SUPERVISED CLASSIFICATION OF WHITE BLOOD CELLS BY FUSION OF COLOR TEXTURE FEATURES AND NEURAL NETWORK

摘要

Nucleus segmentation is one of important steps in the automatic white blood cellndifferential counting. In this paper, we proposed a technique to segment images of thennucleus. We analyze a set of white-blood-cell-nucleus-based features using color fuzzyntexture spectrum (Base 5). We applied artificial neural network for classification. Wencompared the results with moment based features. The classification performances arenevaluated by class wise classification rates. The results show that the features usingnnucleus alone could be utilized to achieve a classification rate of 99.05% on the test sets