摘要
计算机显微图像尿沉渣分析仪,是运用图像处理技术和统计学习理论中支持向量机(SVM)技术,对尿沉渣的有形成分进行自动分类和识别,并从形态学方面对其进行了特征描述。在应用SVM分类方法的过程中,首先建立已知分类的图像,进而提取图像的特征,再对这些特征进行训练,同时交叉验证确定最优的SVM核函数和参数。最后根据训练过程建立的模型来对测试图像分类。结果表明,选用了支持向量机来实现沉渣识别,与传统的方法相比,取得了更高的识别率。
A kind of computer microscopic urine sediment analyzer is introduced. The system categorizes and recognizes the visible urine sediment components based on the technology of image processing and support vector machine (SVM). Moreover, sampled image feature is extracted, trained and classified. Using support vector machine method classifies and counts the urine sediment visible components and gets the number in the unit volume. The system not only realizes urine sediment visible components classifying and recognition, but also describes its feature from morphology. The SVM trains those features and crosses over their validation in order to get the optimal SVM kernel function and parameters. In the end, it classifies tested images according to the model. Experimental results show that SVM process to distinguish the urine sediment styles and the identify performance is better than tradition methods.
出处
《电子器件》
CAS
2006年第1期98-101,共4页
Chinese Journal of Electron Devices
关键词
尿沉
支持向量机
分类
核函数
urine sediment, SVM, classification
kernel function