Scribd
Upload
3 views

cv syllabus

The document outlines a course on Visual Data Analysis and Machine Perception, focusing on key concepts in visual data analysis, image processing, motion analysis, and machine learning techniques. It includes five modules covering various topics such as image formation, image processing fundamentals, motion analysis methodologies, and applications in different domains. The course aims to equip students with the skills to analyze visual data and apply machine perception in real-world scenarios.

Uploaded by

N.vignesh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

cv syllabus

The document outlines a course on Visual Data Analysis and Machine Perception, focusing on key concepts in visual data analysis, image processing, motion analysis, and machine learning techniques. It includes five modules covering various topics such as image formation, image processing fundamentals, motion analysis methodologies, and applications in different domains. The course aims to equip students with the skills to analyze visual data and apply machine perception in real-world scenarios.

Uploaded by

N.vignesh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

VISUAL DATA ANALYSIS AND

CSDX 522 L T P C
MACHINE PERCEPTION
SDG :9 3 0 0 3

COURSE OBJECTIVES :
COB1:To understand the key concepts and techniques in visual data
analysis.
COB2:To familiarize with the fundamentals of image processing
techniques.
COB3: To gain knowledge on methodologies used for motion analysis.
COB4: To get insights on visual perception using machine learning and
deep learning techniques.
COB5: To explore the applications of visual data analysis and machine
perception.

MODULE I VISUAL DATA AND IMAGE FORMATION 09


Overview of Visual Data – Challenges in visual data analysis - Introduction
to Computer Vision – Image Formation - Geometric primitives – 2D
Transformations – 3D Transformations – 3D Rotations – 3D to 2D
projections - Photometric image formation - Digital camera.

MODULE II IMAGE PROCESSING 09


Fundamentals of image processing – Image Transforms – Image filtering
– Color image processing – Mathematical morphology – Image
segmentation - Image descriptors and features - Points and patches –
Edges – Lines.

MODULE III MOTION ANALYSIS 09


Feature-based Alignment – 2D, 3D feature-based alignment - Pose
estimation - Image Stitching - Dense motion estimation - Optical flow -
Layered motion - Parametric motion - Structure from Motion.

MODULE IV MACHINE PERCEPTION 09


Supervised learning for visual task – Convolutional Neural Networks –
Transfer Learning and Fine tuning - Object detection - Artificial Neural
Network for Pattern classification - Recurrent Neural Network – Generative
models for visual data.
MODULE V APPLICATIONS 09
Applications of Visual data analysis and Machine perception –
Performance-driven animation – Medical image segmentation –
Augmented Reality - Motion estimation and object tracking – Face and
facial expression recognition – Gesture recognition – Image fusion.

L – 45; TOTAL HOURS – 45


TEXT BOOKS:
1. Richard Szeliski,” Computer Vision: Algorithms and Applications”,
Springer; 2nd Edition, ISBN-13: 9783030343712, 2022.
2. Manas Kamal Bhuyan,” Computer Vision and Image Processing”,
CRC Press, ISBN: 9781351248389, 2019.

REFERENCES:
1. E. R. Davies,” Computer Vision: Principles, Algorithms,
Applications, Learning”, Elsevier Science, ISBN:
9780128095751,2017.

COURSES OUTCOMES :
Students who complete this course will be able to
CO1:Describe the various orientations of image formation perspectives.
CO2: Apply image processing techniques to analyse and enhance visual
data.
CO3: Develop systems for motion analysis and tracking objects.
CO4:Apply machine learning and deep learning methods to solve
computer vision problems.
CO5: Compare the applications of computer vision in various domains.

PO PO PO
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PSO1 PSO2
10 11 12

CO1 H H
CO2 H L H H M M H H
CO3 H H H H H
CO4 H H H H H
CO5 H M M L L H H

Note: L- Low Correlation M -Medium Correlation H -High Correlation


SDG 9: Build resilient Infrastructure, promote inclusive and sustainable
industrialization and foster innovation.

Statement: The holistic understanding of the basic principles and techniques of image
processing enable the computing devices to process, analyze and interpret visual
data in the most prominent industries including agriculture, healthcare, transportation,
manufacturing and retail.

You might also like