Professional Documents
Culture Documents
Project Report on
Submitted in partial fulfillment of the requirements for the award of the degree
of
Bachelor of Technology
in
by
ARPIT SINGH - 16
ARYAVEER – 17
AYUSH - 19
MISS. SHAMLI
CERTIFICATE
Introduction:
Nutriscan is an innovative mobile application designed to provide users with
accurate information about the safety of food items. By utilizing advanced
technology, Nutriscan empowers users to scan product ingredients, which are then
extracted and analyzed by a robust Machine Learning (ML) model running in the
backend. This ML model, built using Python and Flask, assesses the safety of the
scanned food items based on a pre-defined dataset. Users receive insights into
whether the food is safe for consumption and the degree of safety percentage.
Objective:
The primary objective of Nutriscan is to offer a convenient and reliable tool for
individuals seeking information about the safety of food items. It aims to assist
users in making informed dietary choices by providing accurate assessments of
scanned food ingredients.
Features:
• Ingredient Scanning: Users can easily scan the ingredients of food items using
their smartphone cameras.
• ML Model Assessment: An ML model built on Python evaluates the safety of
scanned ingredients.
• Safety Percentage: Nutriscan displays the percentage of safety associated with
the food item.
• Custom Dataset: The application uses a curated dataset containing specific
food items for analysis.
• User-Friendly Interface: An intuitive interface makes it simple for users to
obtain safety information quickly.
Features:
1. Ingredient Scanning:
Nutriscan simplifies the process of analyzing food items by allowing users to
effortlessly scan product ingredients using their smartphone cameras. The
application's image recognition technology swiftly extracts the listed ingredients
from packaging or labels, ensuring a seamless user experience.
2. ML Model Assessment:
The core of Nutriscan lies in its Machine Learning (ML) model, which operates in
the backend. This sophisticated model, developed using Python, employs
advanced algorithms to evaluate the safety of scanned food ingredients. It
compares the extracted ingredients against a meticulously curated dataset to
determine the potential risks associated with consumption.
3. Safety Percentage:
Upon analyzing the ingredients, Nutriscan provides users with a detailed safety
assessment. It presents the safety level as a percentage, offering users an
immediate understanding of the food item's safety quotient. This percentage scale
allows users to make quick and informed decisions about whether to consume the
product.
4. Custom Dataset:
The application relies on a customized dataset meticulously crafted by experts.
This dataset contains specific food items, their ingredients, and associated safety
levels. The utilization of this tailored dataset ensures accurate and reliable
assessments, enhancing the credibility of the analysis provided to users.
5. User-Friendly Interface:
Nutriscan boasts an intuitive and user-friendly interface, making it accessible to a
wide range of users. Its simple design enables individuals, irrespective of their
technological expertise, to interact with the app effortlessly. The interface
facilitates quick and easy scanning and provides comprehensible safety insights.
- Python:
Python serves as the primary programming language for the development of
Nutriscan's backend functionalities, including the creation of the ML model and
data processing.
- Flask:
The application leverages Flask, a powerful web framework in Python, to deploy
and manage the ML model in the backend. Flask facilitates seamless integration
and communication between the application's front end and the backend processes.
- Python Anywhere:
Python Anywhere, a cloud-based platform, is utilized for hosting the Flask
application. It ensures the application's availability and accessibility to users
across different devices.
- ML Toolkit:
Nutriscan utilizes ML Toolkit, a collection of machine learning algorithms and
tools, to implement and execute the ML model responsible for assessing the safety
of scanned food ingredients. This toolkit enhances the accuracy and efficiency of
the safety assessments performed by the application.
- CSV File:
The custom dataset, stored in a CSV (Comma-Separated Values) file format, acts
as the foundation for the ML model's analysis. This dataset is regularly updated
and maintained to ensure accuracy in food safety assessments.
Advantages:
1. Instantaneous Analysis:
Nutriscan provides real-time safety assessments, enabling users to promptly
determine the safety of scanned food items
This feature is especially beneficial for individuals with allergies or dietary
restrictions, allowing them to make immediate decisions.
2. Informed Decision-Making:
By offering detailed safety percentages, Nutriscan empowers users to make
informed dietary choices. It assists health-conscious individuals in selecting food
items aligned with their health goals and restrictions.
Disadvantages:
1. Dataset Limitations:
The accuracy of Nutriscan's assessments is contingent upon the
comprehensiveness and accuracy of the dataset used. It may not cover all potential
allergens or account for individual sensitivities.
2. Dependency on Technology:
The application's effectiveness relies heavily on technology. Any technical issues
or limitations in scanning accuracy might affect the precision of safety
assessments.
Application:
1. Food Allergies and Dietary Restrictions:
Nutriscan serves as an indispensable tool for individuals with food allergies or
specific dietary restrictions. For those with allergies to gluten, dairy, nuts, or other
common allergens, the app provides a lifeline by swiftly analyzing ingredients. It
empowers users to avoid potential allergens and make informed decisions about
food consumption, significantly reducing the risk of adverse allergic reactions.
Extracted Items
Result Page