Comparison of red blood cells counting using two algorithms: Connected component labeling and backprojection of artificial neural network

A. M.T. Nasution, E. K. Suryaningtyas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

Accurate determination of the number of red blood (RBCs) is important, which leads to correct diagnosis to the. In this paper a comparison of counting procedure using different algorithms is reported. They are the connected labeling, based on morphological processing, and the back-projection of artificial neural network. The comparison is on 23 images of blood samples taken from hematological system which is equipped with a Panasonic CCTV. Results are then benchmarked using a hematology Sysmex KX-21. Counting accuracies of 87,74 % and 86.97 % are obtained for the respective compared algorithms.

Original languageEnglish
Title of host publication2008 IEEE PhotonicsGlobal at Singapore, IPGC 2008
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE PhotonicsGlobal at Singapore, IPGC 2008 - Singapore, Singapore
Duration: 8 Dec 200811 Dec 2008

Publication series

Name2008 IEEE PhotonicsGlobal at Singapore, IPGC 2008

Conference

Conference2008 IEEE PhotonicsGlobal at Singapore, IPGC 2008
Country/TerritorySingapore
CitySingapore
Period8/12/0811/12/08

Fingerprint

Dive into the research topics of 'Comparison of red blood cells counting using two algorithms: Connected component labeling and backprojection of artificial neural network'. Together they form a unique fingerprint.

Cite this