期刊文献+

骨髓细胞分割与识别方法的研究

Studies on segmentation and recognition of marrow cells image
下载PDF
导出
摘要 针对骨髓细胞图像的特点,采用数学形态学的方法对图像进行了处理,获得了不同类型细胞核的准确的边缘。对于获得的边缘图像,采用两级神经网络,利用基于神经网络的PCA算法获得图像的3个主分量,然后采用模拟退火算法和BP算法进行细胞的分类识别,获得了较好的识别效果。 Aiming at the characteristics of the marrow cell image, morphology methods to process image was adopted to detect accurate edges of different kinds of cells. Three principal components could be acquired by adopting two neural networks and using principal component analysis (PCA) based neural network. And marrow cells could be classed and recognized by using simulated annealing (SA) and BP network.
出处 《计算机工程与设计》 CSCD 北大核心 2006年第2期259-261,共3页 Computer Engineering and Design
基金 内蒙古高等学校科学研究基金项目(NJ04109)
关键词 骨髓细胞 分割 数学形态学 主分量分析 模拟退火算法 BP网络 marrow cells segmentation morphology PCA SA BPnetwork
  • 相关文献

参考文献7

  • 1Chengyang Xu, Jerry Prince. Snake shapes and gradient vector flow[J].IEEE Transactions on Image Processing, 1998,7(3): 359-369.
  • 2Velasco, Horacio Manuel Gonzalez. Segmentation of bovine livestock images using GA and ASM in a two-step approach[J].International Journal of Pattern Recognition and Artificial Intelligence, 2003,17(4):601-616.
  • 3Rajapakse J C, Giedd J N. Statistical approach to segmentation of single-channel cerebral MR image[J], IEEE Trans on Medical Imaging, 1997,16(2): 176-186.
  • 4Vannier M W, Hailer J W. Biomedical image segmentation[C].Proc of International Conference on Image Processing, 1998.20-24.
  • 5Bosworth J, Acton S T. The morphological lomo filter for multiscale image processing[C]. 1EEE International Conference on Image Processing,Japan, 1999.22-28.
  • 6裴鑫德.多元统计分析及其应用[M].北京:北京农业大学出版社,1990..
  • 7Sanger T D. Optimal unsupervised learning in single-layer feed forward neural network[J].Neural Networks, 1989,(2):459-473.

共引文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部