatics , University of Gondar, July 2025
College of Informatics
Department of Computer Science
ComputerVision and Image Processing (CoSc4113)
Chapter one: Introduction to ComputerVision and Image Processing
University of Gondar

Introduction to ComputerVision and Image Processing
Objectives
By the end of this lesson, you will be able to:
Define what computer vision and image are, and explain the
difference between them.
1
Identify related fields like AI and robotics, and describe how they
connect to computer vision.
2
Give examples of real-world applications of computer vision and
image processing.
3
List and explain the main steps in the image processing workflow
4

What is a computer vision?
What is image?
Related fields in CV
Computer Vision Vs image processing
Application of CV and IP
Different Image processing examples
Fundamental steps in image processing
Contents
1
2
3
4
5
6
7

1
It is a field of artificial intelligence that enables machines to see,
analyze, and interpret the visual world like humans.
It is the process of using artificial intelligence to enable
computers to obtain meaningful data from visual inputs
It can also be defined as a field of study that seeks to develop
techniques to help computers/Machine “see” and understand
the content of digital images such as photographs and videos
By using images or videos, or 3D scans CV systems extract
meaningful information to make decisions or provide outputs.
The goal is to mimic human vision by extracting high-level
understanding from pixels

1
 From the perspective of
engineering, it seeks to automate
tasks that the human visual system
can do
 The overall goal of computer vision
is to give computers (super)
human-level perception
 Example

How Does Computer Vision Work?
1
01 02
03 04
Input: An image or video
is captured (e.g., from a
camera)
Processing: Algorithms
analyze pixel data
Decision-Making:
Based on the
analysis, the
system reacts
(e.g., a robot
avoiding
obstacles)
Understanding:
The system
identifies objects,
patterns, or
actions

What is an Image?
2
 Representing Digital Images
An image is a 2D array of pixels, where each pixel represents the
intensity of light at that location.
It is a two-dimensional function, where x and y are spatial (plane)
coordinates, and the amplitude of 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 the intensity values of f are all finite, discrete
quantities, we call the image a digital image.
 Pixels or picture elements (image element) is the smallest unit in
an image
 Digital image is
represented by an M×N
numerical array as

Related Fields in Computer Vision
3
Image
Processing
Focuses on enhancement and transformation of images
(e.g., filtering, contrast adjustment)
Pattern
Recognition
Identifies patterns in data (used in handwriting recognition,
fingerprint matching)
Machine
Learning &
Deep Learning
Enables learning from data for tasks like classification or
object detection. Example: A CNN learns to distinguish
cats from dogs by analyzing thousands of labeled images.
Robotics
Uses vision for navigation, object manipulation, and
decision making using cameras and sensors. Example: A
warehouse robot avoiding obstacles while moving goods.
Artificial
Intelligence
Enables decision-making based on visual data. Example:
A surveillance system detecting suspicious activity.
Augmented
Reality &
Virtual Reality
Overlays digital objects on real-world images. Example:
Snapchat filters, virtual furniture placement in IKEA’s app.

Computer Vision Vs. Image Processing
4
Image Processing Computer Vision
Enhance image quality
processing the raw input images to
enhance them or preparing them to do
other tasks
Low-level pixel operations
Denoising, sharpening, Rescaling image
(Digital Zoom), Correcting illumination,
Changing tones
Understand and interpret image
High-level semantic understanding
Object detection, scene labeling,
Face detection, Hand writing
recognition
Goal
Focus
Example

Introduction to Computer Vision and Image Processing
Application of Computer Vision and Image Processing
5
Computer
Vision
Image
Processing
 Facial recognition (security,
authentication)
 License plate recognition
 Autonomous vehicles
 Document image analysis
 Industrial inspection and robotics
 Remote sensing applications: Plotting
weather maps, Oil exploration.
 Vision used for control: Road traffic
monitoring, passive surveillance, etc.
 Medical Imaging
 Image enhancement for satellite images
 Restoration of old/damaged photos
 Noise filtering in medical images
 Preprocessing for OCR systems
 Photography- Enhancing low-light
images. E.g. Night mode in smartphone
cameras.
 Forensics- Enhancing blurry surveillance
footage. License plate recognition

5
 Today, farmers are leveraging computer vision to enhance agricultural
productivity.
 Companies specializing in agriculture technology are developing advanced
computer vision and artificial intelligence models for sowing and harvesting
purposes.
 These solutions are also useful for weeding, detecting plant health, and
advanced weather analysis.
 Computer vision has numerous existing and upcoming applications in
agriculture, including drone-based crop monitoring, automatic spraying of
pesticides, yield tracking, and smart crop sorting & classification.
 for further analysis, these AI-powered solutions scan the crops’ shape, color,
and texture.
 Through computer vision technology, weather records, forestry data, and field
security are also increasingly used
 In Agriculture

