SCHOOL OF COMPUTING & INFORMATION TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

COURSE HAND-OUT

COMPUTER VISION | CS4158 | 3 Credits | 3 0 0 3

Session: August – December 2022
Faculty: Dr. Yadvendra Pratap Singh|| PE-7
Class: B. Tech VII Semester

A. VISION, MISSION AND PROGRAM EDUCATIONAL OBJECTIVES(PEOs)

Vision:
• To achieve Excellence in Computer Science & Engineering Education for Global Competency with Human
Values

Mission:
• Provide innovative Academic & Research Environment to develop competitive Engineers in the field of Computer
Science Engineering
• Develop Problem-solving & Project Management Skills by Student Centric Activities & Industry Collaboration
• Nurture the Students with Social & Ethical Values

Program Educational Objectives (PEOs):

• PEO1: Graduates will Demonstrate Professional Skills on Global Platform in Computer Science Engineering and
Integrated Domains
• PEO2: Graduates will Enhance Knowledge and Skills through Higher Studies and Lifelong Learning of New
Computing Technologies
• PEO3: Graduates will Provide Innovative Solutions to Drive Societal Advancement through Technology
Entrepreneurship and Start-up

B. Introduction: This course is a broad introduction to computer vision. Topics include introduction to computer
vision, camera and image, camera models, multi-view geometry, reconstruction, some low-level image
processing, and high-level vision tasks like image classification and object detection. The course is designed to
give students an in-depth understanding of the basic concepts of computer vision and different algorithms that is
applicable in computer vision application. The course will be taught with the help of several teaching aides such
as power point presentation and via live debugging and execution demonstrations of different algorithms.
The main objective of the course are as follows:
• To teach students about the basics of computer vision (CV) and its application.
• To enable the students to properly use the basic computer vision techniques such as image formation,
camera calibration.
• To enable the students to understand the basic difference between an image processing and an CV.
• To teach students about the implementation aspect of various basic technique such as neural network
and convolution neural network.
• To educate students how to provide various types of technique for CV.
• To introduce students about the role of different filter techniques.
• To teach students about the basic of deep convolution neural network.
C. Course Outcomes: At the end of the course, students will be able to
[2104.1]. Identify basic concepts, terminology, theories, models, and methods in the field of computer vision
and its application. (Level 2)
[2104.2]. Describe basic methods of computer vision related to multi-scale representation, filtering, edge
detection and other primitives. (Level 2)
[2104.3]. Use methods of computer vision related to camera model and calibration, stereo, motion and object
recognition. (Level 3)
[2104.4]. Developed the practical skills necessary to build computer vision applications using deep convolution
neural network. (Level 4)

D. PROGRAM OUTCOMES AND PROGRAM SPECIFIC OUTCOMES

PROGRAM OUTCOMES
[PO.1]. Engineering knowledge: Apply the knowledge of basic science and fundamental computing
in solving complex engineering problems.
[PO.2]. Problem analysis: Identify, formulate, research literature, and analyse complex engineering
problems reaching substantiated conclusions using first principles of mathematics, natural
sciences, and engineering sciences.

[PO.3]. Design/development of Computing solutions: Design solutions for complex IT engineering

problems and design system components or processes that meet the specified needs with
appropriate consideration for the Information oriented public health and safety, and the
cultural, societal, and environmental considerations

[PO.4]. Conduct investigations of complex problems: Use IT domain research-based knowledge

and research methods including design of experiments, analysis and interpretation of data,
and synthesis of the information to provide valid conclusions

[PO.5]. Modern tool usage: Create, select, and apply appropriate techniques, resources, and
modern engineering and IT tools including prediction and modelling to complex engineering
activities with an understanding of the limitations

[PO.6]. The engineer and society: Apply reasoning informed by the contextual knowledge to assess
societal, health, safety, legal, and cultural issues and the consequent responsibilities
relevant to the professional engineering practice

[PO.7]. Environment and sustainability: Understand the impact of the professional engineering
solutions in societal and environmental contexts, and demonstrate the knowledge of, and
need for sustainable development

[PO.8]. Apply ethical principles and commit to professional ethics and responsibilities and norms of
the engineering practices

[PO.9]. Individual and teamwork: Function effectively as an individual, and as a member or leader
in diverse IT teams, and in multidisciplinary settings.
[PO.10]. Communication: Communicate effectively on complex computing engineering activities with the
engineering community and with society at large, such as, being able to comprehend and write
effective reports and design documentation, make effective presentations, and give and receive
clear instructions

[PO.11]. Project management and finance: Demonstrate knowledge and understanding of the
engineering and management principles and apply these to one’s own work, as a member and
leader in a team, to manage projects and in multidisciplinary environments
 [PO.12]. Life-long learning: Recognize the need for, and have the preparation and ability to engage in
independent and life-long learning in the broadest context of technological change

PROGRAM SPECIFIC OUTCOMES

[PSO.1]. Will be able to design, develop and implement efficient software for a given real life
problem.

