Skip to content

armaanaura/ImageCaptioning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Image Captioning Project

This project implements an image captioning system using deep learning techniques. It generates textual descriptions for input images using a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).

Introduction

Image captioning is a challenging task in computer vision and natural language processing, which involves generating descriptive captions for images automatically. This project utilizes pre-trained models such as VGG16 for feature extraction from images and LSTM networks for generating captions based on those features.

Features

  • Extracts image features using the VGG16 model
  • Preprocesses captions data and tokenizes text using the Keras Tokenizer
  • Implements a data generator to handle large datasets efficiently
  • Trains a captioning model using a combination of image features and textual data
  • Evaluates the model using BLEU scores for caption quality assessment
  • Utilizes the OpenAI API to refine generated captions for improved grammatical correctness

Requirements

  • Python 3.x
  • TensorFlow 2.x
  • Keras
  • NumPy
  • NLTK
  • OpenCV
  • tqdm
  • matplotlib

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages