Urine crystal detection in a urinalysis process using the Harris and Stephens corner detection algorithm

Date of Publication

2012

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Engineering

Subject Categories

Computer Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics and Communications Engineering

Thesis Adviser

Ann E. Dulay

Defense Panel Member

Melvin K. Cabatuan

Bernardo F. So, Jr.

Abstract/Summary

In urinalysis, medical technologists have to spend most of their time looking through a microscope trying to identify and count the urine crystals in a sample manually. Their evaluation of the sample is then written in a medical report and sent to the doctor or handed to the patient. This process takes time and it is common for patients to come back several hours or the next day to get the result from the hospital. To address this issue, the previous research conducted by Lee, A. et. al proposed the automation of urine crystal detection in a urine sample. However, their study only included the detection of single crystals. The authors of this study develops a more robust detection system that will detect not only several single crystals in one urine sample image but overlapping crystal as well.

The system developed will incorporate the Harris and Stephens algorithm and the Slope Corner Detection algorithm made by the group to further improve the corner detection capability and reach an accuracy of 95%. The main programming language used is C++ while the graphical user interface makes use of Java.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU18093

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

240 leaves : illustrations (some colored) ; 28 cm.

Keywords

Urine--Examination; Urine--analysis.

This document is currently not available here.

Share

COinS