Multi-Urine Sediment Component Recognition Method
Urine Sediment Component auto recognition system has important application to help doctors clinical diagnosis by digital image processing technology. Because Harr wavelet feature has good property of distinguish different components, the proposed method using AdaBoost to select a little part typical Harr feature which are taken as input data of SVM. The trained several hi-class SVM classifiers corresponding with different components are composed into a muti-class classifier. Moreover, in order to improve system speed, cascade accelerating algorithm is used. It is shown by experiment that the proposed method can not only effectively recognize different visible component of Urine sediment hut also improve precision compared with other methods.
Urine Sediment recognition SVM AdaBoost Multi-classification
Mei-li SHEN
Qingdao Technological University, School of Science, Qingdao, China
国际会议
2009 International Workshop on Information Security and Application(2009 信息安全与应用国际研讨会)
青岛
英文
492-495
2009-11-21（万方平台首次上网日期，不代表论文的发表时间）