Publication Date

Spring 2017

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

T. Y. Lin

Second Advisor

Robert Chun

Third Advisor

Howard Ho

Keywords

path-finding algorithms, visually imparied

Abstract

The objective of this project is to propose and develop the path-finding methodology for the visually impaired patients. The proposed novel methodology is based on image-processing and it is targeted for the patients who are not completely blind. The major problem faced by visually impaired patients is to walk independently. It is mainly because these patients can not see obstacles in front of them due to the degradation in their eye sight. Degradation in the eye-sight is mainly because either the light doesn't focus on the retina properly or due to the malfunction of the photoreceptor cells on the retina, such as in Retinitis Pigmentosa.

Recently, Second Sight Medical introduced Argus retinal prosthesis, an electronic retinal implant which costs more than US$150,000. This solution is good, but it is very costly. Thus, there is a need of low-cost alternate path- finding methodology for visually impaired patients whose photoreceptor cells on the retina do not work properly.

In this project, the proposed approach is very different from the state-of-the- art. The proposed methodology is for patient’s whose vision is impaired such that the patient can not see obstacles, but they are not completely blind. In the proposed methodology, image in front of the patient is captured and processed in the real-time such that the final processed image facilitate patient to find the obstacles in front of them. In this novel proposed methodology, firstly, the edges in the captured images are detected, then, secondly, these edges are super-imposed on the original image and, finally, these edges are widened such that the processed image facilitates the visually impaired patients to recognize obstacles and to figure out the path for walking independently.

Share

COinS