本論文提出一白血球細胞核切割及分類的方法。通常白血球是以人工透過顯微鏡進行分類。然而,這對醫生或是檢驗人員是個負擔極大的工作,因此,一套自動的白血球切割及分類的系統可以有效減少醫檢人員的負擔。本文中,主要利用白血球細胞核進行切割及分類,因此,文中提出了一個增強細胞核區域顏色強度的方法。在辨識的步驟中,我們利用細胞的紋理特徵,並利用主成分分析 (principle component analysis,PCA) 方法有效地降低特徵的維度。並結合基因演算法及 K-means 分類白血球。即使只使用白血球的細胞核作為分類的依據,實驗結果證實我們仍能得到有效的分類結果。
In this paper, a leukocyte segmentation and recognition method is proposed for leukocyte differential counting. In
general, leukocytes are usually manually classified in laboratories by using microscopes. It is a painstaking and
subjective task for biologists. An automatic method is essential to reduce the overhead for biologists. The nuclei are
used to identify fi ve types of leukocyte in this paper. The leukocyte cell nucleus enhancer is proposed to segment
the region we are interested in by enhancing the region of the leukocyte nucleus and suppressing the other region
of the blood smear images. In the recognition steps, we reduce features by principle component analysis (PCA) to
obtain suitable features. The genetic algorithm based K-means clustering approach is used to classify the fi ve kinds
of leukocyte in the reduced dimensions. The experimental results show that even though only leukocyte nucleus
features are used for classifi cation in our method, we achieve a high and promised accurate recognition rate.