Abstract:

In the past few years, the problem of generating descriptive sentences automatically for images has garnered a rising interest in natural language processing and computer vision research. An image caption is something that describes an image in the form of text. It is widely used in programs where one needs information from any image in automatic text format. Image captioning is a fundamental task which requires semantic understanding of images and the ability of generating description sentences with proper and correct structure. With the exponential development in the field of artificial intelligence in recent years, many researchers have focused their attention towards the topic of image caption generation. With advanced deep learning techniques, accessibility of big datasets and computer power one can build an efficient model to generate captions. Hence, in this work Deep Learning based Automated image Caption Generator is presented. The model is trained in such a way that if input image is given to model it generates captions which nearly describes the image. In this approach, two deep learning algorithms like LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks) are used. Feature extraction is done first and then captions are generated. The flickr_8k dataset is used for training the model. The dataset which we are using contains 8000 images and each image is mapped with five different captions.

Description:

Image Caption Generator, Convolutional Neural Network (CNN), Long Short Term Network (LSTM).