Urine Sediment Recognition Method Based on SVM and AdaBoost

It is an important method to help doctor´s clinical diagnosis that using pattern recognition technology recognizes and counts Urine Sediment´s visible component. 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 bi-class SVM classifiers corresponding with different components are composed into a multi-class classifier. In order to improve algorithm´s speed, cascade accelerating algorithm is used. It is shown by experiment that the proposed method not only can effectively recognize different visible component of Urine sediment but also improve precision.