A image captioning based image retrieval model which can be used both via GUI and command line
## Contents - [Introduction](#introduction) - [Features](#features) - [Demo Video](Video) - [Contributors](#contributors) - [Contribute](#contribute) - [Acknowledgement](#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](https://forms.illinois.edu/sec/1713398). ## 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 [](https://www.youtube.com/watch?v=WT5GZaArBpM&feature=youtu.be "Content and Text Based Image Retrieval") ## Contributors ## Contribute * Fork this repository and contribute. * Feel free to report bugs. * All types of feedbacks are welcome ## Acknowledgement * Thanks to [Keras](https://keras.io/) for providing us with the implementation of deep learning libraries. * A special thanks to [Machine Learning Mastery](https://machinelearningmastery.com/) without which we couldn't have thought about the right approach to tackle this problem.