AICTE EDUSKILLS

AI-ML VIRTUAL
INTERNSHIP
An Internship Report Submitted at the end of seventh semester

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING

Submitted By
REDDY JANAKI RAM
(213J1A05E6)

Under the esteemed guidance of

Mr. A.Appala Narasimham
Assistant Professor

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

RAGHU INSTITUTE OF TECHNOLOGY

(AUTONOMOUS)
Affiliated to JNTU GURAJADA, VIZIANAGARAM
Approved by AICTE, Accredited by NBA, Accredited by NAAC with A grade

2024-2025
 RAGHU INSTITUTE OF TECHNOLOGY
(AUTONOMOUS)
Affiliated to JNTU GURAJADA, VIZIANAGARAM
Approved by AICTE, Accredited by NBA, Accredited by NAAC with A grade

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that this project entitled “AI-ML” done by “REDDY JANAKIRAM (213J1A05E6)” is a
student of B.Tech in the Department of Computer Science and Engineering, Raghu Institute of Technology, during
the period 2021-2025, in partial fulfillment for the award of the Degree of Bachelor of Technology in Computer
Science and Engineering to the Jawaharlal Nehru Technological University, Gurajada Vizianagaram is a record of
bonafide work carried out under my guidance and supervision.

The results embodied in this internship report have not been submitted to any other University or
Institute for the award of any Degree.

Internal Guide Head of the Department

Mr.A. Appala Narasimham Dr.R. Sivaranjani,
Assistant Professor Professor

EXTERNAL EXAMINER

i
 DISSERTATION APPROVAL SHEET
This is to certify that the dissertation titled
OBJECT DETECION USING AI
BY
REDDY JANAKIRAM
(213J1A05E6)

Is approved for the degree of Bachelor of Technology

MR.A.APPALA NARASIMHAM
PROJECT GUIDE
(Assistant Professor)

Internal Examiner

External Examiner

DR.R. SIVARANJANI
HOD
(Professor)

Date:

ii
 DECLARATION

This is to certify that this internship titled “AI-ML” is bonafied work done by my me,
impartial fulfillment of the requirements for the award of the degree B.Tech and submitted to the
Department of Computer Science and Engineering, Raghu Institute of Technology,
Dakamarri.
I also declare that this internship is a result of my own effort and that has not been copied
from anyone and I have taken only citations from the sources which are mentioned in the
references.
This work was not submitted earlier at any other University or Institute for the reward of
any degree.

Date:
Place:

REDDY JANAKIRAM

(213J1A05E6)

iii
CERTIFICATE

iv
 ACKNOWLEDGEMENT

I express sincere gratitude to my esteemed Institute “Raghu Institute of Technology”, which

has provided us an opportunity to fulfill the most cherished desire to reach my goal.

I take this opportunity with great pleasure to put on record our ineffable personal
indebtedness to Mr. Raghu Kalidindi, Chairman of Raghu Institute of Technology for
providing necessary departmental facilities.

I would like to thank the Principal Dr.V. Satyanarayana of “Raghu Institute of

Technology”, for providing the requisite facilities to carry out projects on campus. Your
expertise in the subject matter and dedication towards our project have been a source of
inspiration for all of us.

I sincerely express our deep sense of gratitude to Dr.R. Sivaranjani, Professor, Head of
Department in Department of Computer Science and Engineering, Raghu Engineering College,
for her perspicacity, wisdom and sagacity coupled with compassion and patience. It is my great
pleasure to submit this work under her wing. I thank for guiding us for the successful completion
of this project work.

I would like to thank Mr. A.APPALA NARASIMHAM, Assistant Professor for

providing the technical guidance to carry out module assigned. Your expertise in the subject
matter and dedication towards our project have been a source of inspiration for all of us.

I extend my deep hearted thanks to all faculty members of the Computer Science
department for their value-based imparting of theory and practical subjects, which were used in
the project.

Regards
REDDY JANAKIRAM
(213J1A05E6)
v
 TABLE OF CONTENTS

S.NO CONTENT PAGE NUMBER

1. INTRODUCTION 7

2. PROBLEM STATEMENT 8

3. SYSTEM REQUIREMENTS 9

4. SYSTEM DESIGN 10

5. IMPLEMENTATION 11

6. RESULTS 13

7. TESTING 16

8. CONCLUSIONS 19

vi
 INTRODUCTION

Object detection using AI is incredibly important in today's world due to its

wide range of applications across various industries, improving efficiency, safety, and
decision-making.Object detection powers features like face recognition, organizing
photos,identifies pedestrians, vehicles, and road signs,detect diseases in medical
images,Smart cameras with AI detect intruders.In short, object detection simplifies
tasks, enhances safety, and improves convenience in everyday life.

