You are on page 1of 20

K S Institute of Technology, Bangalore

Department of Electronics and Communication Engineering

Presentation of Internship Work


On
Data Analyst Intern
By
Chethan D R (1KS17EC026)

Carried at
( Inversa Techno soft )

Under the guidance of

Internal Guide External Guide


Mr. Praveen A Mr. Rahul Kumar
(Assistant professor ECE Dept, KSIT) (Director-Trainer Inversa Techno soft)
Contents
• About Company
• Introduction slide
• Methodology
• Software Description
• Tests and Results
• Conclusion and Future Enhancement
• Reference
• Queries
About Company

• The company “Inversa Techno soft” coaches and guides a lot of technical and
non technical engineers with great aspirations.

• It is a forward-thinking, fast paced company looking to hire an intern with


strong knowledge and understanding of various social media websites.

• It offers professional technology courses in the field of VLSI, Embedded,


Communication industrial, PCB design , product design , AI&ML etc.
INTRODUCTION
The major concepts learned during the internship were:
• Python programming language and its major libraries such as NumPy, pandas,
scikit etc.

• The basic data science concepts.

• Face detection modules such as open cv, TensorFlow, matplotlib etc.

• Artificial intelligence types and algorithms


METHODOLOGY

 DATA SCIENCE

• blend of mathematics, business acumen, tools, algorithms and machine learning


techniques.

• It is an interdisciplinary field that uses scientific methods, processes, algorithms and


systems to extract knowledge and insights from structured and unstructured data.

• it applies knowledge and actionable insights from data across a broad range of
application domains.
METHODOLOGY CONT…

 Artificial Intelligence Subsets of AI:


• ML
• Artificial intelligence (AI) is wide-ranging branch
• Deep learning
of computer science concerned with building smart
machines . • Neural network
• Robotics
• AI refers to the simulation of human intelligence  • Computer vision
in machines that are programmed to think like
humans and mimic their actions. 
METHODOLOGY CONT…

 MACHINE LEARNING:
• A computer systems can provide sense
to data in much the same way as
human beings do.

• ML is a type of artificial intelligence


that extracts patterns out of raw data by
using an algorithm or method.

Machine learning model


METHODOLOGY CONT…

Fig. Face detection pre processing


METHODOLOGY CONT…

Fig. Face detection modules


Software Description

• Google Collaboratory is a free online cloud-based Jupyter notebook environment


that allows us to train our machine learning and deep learning models on CPUs,
GPUs, and TPUs.
• Collaboratory, or “Colab” for short, is a product from Google Research. 
• MATLAB is a proprietary multi-paradigm programming
language and numeric computing environment developed by
MathWorks.
• It is the easiest and most productive computing environment
for engineers and scientists.

MATLAB Advantages:

•Implement and test your algorithms easily.


•Develop the computational codes easily.
•Debug easily.
•Process still images and create simulation videos easily.
•Symbolic computation can be easily done.
•Call external libraries.
•Perform extensive data analysis and visualization.

MATLAB has applications in industry and academia, including deep learning and machine
learning, signal processing and communications, image and video processing.
Libraries used

OpenCV is an image and video processing library and is used for image and video analysis,
like facial detection, license plate reading, photo editing,
advanced robotic vision, optical character recognition, and a whole lot more.

dlib library, maintained by Davis King, contains our implementation of “deep metric learning” which is
used to construct our face embeddings used for the actual recognition process.

face recognition  library, created by Adam Geitgey, wraps around dlib’s facial recognition functionality,
and this library is super easy to work with and we will be using this in our code.
Remember to install dlib library first before you install face_recognition.

NumPy  is the fundamental package for scientific computing in Python.


It is arrays facilitate advanced mathematical and other types of operations on large numbers of data.
Work done by me

Code used
Source code
continues:
Tests and Results

Gray image

Original image

HSV image

Canny image
Tests and Results

By creating rectangle shape on


face, by using already trained
image or dataset the face
recognition module recognizes
the face of a person
Conclusion and Future Enhancement

• It was a wonderful experience taking up internship in inversa techno soft.

• gained some skills and experience that helps in our career development.

• The main skills we learned here are python and data science for developing
an AI

• gained basic face detection concepts as well as its important libraries.


Reference

[1]. Anna B. Holm. E-recruitment: Towards an ubiquitous recruitment process and candidate
relationship management. German Journal of Human Resource Management, 26(3):241–259, 2012.

[2]. Lori Foster Thompson, Phillip W. Braddy, and Karl L. Wuensch. E-recruitment and the benefits of
organizational web appeal. Computers in Human Behavior,24(5):2384 – 2398, 2008. Including the
Special Issue: Internet Empowerment.

[3]. Peter Kuhn and Hani Mansour. Is internet job search still ineffective? The Economic
Journal,124(581):1213–1233, 2014
QUERIES?
THANK YOU

You might also like