Name
Abstract | ||
|---|---|---|
White blood cell (WBC) detection is one of the most basic and key steps in the automatic WBC recognition system. Its accuracy and stability greatly affect the recognition accuracy of the whole system. This paper presents a novel method for WBC detection based on boundary support vectors (BSVs). Firstly, v-Support Vector Regression (v-SVR) is introduced. Then sparse BSVs are obtained while fitting the 1D histogram by v -SVR. Next so-needed threshold value is directly sifted from these limited support vectors. Finally the entire connective WBC regions are segmented from the original cell image. The proposed method successfully works for WBC detection, and effectively reduces the influence brought by illumination and staining. It also has the advantages, such as high computing efficiency and easy parameter setting. Experimental results demonstrate its good performances. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICSMC.2009.5346736 | SMC |
Keywords | Field | DocType |
recognition accuracy,sparse bsvs,boundary support vector,entire connective wbc region,object detection,cellular biophysics,novel method,original cell image,boundary support vectors,regression analysis,image segmentation,automatic wbc recognition system,detection method,image recognition,white blood cell detection,support vector machine,v-support vector regression,limited support vector,novel white blood cell,threshold value,id histogram,support vector machines,wbc detection,medical image processing,blood,support vector regression,fitting,histograms,support vector,microscopy | Histogram,Object detection,Cellular biophysics,Pattern recognition,Recognition system,Computer science,Support vector machine,Threshold limit value,Image segmentation,Artificial intelligence,Machine learning | Conference |
ISSN | ISBN | Citations |
1062-922X E-ISBN : 978-1-4244-2794-9 | 978-1-4244-2794-9 | 4 |
PageRank | References | Authors |
0.43 | 8 | 2 |