计算机工程

• 图形图像处理 • 上一篇    下一篇

一种基于核函数的彩色血细胞识别方法

杨绍华1,潘 晨2,魏立力1   

  1. (1. 宁夏大学数学计算机学院,银川 750021;2. 中国计量学院信息工程学院,杭州 310018)
  • 收稿日期:2013-05-24 出版日期:2014-06-15 发布日期:2014-06-13
  • 作者简介:杨绍华(1978-),男,讲师、硕士,主研方向:图形图像处理,多媒体技术;潘 晨、魏立力,教授、博士。
  • 基金项目:
    国家自然科学基金资助项目(11261044, 61362029);宁夏高等学校科学研究基金资助项目(2012)。

A Method of Colorful Blood Cell Recognition Based on Kernel Function

YANG Shao-hua 1, PAN Chen 2, WEI Li-li 1   

  1. (1. School of Mathematics and Computer Science, Ningxia University, Yinchuan 750021, China; 2. College of Information Engineering, China Jiliang University, Hangzhou 310018, China)
  • Received:2013-05-24 Online:2014-06-15 Published:2014-06-13

摘要: 为有效提高血细胞识别的性能,提出一种基于核函数的彩色血细胞识别方法。利用血细胞图像的颜色直方图和局部密度直方图对血细胞图像进行归一化表示。将核主成分分析用于非线性特征和数据降维提取,采用支持向量机(SVM)对特征进行加权,SVM和最近邻构成多分类器进行分类。整个系统构成一个支持向量网络,为自动进行网络训练和参数寻优,给出一套自动相关的反馈训练方法。在相关血细胞数据库上的实验结果表明了该方法的有效性。

关键词: 核函数, 血细胞识别, 归一化, 核主成分分析, 支持向量机

Abstract: In order to improve the performance of blood cell images recognition, a method of colorful blood cell images recognition based on kernel function is proposed. The blood cell image is normalized by colorful histograms and local histograms. Kernel Principal Component Analysis(KPCA) is used to extract the nonlinear features and reduce the high dimensionality of data representation. The features are weighted by Support Vector Machine(SVM). The classifier of multiclass is composed by SVM and Nearest Neighbor(NN). The total system is a support vector network for classification task actually. In order to train this network automatically, relevance feedback is utilized for adjusting parameters. The validity of method above is proved by results based on database of colorful blood images.

Key words: kernel function, blood cell recognition, normalization, Kernel Principal Component Analysis(KPCA), Support Vector Machine(SVM)

中图分类号: