An improved support vector machine algorithm for blood cell segmentation from hyperspectral images

Blood cell analysis is becoming more and more attainable and worthy for blood diseases diagnosis. And blood cell segmentation is an important step for automated blood cells analysis based on image processing. This paper presented an improved support vector machine algorithm for blood cell segmentation for molecular hyperspectral images processing. This algorithm combined SVM with iterative self-organizing data analysis techniques algorithm to correct the miss-identified pixels by putting them into the minimum Euclidean distance cluster. Satisfactory performance can be seen from the experimental results that the proposed algorithm is superior to ISODATA and SVM algorithms in blood cell segmentation, because the new algorithm combines spatial and spectral information of blood cells.