摘要
介绍了 CD4细胞的自动识别技术，利用图像处理技术实现了目标区域的分割，分析了形态、光密度、色彩、纹理四个方 面的特征；采用主成分分析法提取特征，构建了 BP 网络分类器，较好的实现了 CD4细胞的识别。
This paper introduces the technology of recognizing CD4 cell by a computer, which successfully segments the objects from the background through image processing and analyses the four features including geometric features, optical density, color and texture features. The method based on Principal Component Analysis algorithm is used for feature extraction, and a Back Propagation neural network classifier is constructed, from which the CD4 cell can be well recognized.
出处
《中国医疗器械杂志》
CAS
2005年第6期419-422,共4页
Chinese Journal of Medical Instrumentation
关键词
CD4细胞
图像分割
特征分析
主成分分析(PCA)
BP网络分类器
CD4 cell, image segmentation, feature analysis, Principal Component Analysis （PCA）, Back Propagation（BP） neural network classifier
