一种基于相关向量机的白细胞检出新方法

White blood cell (WBC) detection is one of the most 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 new method for WBC detection based on Relevance Vector Machine (RVM). Firstly the astonishingly sparse Relevance Vectors (RVs) are obtained while fitting the 1D histogram by RVM. Next so-needed threshold value is directly sifted from these limited RVs. Finally the entire connective WBC regions are segmented from the original image. The proposed method successfully works for WBC detection, and effectively reduces the effects brought by illumination and staining. It also has the advantages, such as high computation efficiency and no extra parameter setting. Experimental results demonstrate its good performances.