A Mini-Project Report

on

Detection of food items with their Calorie and Nutrients

Data

SUBMITTED BY

Student name Exam seat No.

1. Ujwal Murudi T150083089

2. Sanidhya Ved T150083116
3. Mrinal Mohan T150083087

PROJECT GUIDE : Mrs. Manisha Rajput Ma’am

DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION

D.Y.PATIL COLLEGE OF ENGINEERING
AKURDI, PUNE – 411044
SAVITRIBAI PHULE PUNE UNIVERSITY

2020-2021
 D. Y. PATIL COLLEGE OF ENGINEERING
AKURDI, PUNE – 411044

Department of Electronics and Telecommunication

CERTIFICATE

This is to certify that Ujwal Murudi, Sanidhya Ved and Mrinal Mohan
– (Exam. Seat nos : T150083089, T150083116, T150083087 ) of T.E. Electronics
& Telecommunication Department have successfully completed Mini-
Project titled ‘Detection of food items with their Calorie and Nutrients
Data’ under my supervision and submitted the seminar report towards
partial fulfillment of requirement for third year Engineering course under
the Savitribai Phule Pune University during the academic year 2020-2021.

Mrs. Manisha Rajput Dr. Mrs. P. Malathi

Project Guide H.O.D. E&TC
 D. Y. PATIL COLLEGE OF ENGINEERING
AKURDI, PUNE – 411044

Department of Electronics and Telecommunication

CERTIFICATE
This is to certify that following students of T.E. Electronics &
Telecommunication department have successfully completed Mini-
Project titled ‘Detection of food items with their Calorie and Nutrients
Data’ under my supervision and submitted the seminar report towards
partial fulfillment of requirement for third year Engineering course under
the Savitribai Phule Pune University during the academic year 2020-2021.

Student name Exam. Seat No.

1. Ujwal Murudi T150083089
2. Sanidhya Ved T150083116
3. Mrinal Mohan T150083087

Mrs. Manisha Rajput Dr. Mrs. P. Malathi

Project Guide H.O.D. E&TC
 External Examiner

ACKNOWLEDGEMENT
We express our sincere gratitude towards the faculty members who makes this seminar a
successful.
We would like to express our thanks to our/my guide Mrs. Manisha Rajput for her
whole hearted co-operation and valuable suggestions, technical guidance throughout the seminar
work.
We would like to express our special thanks to our H.O.D. Dr. Mrs. P. Malathi for her
kind official support and encouragement.
Finally, we would like to thank to all our faculty & staff members of E&TC Department
who helped us directly or indirectly to complete this work successfully.

Name of the students

Ujwal Murudi
Sanidhya Ved
Mrinal Mohan
 Abstract :
Improper-nutrition intake can be fatal and result in unavoidable circumstances for
health. Standard intake of nutrition is fundamental for keeping the right balance of
nutrition in the human body. The project that we are executing allow users to estimate
the nutrition count of their food, enabled him to identify nutrition part of
a food item by the means of electronic technology. After some pre-processing steps, and
successful segmentation, many physical features are examined such as shape and size
etc. Also, dimensions of the food object are determined. The concluding step is then
recognition along with nutrition estimation. In this project, different nutrition estimation
techniques are reviewed. We contribute to building a system that provides aid to
monitor nutrition intake by estimating the nutrition based on food item recognition
and accurate volume calculation
Sr. No. Chapters Page No.

1. Introduction 1
1.1 Motivation
2
1.2 Objective

2. Literature Survey 3
2.1 (including Fig, references, links, etc)
4
2.2 Feasibility study
3. Proposed Methodology
3.1 Block diagram
5

4. Project Implementation 6
3.1 Design Steps
7
3.2 Circuit Diagram & working
3.3 Simulation
3.4 Selection of components 8

5. Results & Future work

3.5 Results (with tables & Figures)
9
3.6 Future scope
3.7 Conclusion
References 10
 List of figures
Sr no. Title Page no.

3.1.1 Block Diagram 5

3.1.1 Circuit Diagram 5
4.3.1 Working diagram 7
 INTRODUCTION

There has been an unprecedented rise worldwide in over weightiness and

obesity, as well as in diseases they cause . Thus, monitoring daily eating routines
in order to avoid excess nutrition intake has become an important issue in
maintaining a good quality of life. Studies have shown that several diseases are
linked to excessive or little nutrition intake in humans. Several institutions have
found that acute diseases are caused by improper nutrition intake. High calorie
intake was found to be only second to tobacco in directly causing cancer.
Moreover, a previous study found that a proper diet involving lower calorie intake
helped the people to increase their life expectancy and lower the risk of age-
associated diseases. High calorie values in food that is nutritionally poor led to
systemic inflammation and reduced insulin sensitivity, as well as a cluster of
metabolic abnormalities, including obesity, hypertension, and glucose intolerance.
Reducing the calorie intake lessened the risk of cancer in humans. To assist people
in tracking their nutition intake, efficient and convenient mobile applications have
been developed that alert users to the number of calories they consume. Such
mobile applications are becoming increasingly popular. Mobile applications have
the capacity to provide the easy collection of personal health-related data and
timely behavioral cues. Additionally, research has focused on the benefits of
mobile and Internet technologies in reaching diverse populations, such as rural
communities, in order to reduce health disparities and promote health
interventions.

8
 Motivation

Luckily, there is solutions that come in the form of food sensors. Whether they
are hand-held scanners, small patches or appliance-like devices, these new
sensors offer the option of scanning the food we buy, learning precisely what is
in them, monitoring them for spoilage, and essentially making healthier choices
about what we eat.
One such example is our project which aims to build upon that.