[PSO.2]. Will be able to apply knowledge of AI, Machine Learning and Data Mining in analysis big
data for extracting useful information from it and for performing predictive analysis.

[PSO.3]. Will be able to design, manage and secure wired/ wireless computer networks for
transfer and sharing of information.

E. Assessment Plan:
Criteria Description Maximum Marks
Sessional Exam I 20
Internal Assessment Sessional Exam II 20
(Summative)
In class Quizzes and Assignments 20
End Term Exam End Term Exam (Close Book) 40
(Summative)
Total 100
Attendance A minimum of 75% Attendance is required to be maintained by a student to be
(Formative) qualified for taking up the End Semester examination. The allowance of 25%
includes all types of leaves including medical leaves.

F. SYLLABUS
Introduction: Introduction to computer vision and its applications.
Geometric Image Features: Differential Geometry, Contour Geometry,
analytical image features: Euclidean geometry, Geometric Camera Parameters,
Calibration methods, Image formation,
Liner Filtering: Linear filters and convolution, shift invariant linear systems, spatial
frequency, and Fourier transforms.
Image transformations and Colour models.
Edge Detection methods (Laplacian detectors and Canny edge detector), Points and
patches, Harris corner detector, Histogram of Gradients, Difference of Gaussian detector.
SIFT, Colour and Texture, Feature based alignment, least squares and RANSAC,
Camera models, Camera calibration, Stereo vision, Stereo correspondence
Epipolar geometry Optical flow, Lucas Kanade method, KLT tracking method, Mean shift
method
Dense motion estimation, Support Vector Machines, Face detection and recognition, Bag
of words,
Deep convolution neural network.
G. TEXT BOOKS

