Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 25

1

CONTENTS
• Task performed.
• Python programming.
• Data structures.
• Object oriented Programming(oops).
• OpenCV.
• Artificial intelligence.
• Impact of technology.
• Machine learning and types
• Assigned Project
• Software’s used.
• Results.

2
About the company

3
• Friends Union for Energising Lives (FUEL)is a non-profit organisation with a mission to provide the youth
of the nation with access to essential information about career opportunities.

 MISSION
The company has a mission to be the guiding light for the future of our youth. Friends Union for
Energizing Lives (FUEL) is a non-profit organization with a mission to create a supporting community for
the youth of the nation. A community working towards providing them with the essential information and
right career opportunities. A one-stop community they can count on.

VISION
The has the vision to empower the youth and enable them to become the torch bearers of tomorrow.

4
TASK PERFORMED

The weekly task performed have been explained in detail, below which gives the overview of several concepts.
Week 1. Introduction to Python .
Week 2. Data structures .
Week 3. OpenCV using Python.
Week 4. Artificial Intelligence .

5
PYTHON PROGRAMMING

• Python is a computer programming language often used to build websites and software, automate tasks, and conduct
data analysis. Python is a general-purpose language, meaning it can be used to create a variety of different programs
and isn't specialized for any specific problems.

Features of Python

1. Simple

2. Easy to learn

3. Free and open source

4. High Level Language

5. Interpreted

6. Object Oriented etc…. 6


DATA STRUCTURES

• Data structure are used to store a collection of related data .

• There are four built-in data structures in Python.

1. list

2. tuple

3. dictionary

4. set

7
OBJECT ORIENTED PROGRAMMING (OOPs)

• Object-oriented programming is a programming paradigm that provides a means of structuring programs so


that properties and behaviors are bundled into individual objects .

1. Class
2. Method
3. Object

8
OpenCV
• Object-oriented programming is a programming paradigm that provides a means of structuring programs so
that properties and behaviors are bundled into individual objects.

• OpenCV now supports a multitude of algorithms related to Computer Vision and Machine Learning and is
expanding day by day.

• OpenCV supports a wide variety of programming languages such as C++, Python, Java, etc., and is available
on different platforms including Windows, Linux, OS X, Android, and iOS.

• OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning
software library. OpenCV was built to provide a common infrastructure for computer vision applications and
to accelerate the use of machine perception in the commercial products.

9
ARTIFICIAL INTELLIGENCE
• Artificial intelligence (AI) is intelligence demonstrated by machines, as opposed to natural intelligence displayed
by animals including humans.

• AI applications include advanced web search engines (e.g. Google), recommendation systems (used by YouTube,
Amazon and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g. Tesla),
automated decision-making and competing at the highest level in strategic game systems (such as chess and Go).

• AI research has tried and discarded many different approaches since its founding, including simulating the brain,
modelling human problem solving, formal logic, large databases of knowledge and imitating animal behavior.

• The term "Artificial Intelligence" refers to the simulation of human intelligence processes by machines, especially
computer systems. It also includes Expert systems, voice recognition, machine vision, and natural language
processing (NLP).

10
IMPACT OF TECHNOLOGY

Fig: Growth of technology


Reference: https://encryptedtbn3.gstatic.com/images?
11
q=tbn:ANd9GcQjMbobdL_31zD7h834sn7t5TH18aGEeDEKO2e2vqcPuegqUacw
TYPES OF ARTIFICIAL INTELLIGENCE

Fig. Types of Artificial Intelligence

12
BRANCHES OF ARTIFICIAL INTELLIGENCE

Fig. Branches of artificial intelligence


Reference: https://chethankumargn.medium.com/artificial-intelligence-definition-types-examples-technologies-962ea75c7b9b

13
Machine Learning

Fig. Steps in machine learning


Reference: http://biss.co.in/kzdd.aspx?iid=50859953-unsupervised+learning+ml&cid=7

14
Fig. Types of Machine Learning
Reference: https://towardsdatascience.com/types-of-machine-learning-algorithms-you-should-know-953a08248861

15
1) Semi-Supervised Learning

• Semi-Supervised learning is a type of Machine Learning algorithm that lies between Supervised and Unsupervised
machine learning.

• To overcome the drawbacks of supervised learning and unsupervised learning algorithms, the concept of Semi-supervised
learning is introduced.

Advantages:
• It is simple and easy to understand the algorithm.
• It is highly efficient.

Disadvantages:
• Iterations results may not be stable.
• Accuracy is low

16
2) Reinforcement Learning
Reinforcement learning works on a feedback-based process, in which an AI agent (A software component)
automatically explore its surrounding by hitting & trail, taking action, learning from experiences, and improving
its performance. 

Categories of Reinforcement Learning:


1) Positive Reinforcement Learning
2) Negative Reinforcement Learning

Real-world Use cases of Reinforcement Learning:


i. Video Games
ii. Resource Management
iii. Robotics
iv. Text Mining
17
Advantages and Disadvantages of Reinforcement Learning

Advantages:
• It helps in solving complex real-world problems which are difficult to be solved by general techniques.
• Helps in achieving long term results.
• The learning model of RL is similar to the learning of human beings; hence most accurate results can be
found.

Disadvantage:
• RL algorithms are not preferred for simple problems.
• RL algorithms require huge data and computations.
• Too much reinforcement learning can lead to an overload of states which can weaken the results.

18
ASSIGNED PROJECT

• project was performed on people counter using yolov3, deep sort, TensorFlow using python code.

• At present due to covid it very necessary to have social distancing and to maintain a social distance in malls
or shops is a difficult task

• This project could help the owner of the shop to limit the number of people entering his shop.

• The repository implements YOLOv3 and Deep SORT in order to perform real-time object tracking.

• Yolov3 is an algorithm that uses deep convolutional neural networks to perform object detection.

19
SOFTWARES USED

1. Python 3.6
• Python is an interpreted high-level general-purpose programming language.

• Its design philosophy emphasizes code readability with its use of significant indentation.

• Its language constructs as well as its object-oriented approach aim to help programmers write clear, logical
code for small and large-scale projects.

• It supports multiple programming paradigms, including structured (particularly, procedural), object-oriented


and functional programming.

20
2. GIT GUI

• Git has its native environment within the terminal.

• All the new features are updated first at the command line, and only there is the full power of Git.

• It focuses on allowing users to make changes to their repository by making new commits, amending existing
ones, creating branches, performing local merges, and fetching/pushing to remote repositories.

21
3. TENSOR FLOW
• TensorFlow is a free and open-source software library for machine learning and artificial intelligence.

• It can be used across a range of tasks but has a particular focus on training and inference of deep neural
networks.

• TensorFlow can be used in a wide variety of programming languages, most notably Python, as well as
JavaScript , C++, and Java.

22
4. Yolov3

• YOLO is a Deep Learning architecture proposed by Joseph Redmon, Santosh Divvala, Ross Girshick , Ali
Farhadi in the paper ‘You Only Look Once: Unified, Real-Time Object Detection’ uses a totally different
approach.

• It is a clever convolutional neural network (CNN) for object detection used in real-time.

• The YOLO algorithm “only looks once” at the input image needs only one forward propagation pass through
the network to make the predictions.

23
Various layers in operation of Yolov3.

Fig. Layers in Yolov3


Reference: https://viso.ai/deep-learning/yolov3-overview/f

24
RESULTS

Fig. Result1
25

You might also like