White Blood Cell Classification based on the Combination of Eigen Cell and Parametric Feature Detection
Authors:
- 1 May 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
Numbers of white blood cells in different classes help doctors to diagnose patients. A technique for automating the differential count of white blood cell is presented. The proposed system takes an input, color image of stained peripheral blood smears. The process in general involves segmentation, feature extraction and classification. In this paper, features extracted from the segmented cell are motivated by the concept of the well-known eigen face which is performed on the pre-classified which blood cell based on parametric feature detection. The derived eigen value and eigen vector contributes to the important feature in the classification process. The results presented here are based on trials conducted with normal cells. For training the classifiers, a library set of 50 patterns is used. The tested data consists of 50 samples and produced correct classification rate close to 92 %Keywords
This publication has 10 references indexed in Scilit:
- Soft Learning Vector Quantization and Clustering Algorithms Based on Non-Euclidean Norms: Single-Norm AlgorithmsIEEE Transactions on Neural Networks, 2005
- Cell segmentation with median filter and mathematical morphology operation2003
- A fast segmentation scheme for white blood cell images2003
- A multi-resolution algorithm for cytological image segmentation2002
- Measuring shape: ellipticity, rectangularity, and triangularity2002
- Segmentation of blood images using morphological operators2002
- Automatic thresholding of infected blood images using granulometry and regional extrema2000
- Image compression by cellular neural networksIEEE Transactions on Circuits and Systems I: Regular Papers, 1998
- Local linear perceptrons for classificationIEEE Transactions on Neural Networks, 1996
- A Bayes classifier when the class distributions come from a common multivariate normal distributionIEEE Transactions on Reliability, 1992