Image Caption Generator Using Deep Learning

Abstract

Abstract: Nowadays, an image caption generator has become the need of the hour, be it for social media enthusiasts or visually impaired people. It can be used as a plugin in currently trending social media platforms to recommend suitable captions for people to attach to their post or can be used by visually impaired people to understand the image content on the web thus eradicating any ambiguity in image meaning in turn also free of any discrepancy in knowledge acquisition. The proposed paper aims to generate a description of an image also called as image captioning, using CNN-LSTM architecture such that CNN layers will help in extraction of the input data and LSTM will extract relevant information throughout the processing of input such that the current word acts as an input for the prediction of the next word. The programming language used will be Python 3 and machine learning techniques. This paper will also elaborate on the functions and structure of the various Neural networks involved.