1. D. A. Forsyth, J. Ponce, Computer Vision: A Modern Approach, (2e), PHI learning, 2012

H. REFERENCE BOOKS

1. R. Szeliski, Computer Vision: Algorithms and Applications, Springer 2011.

2. J. E. Solem, Programming Computer Vision with Python, O’Reilly, 2012
I. Lecture Plan:

Mode
Mode Of
of
Lectures Major Topics Topics Session Outcome Corresponding CO Assessing
Deliver
CO
y
To acquaint and clear
PPT,
teacher’s
Introduction and Course Hand- Lecture,
1. expectations and NA NA
out briefing Class
understand student
Notes
Introduction to expectations
computer vision To understand about PPT,
Mid Term
and its computer Vision and Lecture,
2. Introduction to computer vision CS4158.1 I, Quiz &
applications (1- its fundamentals Class
End Term
3 Lecture) Notes
To understand the PPT,
Mid Term
different computer Lecture,
3. computer vision application CS4158.1 I, Quiz &
Vision applications Class
End Term
Notes
To understand about Mid Term
Flipped
4. Introduction the Geometric image CS4158.1 I, Quiz &
Class
Features End Term
To understand about PPT,
Mid Term
Geometric the differential Lecture,
5. Differential Geometry CS4158.1 I, Quiz &
Image Features Geometry Class
End Term
(4- 6) Notes
PPT,
Mid Term
Contour Geometry To understand about Lecture,
6. CS4158.1 I, Quiz &
the Contour Class
End Term
Geometry Notes
To understand about PPT,
Mid Term
the Euclidean Lecture,
7. Euclidean geometry CS4158.1 I, Quiz &
geometry Class
End Term
Notes
To understand about PPT,
Mid Term
the Geometric Lecture,
8. Geometric Camera Parameters CS4158.1 I, Quiz &
Camera Parameters Class
End Term
Notes
9. Geometric Camera Parameters To understand about Flipped CS4158.1 Mid Term
 the Geometric I, Quiz &
Class
Camera Parameters End Term
To understand about PPT,
Mid Term
the Calibration Lecture,
10. Calibration methods CS4158.1 I, Quiz &
methods Class
End Term
Notes
To understand and PPT,
Mid Term
describe the Lecture, CS4158.1 &
11. Constructor Chaining I, Quiz &
Constructor Chaining Class CS4158.2
End Term
Notes
To understand and
12. Image formation describe the Image
PPT,
Formation Mid Term
Lecture, CS4158.1,
To understand and I, Quiz &
Class CS4158.2
describe the Linear End Term
13. Linear filters and convolution Notes
filters and
convolution
To understand and PPT,
Mid Term
describe the Linear Lecture, CS4158.1,
14. Linear filters and convolution I, Quiz &
filters and Class CS4158.2
End Term
convolution Notes
To understand and PPT,
analytical image Mid Term
describe the shift Lecture, CS4158.1,
15. features & shift invariant linear systems I, Quiz &
invariant linear Class CS4158.2
Linear Filtering End Term
systems Notes
(7-17 Lecture)
To understand and PPT,
Mid Term
describe the spatial Lecture, CS4158.1 &
16. spatial frequency I, Quiz &
frequency Class CS4158.2
End Term
Notes
To understand and PPT,
Mid Term
describe the Fourier Lecture, CS4158.1 &
17. Fourier transforms I, Quiz &
transforms Class CS4158.2
End Term
Notes
Image To understand and PPT,
Mid Term
transformations use the image Lecture, CS4158.2 &
18. Image transformations I, Quiz &
and Colour transformation Class CS4158.3
End Term
models (19-20 methods Notes
19. lecture) Colour models To understand and PPT, CS4158.2, Mid Term
use the colour models Lecture, CS4158.3 I, Quiz &
Class End Term
Notes
 To understand and PPT,
Mid Term
use the colour models Lecture,
20. Colour models CS4158.2,CS4158.3 I, Quiz &
Class
End Term
Notes
To understand and PPT,
Mid Term
use the Laplacian Lecture,
21. Laplacian detectors CS4158.3 II, Quiz &
detectors Class
End Term
Notes
To understand and PPT,
Mid Term
use the Canny edge Lecture,
22. Canny edge detector CS4158.3 II, Quiz &
detectors Class
End Term
Notes
To understand and PPT,
Mid Term
describe Points and Lecture,
23. Points and patches CS4158.3 II, Quiz &
patches Class
End Term
Notes
To understand and PPT,
Mid Term
use the Harris corner Lecture,
24. Harris corner detector CS4158.2,CS4158.3 II, Quiz &
Edge Detection detectors Class
End Term
methods (21-30 Notes
Lecture) To understand and PPT,
Mid Term
describe Histogram of Lecture,
25. Histogram of Gradients CS4158.3 II, Quiz &
Gradients Class
End Term
Notes
To understand and PPT,
Mid Term
describe difference of Lecture,
26. Difference of Gaussian detector CS4158.3 II, Quiz &
Gaussian detector Class
End Term
Notes
To understand and PPT,
Mid Term
describe SIFT Lecture, CS4158.2,
27. SIFT II, Quiz &
Class CS4158.3
End Term
Notes
To understand about PPT,
Mid Term
Colour and Texture Lecture,
28. Colour and Texture CS4158.2 II, Quiz &
Class
End Term
Notes
To understand and PPT,
Mid Term
describe about Lecture,
29. Feature based alignment CS4158.3,CS4158.4 II, Quiz &
feature-based Class
End Term
alignment Notes
 To understand and PPT,
Mid Term
describe about least Lecture,
30. least squares and RANSAC CS4158.3,CS4158.4 II, Quiz &
squares and RANSAC Class
End Term
Notes
To understand and PPT,
Mid Term
Camera models, Camera desribe camera Lecture, CS4158.3,
31. II, Quiz &
calibration models and Class CS4158.4
End Term
calibration Notes
To understand and PPT,
Mid Term
Stereo vision, Stereo describe Stereo Lecture,
32. Camera model CS4158.3 II, Quiz &
correspondence vision, Stereo Class
(31-34 lecture) End Term
correspondence Notes
To understand and
33. Epipolar geometry Optical flow PPT,
describe Epipolar Mid Term
Lecture,
Lucas Kanade method, KLT geometry Optical CS4158.3 II, Quiz &
Class
34. tracking method, Mean shift flow,LK method,KLT End Term
Notes
method and MS methods
To understand and PPT,
apply dense motion Lecture, Quiz &
35. Dense motion estimation CS4158.4
estimation Class End Term
Notes
To understand and
36. Support Vector Machines apply support vector PPT,
machines Lecture, Quiz &
CS4158.4
Different To understand and Class End Term
Face detection and
37. Algorithms and use Face detection Notes
recognition
Deep CNN (35- and recognition
39 lecture) To understand and
38. Bag of words use the bags of
words PPT,
Deep To understand and Lecture, Quiz &
CS4158.4
apply the deep Class End Term
39. convolution convolutional neural Notes
neural network. network in different
applications
J. Course Articulation Matrix: (Mapping of COs with POs)
CORRELATION WITH PROGRAM OUTCOMES CORRELATION WITH
CO STATEMENT PROGRAM SPECIFIC
OUTCOMES
PO PO PO PO PO PO PO PO PO PO 10 PO 11 PO 12 PSO PSO PSO
1 2 3 4 5 6 7 8 9 1 2 3

Identify basic concepts, terminology, theories, 2 2 1 - 2 2 2 2 1 - - 3 2 2 -

CS 4158.1 models, and methods in the field of computer
vision and its application

Describe basic methods of computer vision

3 3 2 - 3 2 3 2 2 - - 3 2 2 -
CS 4158.2 related to multi-scale representation, filtering,
edge detection and other primitives

Use methods of computer vision related to 3 2 2 2 3 2 2 2 2 - - 2 1 2 -

CS 4158.3 camera model and calibration, stereo, motion and
object recognition

Developed the practical skills necessary to build

3 3 3 2 3 2 3 3 2 - - 3 2 3 -
CS 4158.4 computer vision applications using deep
convolution neural network.

1- Low Correlation; 2- Moderate Correlation; 3- Substantial Correlation