This documentation outlines the development and integration of pretrained

object detector into mobile app using Tensorflow and ML KIT.It includes
development and training of a image classification model using tensor flow lite model
maker .The object detector helps in detecting objects in a given image and the image
classifier classifies the images into respective classes .

The object detection model includes features such as multiple objects detecting
ability in a image matching with high accuracy , which further helps further in
reducing human effort in detecting such objects in image. This detection further uses
image classifiers to classify the objects into their respective fields.we use response of
vision api’s in product search.

Keywords: o b j e c t d e t e c t i o n , tensorflow,image classification,ML kit etc;

vii
 PROBLEM STATEMENT

In digital landscape, we the people want to reduce the human effort and tries to
complete our tasks by using ai where it finds the patterns and works it is some what
difficult to find patterns and give input to the machine as to train the machine to work
itself. To find patterns it is very necessary to handle the real time data and handle with
the data.In handling the data the main task is to find the objects in a image or a video.

To address these challenges, there is a need for a solution that enables object
detection in media like images and videos. Exactly the same thing the projects
highlights and it shows how the detection model are developed and the training
process and the testing phase and the data training phase etc,.

This project seeks to design and implement a object detection and classification
model with a high accuracy using ai and this must work well with unseen data and in
the real time projects also . It tries to avoid low accurate detection and high time
taking process and unwanted classification.

8
 SYSTEM REQUIREMENTS

Software Requirements:

1. ML kit Object detection api: The application requires object detection feature, this feature
we can integrate using ml kit.

2. Tensorflow Lite model maker: The application requires Tensorflow for building object
detection model, and how to develop custom ml models and how to train the model for
better accurate outputs.sub libraries like tflite task library is used for deploying the
model.
3. Development Environment: Android studio verison 4.2+ is mainly used entirely in this
project for code execution and building models and training them.
4. Python : The entire project done in python language which requires an python with
latest version.

Hardware Requirements:

 Processor - Intel(R) Core (TM) i5-6300U CPU @ 2.40GHz 2.50 GHz

 Speed - 1.1 Ghz

 RAM - 8 GB

 Hard Disk - 20 GB

 Keyboard - Standard Windows Keyboard

 Mouse - Two or Three Button Mouse

 Monitor - SVGA
9
 SYSTEM DESIGN

The tensorflow uses CNN layers for data preprocessing. The model is definied with

several layers. Every layer has it specific task .The sequence layer is used to define the

sequence of layers in model.flatten layer takes 2d data and converts in vector etc,. we

train the model with training data and test with testing samples.

In the model we can change the algorithms for accuracy and depending on the usage of model.

10
 IMPLEMENTATION

STEP-1: Import tensorflow library and check for version 2.17.0

STEP-2: Collect the data sets of different clothes.
STEP-3: Divide the entire data set into testing and training sets using
load_data() function.
STEP-4: For handling with images we need to import matplot library.
STEP-5:Normalizing the training and testing data to set bounded values.
STEP-6:Designing the model with multiple layers with 128 layers and adding activation function to
tell the models what to do.
STEP-7: We do compile the model with a loss and a optimizer function.
STEP-8:We ask the model to fit the training data into training labels using fit function.
STEP-9: We test model with testing data set using evaluate function.
STEP-10: We verify the output and their accuracy.

11
The following are the features of the object detection model:

1. Multiple Object detection: It detects multiple objects in the single image if present and
matches with high acuuracy data.

2. Diversified Data: The model takes diversified data which leads to a machine which work
accurately with unseen data.

3. High accuracy: This model contains multiple layers which gives a high accurate prediction
and detection too.

4. Classification: After detection it mainly works on classification of objects in the image and
classifies it into labels.

5. Testing : After model making we test the model with testing data and checks the
accuracy and loss percentages which tells about the can send and receive messages
instantly, providing asmooth and responsive chatting experience.

12
RESULTS

13
14
15
 TESTING

Unit Testing:

Testing individual units or components of code to ensure they function correctly without errors.

16
Functional Testing:

RESULTS OF CLASSIFICATION:

17
18
 CONCLUSION

In conclusion,we developed a image prediction model using ai by training

ai model with diversified data and using tensor flow technologies and many
algorithms and cnn networks for building a model.which we guaranteed with
our testings .The project highlighted the importance and the usage of object
detection in daily life in many sectors.

The application effectively detects the real time images too which uses in
self driving cars and this process used in shopping sector and google lens
too.and mainly in ai-ml projects for face detecing and mask detecting etc,.

In conclusion, this project demonstrates the power of artificial intelligence in

addressing real-world problems, specifically in the object detection in images The
model not only aids in identifying the object but also classifies the objects into their
respective labels and classes.

19