CAJ | 학술논문

利用图像处理和模式识别技术进行复杂背景下黄瓜叶部病害的自动识别，需要先把目标叶片从复杂背景中分割出来，才能进行后续的特征提取和病害识别。为实现复杂背景下黄瓜叶片的分割，首先利用K-均值聚类算法去除图片中的非绿色部分，再采用基于laplacian of gaussia （ LOG）算子的方法对待分割的叶片进行区域检测，然后进行基于形状上下文（ shape context ）的模板匹配和分割。为了提高匹配速度，先检测叶片的生长点和叶尖，以确定叶片的位置、尺寸和方向；然后使用基于超像素（ superpixel ）的最优匹配搜索方法来减少搜索的复杂度。对20幅黄瓜叶部病害图像进行分割测试，并与人工分割法进行对比，结果表明，本文所采用的分割算法能较好地从复杂背景下提取出黄瓜叶部病害图像，分割准确率达94.7％，为后期黄瓜病斑的特征提取等工作奠定了良好的基础。
이용도상처리화모식식별기술진행복잡배경하황과협부병해적자동식별，수요선파목표협편종복잡배경중분할출래，재능진행후속적특정제취화병해식별。위실현복잡배경하황과협편적분할，수선이용K-균치취류산법거제도편중적비록색부분，재채용기우laplacian of gaussia （ LOG）산자적방법대대분할적협편진행구역검측，연후진행기우형상상하문（ shape context ）적모판필배화분할。위료제고필배속도，선검측협편적생장점화협첨，이학정협편적위치、척촌화방향；연후사용기우초상소（ superpixel ）적최우필배수색방법래감소수색적복잡도。대20폭황과협부병해도상진행분할측시，병여인공분할법진행대비，결과표명，본문소채용적분할산법능교호지종복잡배경하제취출황과협부병해도상，분할준학솔체94.7％，위후기황과병반적특정제취등공작전정료량호적기출。
In order to realize automatic identification of cucumber disease leaves in the complex background , target leaves should be segmented from the complex background first to facilitate the subsequent feature extraction and dis -ease recognition .For this purpose , K-means clustering algorithm was initially used to remove the non-green parts of the image, and then the approach based on LOG operator was proposed to select the candidate leaf areas .Finally, template matching was conducted based on shape context .During the matching process , the position, size and direc-tion of the leaves were firstly identified via the detection of the growing point and apex of leaves to improve the matc -hing efficiency , along with the search for the optimal matching based on superpixel to reduce the search complexity . To evaluate the feasibility of the proposed segmentation approach , 20 images of cucumber diseased leaves were seg-mented, and the result was compared with manual segmentation .It was shown that the proposed segmentation ap-proach could extract images with cucumber diseased leaves from the complex background , and the average segmenta-tion accuracy rate was 94.7%, which built a solid foundation for the subsequent feature extraction of cucumber le -sion.