Subject code Computer vision L T P C

20CST432 Total Contact Hours:30 Hours 2 0 0 2

Marks-100
Internal-40 External-60
Course Objectives
 To understand the basic concepts of image processing.
 To enhance knowledge about fundamental steps in image processing.
 To apply different image processing concepts to solve research problems.
Course Outcomes
CO1 Recognize the fundamental principles of computer vision, including its scope,
applications, and the relevance of features, image registration, and image
stitching in the field.
CO2 Demonstrate proficiency in working with features and implementing image
stitching techniques in practical scenarios.
CO3 Analyze and compare the machine learning techniques used for image
classification and object detection in computer vision.
CO4 Evaluate the performance of image classification models using various metrics
and suggest improvements to optimize model performance.
CO5 Design and develop object tracking and motion detection systems using
computer vision techniques, including detecting objects, and detection and
tracking and integrate them into a final project.

Contents of the syllabus

UNIT I [8 hrs]

Introduction to Computer Vision

Introduction to Features: Features Extracting Features Matching Features, Working With Features: Refining Feature
Detection Feature Detection and Extraction Reference, Image Registration: Transformations Feature-Based Image
Registration Visually Selecting Control Points, Image Stitching: Introduction to Image Stitching, Stitching Images
Example Mars Rover: Final Project
UNIT II [11 hrs]

Machine Learning for Computer Vision

Image Classification with Machine Learning: Introduction to Machine Learning for Computer Vision, The Machine
Learning Workflow, Introduction to Classification Models, Preparing Your Images for Classification, Training Image
Classification Models, Image Classification Using Bag of Features: Introduction to Bag of Features, Classifying
Images With Bag of Features, Evaluating Classification Models: Evaluating Classification Models, Evaluating
Classification Models in MATLAB, Common Issues in Image Classification, Object Detection with Machine
Learning: Object Detection with Machine Learning, Labeling your Images for Machine Learning, Introduction to the
Object Detection Project
 UNIT III [13 hrs]

Object Tracking and Motion Detection with Computer Vision

Detecting Objects: Introduction to Object Tracking and Motion Detection, Detecting Objects with Pretrained Models,
Detecting Objects with Segmentation, Motion Detection: Detecting Motion, Stabilizing Video with Template
Matching, Applying Optical Flow, Detection and Tracking: Introduction to Object Tracking, Implementing Object
Tracking 1: Concepts, Implementing Object Tracking 2: Execution, Final Project: Introduction to the Traffic Flow
Project, Integrating Your Code

Text Books:
1. Gonzalez and Woods: Digital Image Processing ISDN 0-201-600- 781, Addison Wesley 1992.
2. Forsyth and Ponce: Computer Vision A Modern Approach Pearson Education Latest Edition.
Reference Books:
1. Pakhera Malay K: Digital Image Processing and Pattern Recognition, PHI.
2. Trucco&Verri: Introductory Techniques for 3-D Computer Vision, Prentice Hall, Latest Edition.
3. Low: Introductory Computer Vision and Image Processing, McGraw-Hill 1991, ISBN 0-07-707403-3.

CO vs PO/PSO PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

CO1 3 NA 2 NA NA 2 NA NA NA NA NA NA 2 NA

CO2 2 2 2 NA 2 NA NA NA NA NA NA NA NA NA

CO3 3 3 NA 3 NA NA NA NA NA NA NA NA NA NA

CO4 3 3 NA 3 NA NA NA NA NA NA NA NA NA NA

CO5 NA NA 3 3 NA 2 NA NA 2 2 NA NA NA NA

Target 2.75 2.66 2.33 3 2 2 NA NA 2 2 NA NA 2 NA

 Syllabus Computer Vision Lab
1. Course number and name: CSP-422 Computer Vision Lab
2. Credits, contact hours, and categorization of credits:

