显微图象的数字图象处理及其在血细胞形态分析中的应用

为了进行血细胞显微图象的快速分析,将显微图象的数字图象处理技术引入到血细胞形态分析中,在研究过程中,首先通过高倍电子显微镜及数字图象采集设备对血细胞图象进行采集;然后对血细胞的数字图象进行预处理,其中包括对比度增强、图象的高通滤波、图象的二值化、图象的腐蚀和膨胀、边缘跟踪等等;最后通过对血细胞的圆形度、矩形度和中心矩等等几何形态进行比较,提取出能够较明显地辨析出它们的特征向量,同时对分析结果的可信度进行了讨论。

Microscope Digital Image Processing and Its Application in the Modality Analysis of Blood Cell

This paper introduced the application of the microscope digital image processing in the modify analysis of blood cell. We deal with the blood cell by the method of digital image processing, and have also thought over the processing step of concerned pattern recognition, so that, we can use the computer voluntarily to judging and distinguishes for the microscope of cell. The viewpoint of artificial intelligence has still been thought over in this paper, for that, the computer have the character of learning, this makes that its recognition result possesses reliability. After we pro processed the digital image of blood cell, by comparing between the round degree, rectangle degree and center quadrature of the geometrical modality, we can get the eigenvectors of the different blood cell, we have discussed their reliability. We calculated the above geometry characteristic from the 56 examples cell samples (every sample includes three kinds of blood cells, and counts 168 images), and by standardization based the standard difference, we computed all values of characteristic weight, finally we got the characteristic vector of three kinds "classification", that are X 1,X 2 and X 3 . Using 2 norm X i-X 2 we created the distinguish function. By train computer to remember the cell characteristic of new kind of cell, we have pledged to differentiate correctly the known classification, and have pledged to distinguishing correctly the new classification.