Vision.X

Architecture

Demo Image

A mobile app designed to assist visually impaired individuals by leveraging object detection, text-to-speech conversion, and environmental interaction features. The app uses Flutter and Dart to create a user-friendly interface, making it easier for users to navigate and interact with their surroundings.

Key Features

• Object Detection: Utilize machine learning models to track and identify objects in the user's surroundings using the mobile camera.

• Text-to-Speech Conversion: Convert text information, such as object labels or environmental details, into spoken words to aid users in understanding their surroundings.

• Adaptive Interface: Design an adaptive and user-friendly interface with features like gesture controls, voice commands, and customizable settings to accommodate various user preferences.

• Accessibility: Ensure compatibility with screen readers and adherence to accessibility guidelines, making the app usable for individuals with visual impairments.

• Real-time Interaction: Enable real-time interaction with the camera feed, allowing users to receive instant feedback about objects and their environment.

Getting Started

These instructions will help you get a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

• Flutter
• Dart

Installation

1. Clone the repository:

   git clone https://github.com/Manu-N-S/ZILCKATHON-HFT-SerVIsta.git

2. Navigate to the project directory:

   cd ZILCKATHON-HFT-SerVIsta

3. Install dependencies:

   flutter pub get
   

4. Running the App

Now that you have the project and its dependencies installed, you can run the app on your local machine.

```bash
flutter run 

Vision.AI - Backend

Overview

Llava7B is a versatile multi-model AI designed for extracting features from both images and text inputs. This README provides a quick guide to the most important features for seamless integration into your project.

Key Features

1. Multi-Model Support:

   • Extract features from both image and text inputs, providing a unified solution for diverse data types.

2. Feature Extraction:

   • Identify patterns, structures, and relevant information in input data for valuable insights.

3. Easy Integration:

   • Simple API for seamless integration into existing projects, minimizing development effort.