Deep Learning for Image Caption Generation for the Visually Impaired

Vajpeyee, Amit (2023) Deep Learning for Image Caption Generation for the Visually Impaired. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Individuals with challenges related to vision have to deal with the pervasiveness of complete or partial unemployment amongst their peer group. World Health Organization (WHO) had estimated that people with headcount surpassing 2 billion are going through vision related impairments around the globe and approximately half of those are having moderate to serious visual problems. Scant studies have been attempted towards creation of employment for such people. Majority of them are restricted in scope and incorporate just a few aspects. This research has attempted to amalgamate the approaches of image-to-caption generation using the encoder (deep learning) – attention mechanism – decoder (natural language processing) architecture, caption-to-speech generation, and robotic process automation. This integrated ecosystem of diverse technical domains would allow the automatic download of the dataset, training and testing the architecture and then allow end user to use their voice to search keywords on Facebook.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Employment of People with Disabilities Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	27 May 2023 11:34
Last Modified:	27 May 2023 11:34
URI:	https://norma.ncirl.ie/id/eprint/6679

Actions (login required)

View Item