https://github.com/nitish2773/vision-bot
The Vision Bot is an AI-powered application designed to analyze images captured from a webcam and dynamically answer user questions about the image. By leveraging the power of computer vision and natural language processing.
https://github.com/nitish2773/vision-bot
artificial-intelligence python3 tensorflow
Last synced: 4 months ago
JSON representation
The Vision Bot is an AI-powered application designed to analyze images captured from a webcam and dynamically answer user questions about the image. By leveraging the power of computer vision and natural language processing.
- Host: GitHub
- URL: https://github.com/nitish2773/vision-bot
- Owner: Nitish2773
- License: mit
- Created: 2024-12-24T10:56:10.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-12-31T14:27:09.000Z (6 months ago)
- Last Synced: 2025-01-12T15:17:57.932Z (5 months ago)
- Topics: artificial-intelligence, python3, tensorflow
- Language: Python
- Homepage:
- Size: 10.7 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: License
Awesome Lists containing this project
README
# Published At
https://app.readytensor.ai/publications/UUYpS17iTiK7
# Vision Bot: AI-Powered Visual Question Answering Tool
Vision Bot is an AI-powered tool that combines computer vision and natural language processing to dynamically answer questions about images captured from your webcam. It uses the BLIP model from Salesforce to perform visual question answering.
---
## Features
- Captures an image from the webcam.
- Answers questions about the captured image using AI.
- Combines computer vision (OpenCV) with natural language processing (transformers).
---
## Installation
1. Clone this repository:
```bash
git clone https://github.com/your_username/vision-bot.git
cd vision-bot
2. pip install opencv-python transformers requests pillow torch
---
## Usage
Run the script:
python vision_bot.py
Follow the prompts to:
- Capture an image using your webcam.
- Type a question about the captured image.
- Receive an AI-generated answer.
---
## Example
- Question: "What object is in the image?"
- Answer: "A red car."
---
## Requirements
- Python 3.8 or higher
- Webcam-enabled system
- Libraries: OpenCV, Transformers, Torch, Pillow
---
## Acknowledgments
- Salesforce BLIP Model
- Hugging Face Transformers