期刊名称：Journal of Theoretical and Applied Computer Science
印刷版ISSN：2299-2634
电子版ISSN：2300-5653
出版年度：2013
卷号：7
期号：1
页码：20-35
出版社：Polska Akademia Nauk * Oddzial w Gdansku, Komisja Informatyki,Polish Academy of Sciences, Gdansk Branch, Computer Science Commission
摘要：The complete blood count (CBC) is widely used test for counting and categorizing various peripheral particles in the blood. The main goal of the paper is to count and classify white blood cells (leukocytes) in microscopic images into five major categories using features such as shape, intensity and texture features. The first critical step of counting and classification procedure involves segmentation of individual cells in cytological images of thin blood smears. The quality of segmentation has significant impact on the cell type identification, but poor quality, noise, and/or low resolution images make segmentation less reliable. We analyze the performance of our system for three different sets of features and we determine that the best performance is achieved by wavelet features using the Dual-Tree Complex Wavelet Transform (DT-CWT) which is based on multi-resolution characteristics of the image. These features are combined with the Support Vector Machine (SVM) which classifies white blood cells into their five primary types. This approach was validated with experiments conducted on digital normal blood smear images with low resolution.
关键词：Complete Blood Count (CBC); White Blood Cell Classification; Dual-Tree Complex Wavelet Transform (DT-CWT); Shape; intensity and texture features; Kernel-PCA; Support Vector Machine (SVM)
