Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/91711
Title: | White cane device : a mobile assistant for visually challenged people |
Authors: | Attard, Judie (2011) |
Keywords: | People with visual disabilities People with disabilities Cell phone systems Pattern recognition systems Mobile communication systems |
Issue Date: | 2011 |
Citation: | Attard, J. (2011). White cane device : a mobile assistant for visually challenged people (Bachelor's dissertation). |
Abstract: | A large percentage of the population is affected in various ways by visual impairments and most of the latter have no effective cure. Such visual impairments can significantly deteriorate the quality of life of people affected. The goal of this study is to exploit the portability and availability of mobile phones to provide a means of guidance to the visually impaired while travelling. The proposed system takes into consideration a visually impaired person while travelling through the city. The main challenge for such a person is to continously identify the correct location of his/her whereabouts. This system assists the user, through image recognition from a mobile phone, by guiding and offering information of the immediate vicinity. The 'White Cane Device' being proposed enables the user to capture a picture, and receives back information about the surroundings. This includes the object recognized within the query image, as well as the current location of the user ifs/he is some distance away from the object recognized within the image. The White Cane Device was implemented in a client-server architecture, where the client acts as a peripheral device, and the server implements the SIFT feature extraction algorithm to perform object recognition. The GPS coordinates of the images are used to optimize the latter process. This is done by reducing the search space. A thorough evaluation of the proposed system gave exciting results and showed that White Cane Device performs reliable matching even when images contain occlusion or are taken from various perspectives. The tested system returned results within more than acceptable time spans and received positive feedback from the usability evaluations held. |
Description: | B.SC.ICT(HONS)ARTIFICIAL INTELLIGENCE |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/91711 |
Appears in Collections: | Dissertations - FacICT - 2011 Dissertations - FacICTAI - 2002-2014 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
BSC(HONS)ICT_Attard Judie_ 2011.PDF | 18.83 MB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.