International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 07 | July 2024
www.irjet.net
p-ISSN: 2395-0072
Analysis of Food Additives in Packaged Food Materials using AI and ML Roopa N K 1, Bi Bi Ameena2, Ayesha Siddiqua3 1Roopa N K, Assistant Professor, Dept of CSE, Sri Siddhartha Institute of Technology 2Bi Bi Ameena, Student, Sri Siddhartha Institute of Technology
3Ayesha Siddiqua, Student, Sri Siddhartha Institute of Technology
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - This paper presents a comprehensive framework
foods and provide personalized dietary recommendations based on user health metrics.
for the analysis of food additives in packaged food materials using AI and ML techniques. The developed software interface integrates CNN algorithms, OCR, and Google Cloud Vision API for efficient image processing and text extraction. Upon uploading an image containing labeled content of packaged materials, the software processes and analyzes the text to identify additives. A dedicated feature analyzes the health risks associated with identified additives. Additionally, the system includes a diet recommender website that predicts body fat and provides personalized dietary recommendations and exercise plans based on user data. This project leverages Python and Tkinter for application development, facilitating seamless integration and user-friendly interaction. The proposed framework enhances the understanding and management of food additives in consumer products, promoting informed dietary choices and healthier lifestyles. Key Words: AI, FOOD ADDITIVES ANALYSIS, MACHINE LEARNING, DIET PREDICTION, NUTRITION PLANNING
1.
Develop AI-driven algorithms to automatically identify and classify food additives from images of packaged food labels.
2.
Utilize machine learning models, particularly Convolutional Neural Networks (CNNs), to improve the accuracy and reliability of food additive detection and classification.
3.
Implement AI techniques to generate personalized dietary recommendations based on identified food additives and user health metrics.
4.
Design an intuitive graphical user interface (GUI) for seamless interaction, allowing users to upload food label images, view additive analysis results, and receive dietary advice.
5.
Evaluate the system's effectiveness in accurately identifying additives, usability of the interface, and user satisfaction through rigorous testing and feedback mechanisms.
1.INTRODUCTION Food additives are integral to modern packaged foods, influencing preservation and flavor. This paper employs AI and ML techniques to enhance the analysis of these additives. Using CNN, OCR, and Google Cloud Vision API, the system extracts and categorizes additives, aiding in informed dietary choices. A companion diet recommender website further tailors nutritional advice, contributing to consumer health awareness.
These objectives succinctly outline the primary goals of your project, focusing on leveraging AI and ML technologies to enhance food safety, consumer awareness, and dietary guidance through automated analysis of food additives in packaged foods.
The system is designed to be user-friendly, incorporating a software interface developed in Python and Tkinter.
1.
2. LITERATURE REVIEW
Users can upload images of food labels, process the text to identify additives, and receive detailed information about the potential health effects of these additives.
"Computer Vision and AI in Food Industry” Authors: Vijay Kakani et al.
This paper provides an extensive overview and critical analysis of the application of computer vision and artificial intelligence (AI) within the food industry. It explores various use cases where these technologies are employed, highlighting their transformative impact on food processing, quality control, and consumer safety. Reviews AI and computer vision in food industry, emphasizing productivity and regulatory challenges.
Additionally, the project includes a dietary recommendation feature that predicts body fat percentage based on user inputs such as age, height, hip size, density, and chest size. This feature not only suggests a balanced diet tailored to individual needs but also recommends appropriate exercises.
1.1 Objectives
2. "Deep Learning and Machine Vision for Food Processing" Authors: Lili Zhu et al.
The primary objective is to develop an AI-powered system to automate the identification of food additives in packaged
This survey paper presents a comprehensive examination of current research trends, methodologies, and advancements
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 127