Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
6 views

First Page Final

This document describes a project report on implementing a deep learning-based food nutritional intake tracking system using convolutional neural network algorithms. The system aims to automatically detect nutritious foods and create an accurate system to monitor a user's daily nutrition levels and provide suggestions to maintain a balanced diet. The system consists of modules for input acquisition, image preprocessing and segmentation, feature extraction, dataset training, nutrition level estimation, and suggestion generation. Convolutional neural networks are used to classify food images and estimate their nutritional content.

Uploaded by

Dhilip
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
6 views

First Page Final

This document describes a project report on implementing a deep learning-based food nutritional intake tracking system using convolutional neural network algorithms. The system aims to automatically detect nutritious foods and create an accurate system to monitor a user's daily nutrition levels and provide suggestions to maintain a balanced diet. The system consists of modules for input acquisition, image preprocessing and segmentation, feature extraction, dataset training, nutrition level estimation, and suggestion generation. Convolutional neural networks are used to classify food images and estimate their nutritional content.

Uploaded by

Dhilip
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

DEEP LEARNING BASED IMPLEMENTATION

OF FOOD NUTRITIONAL INTAKE TRAKING


SYSTEM USING CONVOLUTION NEURAL
NETWORK ALGORITHM

A PROJECT REPORT

Submitted by

VINAYAKAM DHILIP KUMAR AC18UCS136

in partial fulfillment for the award of the


degree of

BACHELOR OF ENGINEERING

In

COMPUTER SCIENCE AND ENGINEERING

ADHIYAMAAN COLLEGE OF ENGINEERING


(AUTONOMOUS)

Dr. M.G.R NAGAR, HOSUR

ANNA UNIVERSITY :: CHENNAI 600


025 OCTOBER 2021

ANNA UNIVERSITY: CHENNAI 600 025

I
BONAFIDE CERTIFICATE

Certified that this main project report “DEEP LEARNING BASED IMPLEMENTATION
OF FOOD NUTRITIONAL INTAKE TRAKING SYSTEM USING CONVOLUTION
NEURAL NETWORK ALGORITHM” is the bonafide work of “VINAYAKAM DHILIP
KUMAR (AC18UCS136), who carried out the project under my supervision.

SIGNATURE SIGNATURE

Dr G. FATHIMA, M.E., Ph.D., Mrs. A. SHOBANA ME.,

HEAD OF THE DEPARTMENT ASSISTANT PROFESSOR,


PROFESSOR,

Department of CSE, Department of


CSE,

Adhiyamaan College of Adhiyamaan College of


Engineering, Engineering,
(Autonomous) (Autonomou
s)

Dr. M.G.R. Nagar, Dr. M.G.R.


Nagar,

Hosur – 635 130 Hosur – 635


130

Submitted for the Main project VIVA-VOCE Examination held on ____________ at


Adhiyamaan College of Engineering (Autonomous), Hosur-635 130.

INTERNAL EXAMINER EXTERNAL EXAMINER

II
ACKNOWLEDGEMENT

It is one of the most efficient tasks in life to choose the appropriate words to
express one’s gratitude to the beneficiaries. We are very much grateful to god who
helped us all the way through the project and how moulded us into what we are today.

We are grateful to our beloved Principal Dr. G. RANGANATH, M.E., Ph.D.,


Adhiyamaan College of Engineering (Autonomous), Hosur for providing the
opportunity to do this work in the premises.

We acknowledge our heartfelt gratitude to Dr. G. FATHIMA, ME., Ph.D.,


Professor and Head of the Department, Department of Computer Science and
Engineering, Adhiyamaan College of engineering (Autonomous), Hosur, for her
guidance and valuable suggestions and encouragement throughout this project.

We are highly indebted to Mrs. A. SHOBANA, ME.,

Assistant Professor, Department of Computer Science and Engineering,


Adhiyamaan College of engineering (Autonomous), Hosur, whose immense support,
encouragement and valuable guidance made us to complete this project successfully.

We also extent our thanks to Project Coordinator and all Staff Members for
their support in completing the project successfully.

