Image Annotation Generation using Deep-Learning

Abstract

The paper tends to aim at creating automated captions by learning the contents of the image. Nowadays images are interpreted with human interference and it becomes a nearly unbearable task for enormous commercial records. The image records are given as input to a Convolutional Neural Network (CNN)) encoder for generating “thought vector” which extracts the features and enhances objects out of our image and RNN decoder (as a “Long Short-Term Memory”) is used to translate the features given by our image to obtain a sequential, meaningful description of the image. In this paper, we are going to explain the survey about image captioning and our proposed system.