📊 InfoBuddy

Table of Contents📚

• 📝Overview
• ✨ Features
• 🚀 Prototype
• 💻 Technological Stack
• 🏗️ System Architecture
• 🔧 Installation
• 📈 Model Development
• ⚙️ Challenges and Solutions
• 🌟 Future Enhancements
• Project Admin⚡
• 🤝 Contributing
• 📄 License

📝 Overview

InfoBuddy is an innovative machine learning-based project that identifies key physical attributes—such as height, weight, voltage, wattage, width, volume, and depth—of objects from uploaded images. This project was created by Team Prime Predictors for the Unstop Amazon ML Challenge 2024. The solution features an interactive frontend that supports multilingual interaction (English, Spanish, French, Hindi) and offers both voice input and output capabilities for seamless user experience.

✨ Features

• 🔍 Attribute Detection: Detects height, weight, voltage, wattage, width, volume, and depth from uploaded images.
• 🌐 Multilingual Support: Interface supports English, Spanish, French, and Hindi.
• 🎙️ Voice Interaction: Includes voice input and output features using native JavaScript libraries.
• 🔊 Text-to-Speech (TTS): Read-along feature that reads out the responses for enhanced accessibility.
• 💬 Chat History: Keeps track of user interactions for easy reference.

🚀 Prototype

Recording.2024-10-04.102049.1.mp4

Recording.2024-10-04.103917.1.mp4

💻 Technological Stack

• Backend: Python, Jupyter Notebook, GEMINI API.
• Frontend: React, JavaScript, HTML, CSS.
• Automation and Testing: Selenium.
• Speech and Voice: Native JavaScript libraries for speech-to-text and text-to-speech.

🏗️ System Architecture

1. Backend: Python-based machine learning model built in Jupyter Notebook.

             - Utilizes the GEMINI API for data processing.
             - Integrated with Selenium for testing and automation.
   

2. Frontend: React-based application with interactive elements.

             - Offers chat-style interaction and dynamic response rendering.
             - Allows language switching and voice integration.
   

🔧 Installation

To set up the project locally, follow these steps:

1. Prerequisites

• Node.js
• Python 3.x
• Jupyter Notebook
• GEMINI API Access

Clone the Repository

git clone https://github.com/apu52/INFOBUDDY_ML_CHALLANGE_2k24.git  
cd InfoBuddy  

📈 Model Development

The machine learning model is built using Python and Jupyter Notebook. The following steps were followed for model development:

• 📊 Data Collection: Compiled a dataset of various objects to train the model for accurate attribute detection.
• 🤖 Model Training: Leveraged deep learning techniques to train the model for predicting height, weight, and other parameters.
• 🔍 Testing: Utilized Selenium for testing the model’s output against expected values.

⚙️ Challenges and Solutions

• 🔄 Data Processing: Ensured data consistency and variety during the model training phase to enhance accuracy.
• 🎙️ Voice Integration: Overcame voice recognition challenges by leveraging native JavaScript libraries and optimizing the voice flow.

🌟 Future Enhancements

• 📊 Expand the dataset for more accurate attribute detection.
• 🌐 Incorporate additional languages and improve voice command capabilities.
• 🔄 Optimize the real-time detection feature to handle more complex objects.

Team "Prime Predictors"⚡

Shreya Gupta

Surya R

Debasri Pal

Arpan Chowdhury

🤝 Contributing

Contributions are welcome! Please follow these steps to contribute:

• Fork the repository.
• Create a new branch for your feature or bug fix.
• Commit your changes and open a pull request.

Show some ❤️  by giving to this repository.

📄 License

This project is licensed under the Apache-2.0 license License. See the [LICENSE] file for details.