Comparison of Performance on the Different Classifiers of the Locating Protected Projection (LPP) Dimension Reduction Method Based LBP Features

Image cells havetaken with Light Microscope help. The local binary pattern (LBP) features haveobtained for original images. High-dimensional of these LBP features is reducedto lower-dimensional with Locality Preserving Projections (LPP). These lowdimensional data are classified by the Random Forest...

Full description

Saved in:
Bibliographic Details
Main Author: Sevcan Aytaç Korkmaz
Format: Article
Language:English
Published: Sakarya University 2018-08-01
Series:Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi
Subjects:
Online Access:https://dergipark.org.tr/tr/download/article-file/394755
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image cells havetaken with Light Microscope help. The local binary pattern (LBP) features haveobtained for original images. High-dimensional of these LBP features is reducedto lower-dimensional with Locality Preserving Projections (LPP). These lowdimensional data are classified by the Random Forest (RF), Naive Bayes (NB),and Artificial Neural Networks (ANN) classifiers. The classification resultsare compared with previous studies. The performance achieved with the ANNclassifier is higher than the RF and NB classifiers. Moreover, feature vectorsize used in ANN classifier is a lower than feature vector size used in RF andNB classifiers. The success rates achieved with the ANN, RF, and NB classifiersis respectively 96.29%, 74.44%,and 70.00% according to LPP Method.
ISSN:2147-835X