Objective

As been said earlier, a person must have the perfect balance between the
daily meal intake and the energy utilized. If the amount of meal intake is
higher than the energy utilization then it concluded that the person is becoming
obese. So, it reflects that the measurement of daily meal intake is quite
essential to lose weight as well as to preserve the healthy weight for
ordinary people. To accomplish this task, a mechanism is required that
empowers the patients with a long-term solution and also guide them to
achieve constant and lasting changes to their dietary quality and calorie
intake. The objective of this project paper is to discuss, implement and execute a
technology-driven technique.

9
 Literature Survey

In this section, we review significant food intake calculation and measurement

techniques. We will review techniques spanning from old manual dietary
assessment to modern image-based approaches.

Manual Approach

The manual methods require the user to manually record food details along
with the proportion sizes. The person under examination is inspected by a
dietitian or an expert for consumed food. Another approach uses a list of food
items. For each food item, the user enters the number of time that food has been
consumed in a given
time frame (e.g. one year). To calculate the nutrition value of the food
consumed, food portion sizes must be known. To avoid underreporting of
portion sizes, techniques have been designed to improve the portion size
estimation The general drawbacks of traditional manual approaches are
misreporting, data management and time consumption. Also, the user has to fill
in the forms and, in some methods, preserve the
data every day.

Automated Approaches

Automated systems electronic bar code reader with bar-coded food

identification catalogue. The system can be used for automated nutrition
evaluation The use of sensors was extended further in Automatic Dietary
Monitoring (ADM). This idea used a chewing sound sensor which comprised
of a wrist-worn acceleration sensor and a microphone in the external ear
canal to record chewing sounds. The sound chewing sensor
monitors the weight of consumed bites via recording chewing cycles using
described sensors and food types. This approach uses expensive equipment,
however, which limits its usability. The use of smartphones for indirectly
measuring the calorie expenditure was explored. A smartphone equipped
with a built-in accelerometer (3-axis) estimated the energy expenditure,

10
measured in metabolic equivalents (METs) by guessing the posture using
acceleration values of the mobile device. The calculated METs value differs or
different behaviour, e.g. sitting, standing, walking and running.

Feasibility study

The cost regarding computation and time is one of the critical aspects of any
project. If an project is not precise enough to lower the computation cost, then
another solution will outdate it shortly. The economic cost of a solution to a
problem also has an adverse effect. If we consider the traditional and
manual approaches, monetary cost is the most disturbing factor. Many
approaches involve the analysis of an expert dietician, who may charge a very
high amount. An automatic system utilizing smart devices may offer that
analysis free of cost

11
 Proposed Methodology

Block diagram :

12
 Project Implementation
Design Steps :

- Connect the A0 of Arduino UNO R3 and resistor with wire.

- Connect the Probe (metal rod) to another 'leg' of resistor.
- Connect the +5V and Probe.
- Place an insulator so that you can hold the probles.

Upload Program Code to Arduino Board

Different foods have different resistances. You can use Food Detector to detect
your favorite food by just put it into IF and ELSE loop.

So here is the breakdown for you:

 Check resistance range of different foods using Serial Output.

 Use those resistances to make create a range.
 Serial Output the food name.

Single and Mixed Food We have divided our food into two different groups:
single food and fruits such as apple, orange, and bread, and mixed food which
includes different food portions in a plate of food such as salad, pizza, and kebab
with rice

13
Circuit diagram

14
 Selection of components

 1 * Arduino UNO R3

 1 * 10kohm resistor

 1 * Mini Breadboard

 1 * LCD (16*2)

 1 * Arduino USB cable wires

 2 * Metal rods

15
 Results and Conclusions

Currently, obesity is the major issue in human life. Curiosity is found among
people to measure their heaviness and healthy eating in order to avoid obesity.
So, there is a need of a system which can measure calories of daily intake of
diet. The calorie measurement system can help nutritionist for physical and
medical treatment of overweight persons; ordinary people can also get the
benefit of this system by controlling their diet more closely without worrying
about being fat. This presents discussion at different calorie estimation
techniques. Every technique has negative and positive features as well. We also
throw light on the deficits of these methods.

Critical analysis of recent studies on accurate calorie estimation and food

item recognition is the primary objective of the paper being presented. Based
on this, we now conclude that food calorie measurement is a hot
currently. By all counts, and with comparative results, this study unveiled that
recent methods have scope for improvement, as this remains an open research
problem.

Also, the strengths and weaknesses of all the reviewed techniques are revealed.
It is clear from the presented review that the presented topic has the
potential to turn into a more beneficial and effective application by eradicating
the described deficits of these techniques. We have also described possible
improvements and future work to enhance the usability and accuracy of the
system.

Food detection and classification is a problem gaining much importance in

healthrelated applications. Since algorithms to accomplish this task are currently
being developed and refined, diverse and complementary datasets for evaluation
are not only helpful but also necessary to aid research. We placed careful
attention in generating the food images characteristics pertained to camera type,
shooting angle, and illumination variations. A strong feature is the good
distribution of single and mixed food images. Thus, it can be used to facilitate
testing and benchmarking of various food detection algorithms

16
 References

Research papers

https://link.springer.com/chapter/10.1007/978-3-319-23222-5_54

Website
https://www.researchgate.net/publication/331165679_Food_Item_Recognition_and_Intak
e_Measurement_Techniques

file:///C:/Users/User/Downloads/FoodRecognitionDataset-MadiMa.pdf

https://www.irjet.net/archives/V7/i12/IRJET-V7I12173.pdf

17