5
 Market leaders such as Tesla, backed by advanced technologies such as
computer vision and 5G, are making great strides.
 Tesla’s autonomous cars use multi-camera setups to analyze their
surroundings.
 This enables the vehicles to provide users with advanced features, such as
autopilot.
 The vehicle also uses 360-degree cameras to detect and classify objects
through computer vision.
 Drivers of autonomous cars can either drive manually or allow the vehicle to
make autonomous decisions.
 In case a user chooses to go with the latter arrangement, these vehicles use
computer vision to engage in advanced processes such as path planning,
driving scene perception, and behavior arbitration
 In Autonomous vehicles

5
 While facial recognition is already in use at the personal level, such as through
smartphone applications, the public security industry is also a noteworthy
driver of facial detection solutions.
 How Facial recognition can work?
 Detecting and recognizing faces in public is a contentious application of
computer vision that is already being implemented in certain jurisdictions and
banned in others.
 Successful facial detection relies on deep learning and machine vision.
Proponents support computer vision-powered facial recognition because it
can be useful for detecting and preventing criminal activities. These solutions
also have applications in tracking specific persons for security missions
 In Face Recognition

5
 Gone are the days when digital entertainment meant that the viewer had to
sit and watch without participating.
 Today, interactive entertainment solutions leverage computer vision to deliver
truly immersive experiences.
 Cutting-edge entertainment services use artificial intelligence to allow users to
partake in dynamic experiences.
 For instance, Google Glass and other smart eyewear demonstrate how users
can receive information about what they see while looking at it. The
information is directly sent to the user’s field of vision. These devices can also
respond to head movements and changes in expressions, enabling users to
transmit commands simply by moving their heads
 In Interactive Entertainment

5
 Medical systems rely heavily on pattern detection and image classification
principles for diagnoses.
 While these activities were largely carried out manually by qualified
healthcare professionals, computer vision solutions are slowly stepping up to
help doctors diagnose medical conditions.
 There has been a noteworthy increase in the application of computer vision
techniques for the processing of medical imagery.
 This is especially prevalent in pathology, radiology, and ophthalmology.
 Visual pattern recognition, through computer vision, enables advanced
products, such as Microsoft InnerEye, to deliver swift and accurate diagnoses
in an increasing number of medical specialties
 In Medical Imaging

5
 With remote education receiving a leg-up due to the COVID-19 pandemic, the
education technology industry is also leveraging computer vision for various
applications.
 For instance, teachers use computer vision solutions to evaluate the learning
process non-obstructively.
 These solutions allow teachers to identify disengaged students and tweak the
teaching process to ensure that they are not left behind.
 Apart from this, AI vision is being used for applications such as school logistic
support, knowledge acquisition, attendance monitoring, and regular
assessments.
 One common example of this is computer vision-enabled webcams, which are
being used to monitor students during examinations
 In Education

5
 Computer vision systems are being increasingly applied to increase
transportation efficiency.
 For instance, computer vision is being used to detect traffic signal violators,
thus allowing law enforcement agencies to minimize unsafe on-road behavior.
 Intelligent sensing and processing solutions are also being used to detect
speeding and wrong‐side driving violations, among other disruptive behaviors.
 Apart from this, computer vision is being used by intelligent transportation
systems for traffic flow analysis
 In Transportation

5
 Face Detection
 Complex Decision

Different Image Processing Examples
6
 Histogram Equalization – Improves contrast for Poor contrast (too dark/bright) images by
redistributing pixel intensities for better visibility.
 Filtering – Smoothen or sharpens images (e.g., Gaussian, Median filters)
 Edge Detection –Identifying object boundaries (algorithms like , Sobel, Prewitt, Canny)
 Morphological Operations – Cleaning up binary images (e.g., erosion, dilation)
 Thresholding – Converts grayscale to binary using a set value (e.g. Otsu’s method**
automatically finds the best threshold. )
 Color Space Conversion – RGB ↔ HSV, YCbCr for segmentation or compression Example:
Converting an RGB image to grayscale for edge detection
 Sharpening:- Used for filtering an images to enhance edges and ignore noise
 Smoothing:- remove noise. Used for smooth an images to denoise and ignore edges
 Enhancing:
 Restoring:
 Blurring/ deblurring

Fundamental Steps in Image Processing
6
Image Acquisition Preprocessing Segmentation
Feature Extraction
Capturing an image using
cameras, sensors or scanners.
Digitization is necessary because
the standard video signal is in
analog (continuous) form and the
computer requires a digitized or
sampled version of that
continuous signal
Classification
/Object Recognition
Interpretation &
Decision-Making (Post-
processing)
Enhancing image
quality, removing
noise, normalization,
resizing
Dividing image into
meaningful regions (e.g.,
foreground/background)
Extracting significant
characteristics (edges, corners,
textures)
Classifying or
identifying objects in
an image Using ML
models
Improving the presentation,
interpreting the results or
acting on the analysis (e.g.,
a robot avoiding obstacles)
1 2 3
4
5
6

End of Introduction
Thank You

Chapter 1 Introduction to Computer Vision and Image Processing .pdf

More Related Content

Similar to Chapter 1 Introduction to Computer Vision and Image Processing .pdf

More from Getnet Tigabie Askale -(GM)

Recently uploaded

Chapter 1 Introduction to Computer Vision and Image Processing .pdf