Improving Anemic RBCs Images Recognition: Improving Anemic RBCs Recognition Using Spatial Spectral Statistical Features and Transformative Features With RBFNN - Couverture souple

Ali Alkrimi, Jameela; Ahmad, Abdul Rahim; E. George, Loay

 
9783659974311: Improving Anemic RBCs Images Recognition: Improving Anemic RBCs Recognition Using Spatial Spectral Statistical Features and Transformative Features With RBFNN
Couverture souple
ISBN 10 : 3659974315 ISBN 13 : 9783659974311
Editeur : LAP LAMBERT Academic Publishing, 2017

Synopsis

In this research a new anemic red blood cells (RBCs) data set was collected and used to investigate the automatic recognition of the RBCs. It includes the required processes to extract Spatio- Statistical Spectral features of the RBCs and to utilize these features to recognize between normal RBCs and the other seven groups of abnormal RBCs from five most dominant types of anemic RBCs in Malaysia. Three sets of features were used and tested: geometrical,colo and textural. The suggested RBCs recognition scheme consists of four stages after data acquisition. The first one is to determine the background and target colors, isolating the cell target area from the surrounding and tracing the external and internal boundaries of central pallor area pixels of the cell cut-out. Second is to determine the adopted geometrical features by using the trace points, such as: Fourier descriptors, aspect ratio and moments, which have been used to describe the shapes of RBCs. Some textural features were also computed to evaluate the spatial color variation within the RBCs. PCA technique was applied in order to remove redundant features that affected the classification accuracy and training time.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

In this research a new anemic red blood cells (RBCs) data set was collected and used to investigate the automatic recognition of the RBCs. It includes the required processes to extract Spatio- Statistical Spectral features of the RBCs and to utilize these features to recognize between normal RBCs and the other seven groups of abnormal RBCs from five most dominant types of anemic RBCs in Malaysia. Three sets of features were used and tested: geometrical,colo and textural. The suggested RBCs recognition scheme consists of four stages after data acquisition. The first one is to determine the background and target colors, isolating the cell target area from the surrounding and tracing the external and internal boundaries of central pallor area pixels of the cell cut-out. Second is to determine the adopted geometrical features by using the trace points, such as: Fourier descriptors, aspect ratio and moments, which have been used to describe the shapes of RBCs. Some textural features were also computed to evaluate the spatial color variation within the RBCs. PCA technique was applied in order to remove redundant features that affected the classification accuracy and training time.

Biographie de l'auteur

Dr. Jameela Ali Alkrimi Lecturer in IT and communication at College of Dentistry, Babylon Univ., Babylon, Iraq. Doctorate in IT & Communication, UNITEN, 2015. M.Sc IT. Univ. of IT & Communications, 2006. Diploma in IT. Univ. of IT & Communications, 2000. B.Sc (Statistics Science) college of Administration & Economic, Baghdad Univ.,1987.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
LAP LAMBERT Academic Publishing
Date d'édition
2017
Langue
anglais
ISBN 10 
3659974315
ISBN 13 
9783659974311
Reliure
Broché
Nombre de pages
268
Coordonnées du fabricant
non disponible
Personne responsable
KreGa Onlinehandel GmbH
4950000000000
info@krega-onlinehandel.de

Birkenweg 31
Brakel
33034
Allemagne