Name: M.

MOUNIKA
Designation: Assistant Professor
Subject: NATURAL LANGUAGE PROCESSING

The teaching plan should have the following components

SL.No. Course Course Title Class room Lab Team Total

Code instruction Instructions in work no.
in hours hours (TM)+ Of
per per semester Self hours
semester learning per
(SL) week
L T P
01 D86PE4 COMPUTER 35 11 0 5 51
VISION

NATURAL LANGUAGE PROCESSING

Tutorial-based Learning :The Computer Vision subject, as defined by the given syllabus, focuses on
enabling students to understand and implement the principles and algorithms that allow computers to
interpret and process visual data. It spans a variety of topics crucial for processing and analyzing images,
with an emphasis on mathematical, physical, and computational approaches.
This course combines theoretical learning with hands-on tutorials and coding exercises to prepare students
for practical applications in computer vision, such as object recognition, image segmentation, and 3D
modeling.
Self-learning:Learning computer vision offers numerous benefits, including access to high-demand
career opportunities.Mastering computer vision provides valuable skills in AI, machine learning,
and image processing, helping solve real-world problems and enhancing user experiences.
Additionally, it gives you a competitive edge in the tech industry, allowing you to contribute to
cutting-edge advancements and research in both academic and practical settings.

Aspect Tutorial-Based Learning Self-Learning

Teaches step-by-step visual Machine Learning for Computer
Structure processing techniques and tasks Vision
(e.g., image classification, object
detection).
Provides clear instructions and Encourage exploration of
Guidance
support through structured algorithms and model architectures.
lessons.
Helps students visualize concepts Use of real-world datasets and open-
Interactivity like feature extraction and source tools (e.g., OpenCV,
convolutional layers through TensorFlow).
hands-on exercises.
Break down tasks like image Start with fundamental topics (e.g.,
Pacing preprocessing, edge detection, and image processing, CNNs) and
model training. Hands-on: Build a gradually progress to complex tasks
simple image classifier. as confidence grows.
Equip students with practical skills Emphasize hands-on coding, model
Focus in building and training vision building, and experimentation. Dive
models. Basic tasks: Object into advanced topics: transfer
detection, segmentation, image learning, GANs, or 3D vision.
classification.
 Immediate feedback from Self-assessment through coding
Feedback exercises, quizzes, and challenges, discussions in online
assignments. (via platforms like communities, and mentor feedback.
Google Forms or learning
management systems)
Learners with a basic
Target Beginners or those with limited understanding of programming and
Learners experience in computer vision. machine learning.
Building scalable, efficient
Motivations Learning to use vision libraries like computer vision systems and
OpenCV, PyTorch, and understanding cutting-edge models.
TensorFlow means getting hands-
on experience with tools that help
computers "see" and understand
images or videos. These libraries
are used to create applications like
facial recognition, object detection,
and image classification in real-
world projects.
Encourage independent exploration,
Learning Online tutorials, video lessons, reading research papers, and
Resources textbooks, and MOOCs (e.g., contributing to open-source projects.
Coursera, Udemy). Practical Use documentation, forums, and
exercises and case studies. blogs.

Course Outcomes:
S.No Description Bloom’s Taxonomy Level
1 Able to Show Implemention of fundamental image L3:
processing techniques required for computer vision.
2 Perform shape analysis and Implement L4:
boundary tracking techniques.L4
3 Apply chain codes and other region L3:
descriptors.
4 Apply Hough Transform for line, circle, L3:
and ellipse detections and 3D vision
techniques
5 Develop applications using motion L3:
related and computer vision techniques

Syllabus:

UNIT – I:

CAMERAS: Pinhole Cameras, Radiometry – Measuring Light: Light in Space, Light Surfaces, Important
Special Cases, Sources, Shadows, And Shading: Qualitative Radiometry, Sources and Their Effects, Local
Shading Models, Application: hotometric Stereo, Inter reflections: Global Shading Models, Color: The
Physics of Color, Human Color Perception, Representing Color, A Model for Image Color, Surface Color
from Image Color.
Here's a similar lesson plan format for Unit I: Cameras and Radiometry:

