计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
20期
179-182
,共4页
轮胎花纹%特征提取%多级支持向量机(SVM)%分类
輪胎花紋%特徵提取%多級支持嚮量機(SVM)%分類
륜태화문%특정제취%다급지지향량궤(SVM)%분류
tire tread pattern%feature extraction%hierarchical Support Vector Machine(SVM)%classification
基于轮胎花纹分类识别在交通与刑事部门的重要作用，提出了一种新的基于组合特征提取与多级SVM的轮胎花纹识别方法。分别采用非下采样Contourlet变换和灰度共生矩阵方法提取轮胎花纹特征；组合两种方法所提取的特征作为图像特征，并从中提取5个有效特征作为最终识别特征；运用提取的5个特征和多级支持向量机分类器完成轮胎花纹的分类识别。新的特征提取方法所得轮胎花纹特征分离度高，用决策树SVM分类器预测分类效果理想，对轮胎花纹的正确分类识别有着重要意义。
基于輪胎花紋分類識彆在交通與刑事部門的重要作用，提齣瞭一種新的基于組閤特徵提取與多級SVM的輪胎花紋識彆方法。分彆採用非下採樣Contourlet變換和灰度共生矩陣方法提取輪胎花紋特徵；組閤兩種方法所提取的特徵作為圖像特徵，併從中提取5箇有效特徵作為最終識彆特徵；運用提取的5箇特徵和多級支持嚮量機分類器完成輪胎花紋的分類識彆。新的特徵提取方法所得輪胎花紋特徵分離度高，用決策樹SVM分類器預測分類效果理想，對輪胎花紋的正確分類識彆有著重要意義。
기우륜태화문분류식별재교통여형사부문적중요작용，제출료일충신적기우조합특정제취여다급SVM적륜태화문식별방법。분별채용비하채양Contourlet변환화회도공생구진방법제취륜태화문특정；조합량충방법소제취적특정작위도상특정，병종중제취5개유효특정작위최종식별특정；운용제취적5개특정화다급지지향량궤분류기완성륜태화문적분류식별。신적특정제취방법소득륜태화문특정분리도고，용결책수SVM분류기예측분류효과이상，대륜태화문적정학분류식별유착중요의의。
Based on the important role of tire tread pattern in road traffic and criminal department, a novel approach of tire tread pattern recognition based on composite feature extraction and hierarchical support vector machine is proposed. The features of tire tread pattern are extracted by nonsubsampled Contourlet transform method and grey level co-occurrence matrix method respectively. The features extracted from the two methods are composited as tire tread pattern features, and five effective fea-tures are selected from all the features as the final features. The classification and recognition of the tire tread pattern is completed by using hierarchical SVM classifier and the five extracted features. The features extracted by the new method have the higher degree of separation among clusters. In addition, the classifying quality of hierarchical SVM based on decision tree is feasible and effective, which is significant for the correct classification and recognition of tire tread pattern.
