NORMA eResearch @NCI Library

Deep learning approach for Image captioning in Hindi language

Rathi, Ankit (2019) Deep learning approach for Image captioning in Hindi language. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (3MB) | Preview

Abstract

Generating image description automatically from the content of an image is one of the fundamental problem in artificial intelligence. This task involves the knowledge of both computer vision and natural language processing, called \Image caption generation". Many research has been carried out in this field, but it was mainly focused on generating image descriptions in English, as existing image caption datasets are mostly in English. However, the image description generator model should not be limited by language. The lack of image captioning dataset other than English is a problem, especially for a morphologically rich language such as Hindi. Thus, this research constructed Hindi image description dataset based on images from Flickr8k dataset using Google cloud translator, which is called \Flickr8k-Hindi Datasets". The Flickr8k-Hindi Datasets consist of four datasets based on a number of description per image and clean or unclean descriptions. The study uses these Hindi datasets to train encoder-decoder neural network model. The experiments showed that training the model with a single clean description per image generates high-quality caption than a model trained with five uncleaned descriptions per image. Although model trained with five uncleaned descriptions per image achieved BLEU-1 score of 0.585, which is the current state of art.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
P Language and Literature > P Philology. Linguistics > Language Acquisition
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Caoimhe Ní Mhaicín
Date Deposited: 14 Oct 2019 11:18
Last Modified: 14 Oct 2019 11:18
URI: https://norma.ncirl.ie/id/eprint/3869

Actions (login required)

View Item View Item