Time in No. of Lecture/Tutorial/Self

SL. No Topic(s) to be covered Teaching Aid
Minutes Sessions Learning
CAMERAS AND
Unit-I
RADIOMETRY
Introduction to Pinhole
1. 15M 1 Lecture PPT
Cameras
Overview of Pinhole
10M Lecture
Camera Principles
Discussion about real-
world camera models and
15M Discussion
their connection to Pinhole
Camera
Conclusion on Pinhole
5M
Camera Concept
Light Propagation and
2. 25M 1 Lecture PPT
Interaction with Surfaces
Light in Space: Concept
and Types of Light Sources
15M Lecture
(Point, Directional,
Ambient)
Surface Reflection and
10M Lecture
Transmission
3. Shading and Shadows 40M 1 Lecture PPT
Shadows: Umbra,
Penumbra, and Their 20M Lecture
Formation
Introduction to Local
15M Lecture
Shading Models
Class Discussion on
Shadows in Real-World 5M Classroom Discussion
Scenes
Global Shading Models
4. 40M 1 Lecture PPT
and Interreflections
Global Shading Effects
20M Lecture
(Radiosity, Ray Tracing)
Interreflections and Their
15M Lecture
Impact on Image Realism
Real-time Example
Discussion on Global 5M Classroom Discussion
Shading Applications
Introduction to Color and
5. its Representation in 30M 1 Lecture PPT
Computer Vision
The Physics of Color and
15M Lecture
Human Color Perception
Color Models (RGB, HSV,
CMYK) and Their Use in 15M Lecture
Image Processing
Extracting Surface Color
6. 30M 1 Lecture PPT
from Image Color
Methods to Extract and
Represent Surface Color in 20M Practical Demo OpenCV/TensorFlow
Images
Class Activity on Color
Representation and Color 10M Classroom Activity
Models
 Time in No. of Lecture/Tutorial/Self
SL. No Topic(s) to be covered Teaching Aid
Minutes Sessions Learning
Practical Application of
7. Hotometric Stereo and 40M 1 Tutorial Video/Software
Color Shading Models
Hotometric Stereo: Theory
and Application in Depth 20M Tutorial
Estimation
Color Shading Models and
20M Tutorial
Real-World Applications
Student-Centered
Approach to Implementing Student-Centered
8. 30M 1 OpenCV/TensorFlow
Simple Shading and Color Activity
Models
Building Basic 3D Models
using Hotometric Stereo 20M Student Work
Techniques
Summary of Key Concepts
9. in Cameras and 15M 1 Lecture PPT
Radiometry
Recap of Shading, Color,
and Light Interaction in 10M Lecture
Computer Vision
Q&A and Discussion on
5M Classroom Discussion
Real-World Applications
Final Project and
10. 50M 1 Self Learning Slide
Evaluation
Final Project: Applying
Camera and Radiometry
40M Project Work
Concepts to a Real-World
Scenario
Assignment Submission
10M
and Conclusion
Total
10
Classes
Sessions
for Unit-I

Lesson Plan Unit-1

What are sustainable goals in engineering education

The Sustainable Development Goals (SDGs), established by the United Nations in 2015, are a universal
call to action to address global challenges such as poverty, inequality, climate change, and peace. Natural
Language (NL) technologies, including Natural Language Processing (NLP), play a crucial role in
advancing these goals by enabling more inclusive, accessible, and sustainable solutions in various sectors.
Below, I'll outline how NL and NLP can contribute to each of the 17 SDGs.
1. No Poverty (SDG 1)

 NL Impact: NLP can help in understanding and addressing poverty-related issues through social
media monitoring, analyzing financial accessibility, and interpreting public policy debates.
 Examples:
o Using NLP to extract insights from financial reports, poverty indices, and surveys.
o Analyzing text data from news, social media, and government reports to identify regions with
high poverty risks and design interventions.

2. Zero Hunger (SDG 2)

 NL Impact: NLP can support efforts to tackle food security by analyzing agricultural reports,
predicting food shortages, or processing satellite data and farmer feedback.
 Examples:
 o Using NLP to analyze crop reports, weather patterns, and social media posts about food
supply chains.
o Enhancing food aid distribution by analyzing public communications and local demands.

3. Good Health and Well-being (SDG 3)

 NL Impact: NLP is essential in healthcare by improving medical documentation, enhancing health

chatbots, and analyzing vast amounts of medical literature to identify trends.
 Examples:
o Automated clinical transcription, improving diagnostic accuracy.
o NLP-based tools for interpreting health records, symptoms, or social media sentiment related
to public health crises (e.g., during pandemics).

4. Quality Education (SDG 4)

 NL Impact: NLP can revolutionize education by enabling automatic grading systems, language
learning tools, and personalized learning assistants.
 Examples:
o Language translation tools to break language barriers in education.
o NLP-powered chatbots to provide 24/7 tutoring and assistance to students worldwide.

