Text and Content Based Image Retrieval

A image captioning based image retrieval model which can be used both via GUI and command line

Contents

• Introduction
• Features
• Demo Video
• Contributors
• Contribute
• Acknowledgement

Introduction

This is a python based image retrieval model which makes use of deep learning image caption generator. It uses a merge model comprising of Convolutional Neural Network (CNN) and a Long Short Term Memory Network (LSTM) . The dataset used here is Flickr8K dataset. You can request the dataset here.

Features

This model can be used both via GUI and command line. In both of these models image can be retrieved by-

• A description of image you want to retrieve
• An image whose semantically image you want to retrieve.

Note- The model performs well when text and images are semantically similar to the images in the dataset.

Video

Contributors

• Abhinav Dixit
• Ishaan Rajput
• Abhishek Sharma
• Harshita Rastogi
• John Prasad

Contribute

• Fork this repository and contribute.
• Feel free to report bugs.
• All types of feedbacks are welcome

Acknowledgement

• Thanks to Keras for providing us with the implementation of deep learning libraries.
• A special thanks to Machine Learning Mastery without which we couldn't have thought about the right approach to tackle this problem.