Automated Image Description Generation using ...

Automated Image Description Generation using Deep Learning Techniques

Author Name : Atharva Sachin Chaudhari, Fenil Ashokkumar Chodavadiya, Aman Malviya, Fahad Aasif Khan, Shamal Arun Hangirkar, Avasarala Lakshmi Vineesha, Pooja VR , Varun Reddy J

ABSTRACT Image captioning is a fusion of Natural Language Processing (NLP) and Computer Vision (CV) aimed at generating descriptive sentences for images. The process relies on an encoder-decoder architecture, where image features are extracted to form the encoder. In this project, multi-layered Convolutional Neural Networks (CNNs) are used to extract image features, while a Long Short Term Memory (LSTM) network, a type of Recurrent Neural Network (RNN), forms descriptive sentences based on these extracted features. The model is trained on the Flickr8k dataset, which provides five different descriptions for each image.