提出了一种改进的基于分块迭代函数系统的分形维估计方法,对骨髓涂片中不同成熟阶段的粒细胞核表面的纹理进行了研究.该方法首先通过压缩仿射变换对细胞核灰度图象进行分块迭代函数系统构建,然后从该系统中提取出反映细胞核分形特征的匹配块因子、尺度系数等参数用于计算分形维.为了避免对细胞核表面分形维的过高估计,就匹配块因子、尺度系数的计算进行了改进.对60幅不同类型的粒细胞核表面图象进行比较实验,其结果表明该方法提取的分形参数可有效地反映不同细胞核表面间的纹理差异,它们可作为细胞识别中的新特征量.

An improved approach of estimating fractal dimension by partition iterated function system (PIFS) is proposed, which is used to analyze the different texture surfaces of bone marrow granulocytic cell nuclei in the different maturation stages. Based on contractive affine transformations, a PIFS for cell nucleus gray-level image is constructed, scale coefficients, domain factors and a scale factor are obtained from PIFS and used to calculate the fractal dimension. In this paper, the evolution of computational methods of domain factor and scale coefficient is used to overcome fractal dimensions overestimated. In order to testify the validity of the proposed method, there are 60 images of different types of cell nuclei to be applied to the experiment. The results show that fractal parameters obtained by our method are able to differentiate with the different types of cell nucleus texture surfaces efficiently, they can be used to the recognition of cells as new features.