Identification of different types of leucocytes in dried blood smears using neural networks

Author

Gulcur, Halil Ozcan ; Büyükaksoy, Güay

Author_Institution

Inst. of Biomed. Eng., Bogazici Univ., Istanbul, Turkey

fYear

1992

fDate

18-20 Aug 1992

Firstpage

203

Lastpage

206

Abstract

A new method based on artificial neural networks is developed for the identification of white blood corpuscle images. It uses a two-dimensional Self Organizing Feature Map (SOFM) and a single-layer perceptron. The SOFM algorithm imitates the ordering of sensory pathways and the high level of organization created during learning in the human brain. It is used to reduce the dimension of the input vector corresponding to the digitized image. This reduced dimensional `feature´ vector is applied to a single-layer perceptron

Keywords

blood; cellular biophysics; image recognition; medical expert systems; medical image processing; self-organising feature maps; dried blood smears; leucocyte types identification; neural networks; reduced dimension feature vector; single-layer perceptron; two-dimensional Self Organizing Feature Map; white blood corpuscle images; Artificial neural networks; Biological neural networks; Computer architecture; Intelligent networks; Neural networks; Noise level; Organizing; Pattern recognition; Pixel; White blood cells;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering Days, 1992., Proceedings of the 1992 International

Conference_Location

Istanbul

Print_ISBN

0-7803-0743-7

Type

conf

DOI

10.1109/IBED.1992.247113

Filename

247113