计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2015年
5期
156-166
,共11页
图像分割%图像特征值算法%OpenCV%Canny边缘检测%Hough变换%Harris角点检测
圖像分割%圖像特徵值算法%OpenCV%Canny邊緣檢測%Hough變換%Harris角點檢測
도상분할%도상특정치산법%OpenCV%Canny변연검측%Hough변환%Harris각점검측
image segmentation%image feature extraction algorithm%OpenCV%Canny edge detector%Hough transform%Harris corner detector
在光照不均匀，存在阴影以及存在背景小杂色块干扰的图像中准确辨识出叶片图像，并将其显著特征抽取出来是叶片图像特征的研究重点。对实际叶片图像的处理，提出了先综合利用图像边界探测算法以及连接线、连通域抽取及变形算法确认叶边缘和叶脉图像，去除了光影，杂色轮廓的干扰，接着综合利用Hough变换、角点检测等算法来抽取树叶叶形，叶脉特征。实验中利用SVM（Support Vector Machine，支持向量机）算法对抽取特征进行分类测试，分类正确率超过了90%。
在光照不均勻，存在陰影以及存在揹景小雜色塊榦擾的圖像中準確辨識齣葉片圖像，併將其顯著特徵抽取齣來是葉片圖像特徵的研究重點。對實際葉片圖像的處理，提齣瞭先綜閤利用圖像邊界探測算法以及連接線、連通域抽取及變形算法確認葉邊緣和葉脈圖像，去除瞭光影，雜色輪廓的榦擾，接著綜閤利用Hough變換、角點檢測等算法來抽取樹葉葉形，葉脈特徵。實驗中利用SVM（Support Vector Machine，支持嚮量機）算法對抽取特徵進行分類測試，分類正確率超過瞭90%。
재광조불균균，존재음영이급존재배경소잡색괴간우적도상중준학변식출협편도상，병장기현저특정추취출래시협편도상특정적연구중점。대실제협편도상적처리，제출료선종합이용도상변계탐측산법이급련접선、련통역추취급변형산법학인협변연화협맥도상，거제료광영，잡색륜곽적간우，접착종합이용Hough변환、각점검측등산법래추취수협협형，협맥특정。실험중이용SVM（Support Vector Machine，지지향량궤）산법대추취특정진행분류측시，분류정학솔초과료90%。
Key point of processing leaf image is to extract distinguishable features of leaf from images containing both shadow and background noise interferences. To process the picture taken in real circumstance, a two-step method is pro-posed. It uses the combination of edge detection algorithm, connected lines and domains extraction method and shape modify algorithm to obtain the exact leaf edges and the leaf vein, eliminates the disturbance of shadow and background noise. It uses Hough line transform algorithm, Harris corner detector algorithm and other feature detecting algorithm to extract the features of leaf edge and leaf vein. When using the futures extracted to perform a SVM(Support Vector Machine)clas-sify algorithm, the result shows accurate is above 90%.
