Visual Recognition Based System To Assist Blind Persons

Dongre, Ankit (2020) Visual Recognition Based System To Assist Blind Persons. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (7MB) | Preview

Abstract

Blind persons are devoid of vision, which plays an important role in day-to- day life. The lack of vision restricts the autonomity of a blind person to a level. Computer Vision and Machine Learning have seen rapid growth in recent years and have been used in the past for developing assistive systems. In this paper, a visual recognition based assistive system is proposed to compensate for the lack of vision. This project uses a pre-trained model obtained by training COCO dataset on MobileNet network. The YOLO algorithm has been used for object detection. Experiemental results shows the proposed system performs fairly well as compared to existing applications that are available in the Google Play store. The application can handle illumination changes and transformation with negligible performance degrade. This system has its own limitations which are discussed later in the conclusion section.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	23 Mar 2020 17:35
Last Modified:	23 Mar 2020 17:35
URI:	https://norma.ncirl.ie/id/eprint/4143

Actions (login required)

View Item