Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/39786
Title: Classification of pH levels using a mobile phone
Authors: Loh, Ivan Bao Yuan.
Keywords: DRNTU::Engineering::Computer science and engineering::Computer systems organization::Computer system implementation
Issue Date: 2010
Abstract: Camera phones are increasingly popular and are small yet powerful mobile devices capable of running diverse applications. We tap on the capabilities of camera phones to present a novel and automated system for classification of pH level of body’s fluid using non-calibrated camera phones. Our system also allows classification of any fluids using litmus paper and will automate the process of reading the pH value of the litmus paper. A simple process of capturing an image of a litmus paper test strip with colour reference charts, will allow the user to use our application to receive a pH classification value, particularly useful for the elderly and colour blind. The approach we devised, involves using edge detection techniques to determine the test strip and colour reference charts, followed by clustering techniques to segment the image and finally post clustering procedures to produce the pH classification value. We have also implemented the application in both J2SE and J2ME and our experiment results using different mobile camera phone devices with various image resolutions have proved to be consistent even when there are reflection and slanted placement of strips in the images. With widespread usage of camera phones, our solution is affordable and easy to operate and could be used anywhere, thus making medical solutions mobile.
URI: http://hdl.handle.net/10356/39786
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
SCE09-0042.pdf
  Restricted Access
2.96 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.