Finally, we would like to thank our parents, without their motivations and
support would not have been possible for us to complete this project successfully.

III
ABSTARCT

Nutrition is an important basis for the development of the human body.


Malnutrition can lead to a weakening of the immune system, an increased risk of
various diseases, and the development of poor physical and mental health. This project
based on in-depth study will automatically detect nutritious foods and create an
accurate system in which we find that nutritional levels in the diet increase the level of
nutritional or poor nutrition. Monitor nutrition in their diet and maintain daily health
records. The quality of the nutrition is maintained on the website. The level of the
elements should be compared to the site using the convolution neural network (CNN)
algorithm. Collected databases should be reviewed after 7 days when food levels are
healthy or nutritious. If the level of healthy eating is not good the methods try to eat
more protein and fat and light sugars and walking or engage in less activity to
stimulate your appetite. It is about building a healthy and balanced diet and is essential
for a healthy lifestyle. The technology is useful in developing a daily diet plan aimed
at recommending the most popular foods for the user, which can be eaten as soon as
possible, and to satisfy one's daily nutritional needs

IV
TABLE OF CONTENTS

CHAPTER TITLE PAGE


NO NO
ABSTRACT IV

LIST OF FIGURES

1 INTRODUCTION 1
1.1. OVERVIEW
2
1.2 .OBJECTIVE
2 LITERATURE SURVEY 3
3 SYSTEM ANALYSIS 7
3.1 EXISTING SYSTEM 7
3.2 PROPOSED SYSTEM 8
4 SYSTEM FUNCTION 9
4.1 ARCHTECTURE DESIGN 9
4.2 MODULE DESCRIPTION 10
4.2.1 INPUT ACQUISITION MODULE 10
4.2.2 IMAGE PREPROCESSING AND 10
SEGMENTATION MODULE
4.2.3 FEATURE EXTRACTION 11
MODULE 11
4.2.4 DATASET TRAINING MODULE 11
4.2.5 NUTRITION LEVEL 11
ESTIMATION MODULE
4.2.6 SUGGESTION MODULE 11

5 SYSTEM SPECIFICATION 12
5.1 HARDWARE SPECIFICATION 12

5.2 SOFTWARE SPECIFICATION 12


12
5.3 CONVOLUTIONAL NEURAL
NETWORK

6 SYSTEM SOFTWARE 26
V
6.1 PYQT5 26
6.2 PYTHON PROGRAMMING LANGUAGE 35
6.2.1 PYTHON INTRODUCTION 37
6.2.2 PYTHON INSTALLATION 39
6.2.3 RUNNING AND DEBUGGING 48
7 HARDWARE REQUIREMENTS AND 54
SPECIFICATIONS
7.1 ADVANCED MICRO DEVICES
7.1.1PROS OF AMD PROCESSOR 54

7.1.2 CONS OF AMD PROCESSOR 56


7.2 RAM(RANDOM ACCESS MEMORY)
7.2.1 HISTORY OF RAM
58
7.2.2 STATIC RAM
59
7.2.3 DYNAMIC RAM
60

8 RESULTS 64

9 CONCLUSION 65

SOURCE CODE 66

OUTPUT 80

10 REFERENCE 81

VI
LIST OF FIGURES

FIGURE NO FIGURE NAME PAGNO


4.1 BLOCK DIAGRAM FORPROPOSED 9
SYSTEM
5.1 FOOD CNN ALGORITHM 13
5.2 CONVOLUTION LAYER 14
5.3 RELU LAYER 15
5.4 POOLING LAYER 15
5.5 PBT FOOD IMAGE 18
5.6 HSV IMAGE 21
6.1 QMAIN WINDOW 28
6.2 PYQT5MAIN WINDOW 29

6.3 DIALOG BOX 29

6.4 FORM PAGE 30

7.1 AMD PROCESSOR 54

7.2 PROCESSOR WORK CHART 57

7.3 STATIC RAM 60

7.4 DYNAMIC RAM 61

8.1 POOR FOOD DETECT 64

VII
VIII

You might also like