电子测试
電子測試
전자측시
ELECTRONIC TEST
2013年
11期
61-63,72
,共4页
线段聚类%结构特征%距离%方向%合并分离
線段聚類%結構特徵%距離%方嚮%閤併分離
선단취류%결구특정%거리%방향%합병분리
line segment clustering%structure feature%distance%direction%merging or splitting
针对图像处理获得杂乱边缘线条信息,本文提出了一种新的三步快速线段聚类算法。该算法首先利用线条检测算法对原始图像进行线条检测获得初始线条集合,然后根据这些线段的方向进行粗分类,在此基础上对构成的每个集合内部根据距离差异再进行细分,把距离较远的线段进一步聚类到不同的集合中,最后根据线段之间的邻近关系进行合并和分离,形成最终线段聚类效果。通过试验,与前人工作相比,本文算法效率更高,而且容易实现,所形成的线段聚类能充分反映出目标的结构信息。
針對圖像處理穫得雜亂邊緣線條信息,本文提齣瞭一種新的三步快速線段聚類算法。該算法首先利用線條檢測算法對原始圖像進行線條檢測穫得初始線條集閤,然後根據這些線段的方嚮進行粗分類,在此基礎上對構成的每箇集閤內部根據距離差異再進行細分,把距離較遠的線段進一步聚類到不同的集閤中,最後根據線段之間的鄰近關繫進行閤併和分離,形成最終線段聚類效果。通過試驗,與前人工作相比,本文算法效率更高,而且容易實現,所形成的線段聚類能充分反映齣目標的結構信息。
침대도상처리획득잡란변연선조신식,본문제출료일충신적삼보쾌속선단취류산법。해산법수선이용선조검측산법대원시도상진행선조검측획득초시선조집합,연후근거저사선단적방향진행조분류,재차기출상대구성적매개집합내부근거거리차이재진행세분,파거리교원적선단진일보취류도불동적집합중,최후근거선단지간적린근관계진행합병화분리,형성최종선단취류효과。통과시험,여전인공작상비,본문산법효솔경고,이차용역실현,소형성적선단취류능충분반영출목표적결구신식。
For mess lines detected from image processing,this paper presents a new fast line segment clustering algorithm.Firstly we use line segment detector to generate the initial line set from the input original image,then group these lines into different sets according to their directions roughly.Based on these direction sets,each set is further subdivided into different sub-sets according to their relative distances,and then the lines are merged or split on the basis of their neighborhood relations to form the final grouping effects.Compared to previous work,our method is more efficient and easier to be implemented, and the clustered line segments can fully indicate the structure information of targets in the image,which is verified by the experiments.