利用SVM进行车型识别  

Car model recognition based on SVM method

作　　者：王亮申[1] 朱玉才[1] 陈少华[1] 侯杰[1] 于京诺[1] 苏子林[1] 欧宗瑛[2] 

机构地区：[1]烟台师范学院,山东烟台264025 [2]大连理工大学,辽宁大连116023

出　　处：《计算机工程与设计》2005年第9期2453-2454,共2页Computer Engineering and Design

摘　　要：为了提高车辆图像的识别率,提出了利用支持向量机(SVM)理论进行轿车车型识别方法。SVM能够解决线性及非线性分类问题,以较少的支持向量确定分类面,对样本数量及维数不敏感。基于颜色直方图及惯性比确定的图像特征具有平移、旋转和尺度不变性,可以用来确定SVM的最优分类面,并由此识别车型。In order to increase recognized rate, a method for recognition of car model based on SVM isintroduced. Linear and nonlinear classifications could be solved with SVM, and the hyperplane could be defined by a few support vectors. SVM was insensitive to dimensions and numbers of training set. The features based on color histogram and ratio of inertial moment could keep their scale-invariance, rotation-invariance and translation-invariance, and got optimal hyperplane and recognize car model.

关 键 词：图像 识别 特征 SVM 车型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]