Skip to content

MamoonaRamzan/Visual-Narrator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Visual-Narrator

An elegant desktop application that uses deep learning to automatically generate descriptive captions for images.

Features

🖼️ Upload and preview images 🤖 AI-powered caption generation 📊 Simple and intuitive user interface 🔄 Real-time processing with progress indicators 📝 Detailed caption analysis


Usage

Run the application:

bash python main.py

Use the interface to:

Select an image using the "Select Image" button Generate a caption by clicking "Generate Description" View the generated description both below the image and in the detailed panel.


Working

The application utilizes a deep learning architecture with: Image Feature Extraction: A pre-trained CNN extracts visual features from the uploaded image Caption Generation: An LSTM-based decoder generates natural language descriptions based on the extracted features Text Processing: The generated text is processed to create grammatically correct and coherent captions


Preview

Screenshot 2025-04-27 234527

About

 Image Description Generator using CNN and LSTM trained on Flickr 8k Dataset

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published