5. Gender Equality (SDG 5)

 NL Impact: NLP can be used to analyze and promote gender equality by detecting gender bias in
texts, promoting inclusive language, and providing gender-sensitive insights.
 Examples:
o Analyzing media and social platforms for gender-related biases.
o Building systems that assist women in marginalized communities through voice-based
applications or language learning tools.

6. Clean Water and Sanitation (SDG 6)

 NL Impact: NLP can assist in analyzing environmental reports, water usage data, and public feedback
related to water management and sanitation.
 Examples:
o Processing water quality reports, government publications, and social media discussions to
detect areas facing water scarcity or contamination.
o Analyzing community surveys or complaints to identify gaps in water and sanitation
infrastructure.

7. Affordable and Clean Energy (SDG 7)

 NL Impact: NLP can help by processing energy consumption data, public policy reports, and
environmental impact statements, promoting energy efficiency and clean energy adoption.
 Examples:
o NLP tools for analyzing legislative documents or public opinions on energy policies.
o Creating tools to monitor energy consumption through real-time analysis of text-based data,
such as user feedback or smart grid communications.

8. Decent Work and Economic Growth (SDG 8)

 NL Impact: NLP enables improved job matching, workforce analysis, and economic development
through the analysis of labor market trends and employment opportunities.
 Examples:
o NLP-driven job portals that match candidates with the right jobs based on resumes, job
descriptions, and skills.
o Analyzing business news, reports, and social media for trends that could foster economic
development.

9. Industry, Innovation, and Infrastructure (SDG 9)

  NL Impact: NLP can drive innovation by automating technical documentation, enabling smart city
projects, and optimizing supply chain management.
 Examples:
o Using NLP to analyze and summarize scientific research, driving innovation.
o Processing real-time data from infrastructure monitoring systems to improve smart city
initiatives.

10. Reduced Inequalities (SDG 10)

 NL Impact: NLP tools can help reduce inequalities by analyzing marginalized groups’ concerns and
addressing language barriers in public communication and legal systems.
 Examples:
o NLP models for language translation to ensure equitable access to government resources.
o Analyzing texts (news, reports) for indicators of social inequality and providing insights to
policymakers.

11. Sustainable Cities and Communities (SDG 11)

 NL Impact: NLP can assist in creating sustainable communities by analyzing social media data,
public complaints, and community feedback to improve urban living conditions.
 Examples:
o Analyzing urban planning documents, social media discussions, and community feedback to
enhance city infrastructure and services.
o Using sentiment analysis to assess public opinions on environmental sustainability and urban
development.

12. Responsible Consumption and Production (SDG 12)

 NL Impact: NLP can facilitate responsible consumption by analyzing consumer behavior, product
reviews, and corporate sustainability reports to improve decision-making.
 Examples:
o Analyzing social media and review sites to track consumer attitudes toward sustainable
products and services.
o NLP tools for processing corporate sustainability reports to promote transparency and
responsible business practices.

13. Climate Action (SDG 13)

 NL Impact: NLP can process environmental data, climate research, and policy documents,
contributing to more informed climate change action.
 Examples:
o Analyzing climate change reports and public communications to predict trends and inform
policies.
o Processing and summarizing scientific literature to inform climate change research and action
plans.

14. Life Below Water (SDG 14)

 NL Impact: NLP can support marine conservation by analyzing reports on marine biodiversity, water
quality, and fishing practices.
 Examples:
o Analyzing social media and environmental reports for trends related to marine pollution or
illegal fishing.
o Automatically summarizing scientific publications related to marine ecosystems to aid
conservation efforts.

15. Life on Land (SDG 15)

 NL Impact: NLP can help track biodiversity, deforestation, and land use changes by processing
satellite imagery reports, environmental documents, and community feedback.
 Examples:
 o Analyzing environmental impact reports and government policies on land use and
conservation.
o Identifying deforestation patterns through the analysis of texts and reports from conservation
organizations.

16. Peace, Justice, and Strong Institutions (SDG 16)

 NL Impact: NLP can enhance governance by analyzing legal texts, reports on human rights, and
public sentiment to promote transparency and accountability.
 Examples:
o Automating the analysis of legal documents and human rights reports.
o Using NLP for monitoring and combating hate speech, fake news, and online violence that
undermine social justice.

17. Partnerships for the Goals (SDG 17)

 NL Impact: NLP can facilitate global cooperation by analyzing international policy documents,
research, and collaborations across borders.
 Examples:
o Using NLP to analyze and summarize multilateral agreements and research to foster cross-
border cooperation.
o Promoting knowledge-sharing platforms through NLP tools that translate and interpret
materials for global accessibility.