Credits Contact Hours Categorization

of Credits
1 2 Program Core
3. Instructor ‘s or course coordinator ‘s name: Er. Payal Thakur
4. Text book, title, author, and year
a. Gonzalez and Woods: Digital Image Processing ISDN 0-201-600- 781, Addison Wesley 1992..
b. Forsyth and Ponce: Computer Vision A Modern Approach Pearson Education Latest Edition.
other supplemental materials
Reference Material.
a. Pakhera Malay K: Digital Image Processing and Pattern Recognition, PHI
b. Trucco&Verri: Introductory Techniques for 3-D Computer Vision, Prentice Hall, Latest Edition..
5. Specific course information
a. Brief description of the content of the course (catalog description)
This course deals with emerging and exciting domain of real-time systems.
b. Prerequisites or Co-requisites:
Prerequisites: Knowledge of Artificial Intelligence and Machine Learning Co-requisites: None
c. Indicate whether a required, elective, or selected elective (as per Table 5-1) course in the program:
Required
6. Specific goals for the course
a) Course Outcomes:
Students will be able to
learn:
CO1: Implement various feature extraction techniques for image classification and evaluate
their effectiveness.
CO2: Assess and compare the performance of different feature matching algorithms for object
recognition.
CO3: Analyze the impact of refining feature detection on image segmentation tasks and
understand its significance.
CO4: Evaluate the efficacy of human-guided control point selection for image alignment and
understand its implications in image processing.
CO5: Compare and interpret the performance of different classification models in image recognition
and gain insights into their strengths and weaknesses..
 COs-POs mapping

PSO1

PSO2
PO10

PO12
PO11
PO2

PO6

PO7

PO9
PO1

PO3

PO4

PO5

PO8
CO
CO-1 3 2 - - 3 - - - - - - - 3 -
CO-2 - 3 - 2 - - - - - 2 - - 2 -
CO-3 - 3 2 - - - 1 - - - - - 2 -
CO-4 - 2 - - - 2 - 2 2 - - - 2 -
CO-5 - 3 - 2 - - - - - 2 - 2 2 -

b) Explicitly indicate which of the student outcomes listed in Criterion 3 or any other outcomes are
addressed by the course.
CAC
Analyze a complex computing problem and to apply principles of computing and other √
SO1
relevant
disciplines to identify solutions.
Design, implement and evaluate a computing-based solution to meet a given set of √
SO2 computing

requirements in the context of the program ‘s discipline.

SO3 Communicate effectively in a variety of professional contexts.
Recognize professional responsibilities and make informed judgments in computing
SO4 practice
based on legal and ethical principles.
Function effectively as a member or leader of a team engaged in activities appropriate to the √
SO5
program ‘s discipline.
Identify and analyze user needs and to take them into account in the selection, creation,
√
SO6 integration, evaluation, and administration of computing-based systems

EAC
An ability to identify, formulate, and solve complex engineering problems by applying √
SO1
principles of engineering, science, and mathematics
An ability to apply engineering design to produce solutions that meet specified needs with
√
SO2 consideration of public health, safety, and welfare, as well as global, cultural, social,
environmental, and economic factor
SO3 An ability to communicate effectively with a range of audiences
 An ability to recognize ethical and professional responsibilities in engineering situations and
SO4 make informed judgments, which must consider the impact of engineering solutions in global,
economic, environmental, and societal contexts
SO5 An ability to function effectively on a team whose members together provide leadership,
create a collaborative and inclusive environment, establish goals, plan tasks, and meet
objectives
SO6 An ability to develop and conduct appropriate experimentation, analyze and interpret data, and
use engineering judgment to draw conclusions √

SO7 An ability to acquire and apply new knowledge as needed, using appropriate learning
strategies. √

List of Experiments

S.NO Name of the Experiment Hours/CO

Mapped
UNIT I 15 hours
1.1 Write a program to implement various feature extraction CO1
techniques for image classification.
1.2 Write a program to assess various feature matching algorithms for CO2
object recognition.
1.3 Write a program to analyze the impact of refining feature CO3
detection for image segmentation.
1.4 Write a program to evaluate the efficacy of human-guided control CO4
point selection for image alignment.
UNIT II 15 hours
2.1 Write a program to compare the performance of different CO5
classification models in image recognition.
2.2 Write a program to interpret the effectiveness of Bag of Features in CO1
enhancing image classification performance.
2.3 Write a program to analyze various object detection algorithms CO2
with machine learning.
UNIT III 15 hours
3.1 Write a program to determine the effectiveness of incorporating CO3
optical flow analysis into object tracking algorithms.
3.2 Write a program to examine the performance of various pretrained CO5
deep learning models for real-time object tracking tasks.
3.3 Write a program to interpret the effectiveness of template matching CO4
techniques for video stabilization tasks.