基于边缘检测和骨架线跟踪的线状目标识别  

The Recognition of Linear Objects Based on Edge Detection and Skeleton Tracking

作　　者：刘芹[1] 田建英[1] 贾连芹[1] 

机构地区：[1]山东商业职业技术学院,山东济南250103

出　　处：《山东商业职业技术学院学报》2008年第4期93-96,共4页Journal of Shandong Institute of Commerce and Technology

摘　　要：线状目标的识别在很多方面具有重要应用,而目前常用的识别方法在准确性、抗干扰能力等方面有所欠缺。本文提出了一种综合利用边缘和骨架线这两个特征对线状目标进行识别的方法。方向小波变换不仅体现了多尺度特征,而且能很好地结合图像的方向及纹理特征,反映图像的边缘信息;基于优先搜索方向的骨架线跟踪方法可以减少搜索范围,降低问题复杂度。综合利用基于方向小波变换的边缘提取方法和基于优先搜索方向的骨架线跟踪方法,有效识别出线状目标,并通过纤维的识别证明了该方法的可靠性与精确性。The recognition of linear objects is applied to .many aspects, but most frequently used image recognition schemes need to be improved in terms of accuracy, immunity to noise and so on. This paper presents a method to recognize linear objects that synthesizes the edge and the skeleton of linear object. Extraction based on directional wavelet transform tracking based on direction priority for searching. Directional wavelet transform not only presents the multi - scale properties, but also can better reflect the edge information of images, because direction and texture information of the image can be better expressed; The skeletons tracking method based on direction priority for searching can decrease searching region and reduce the complexity. This paper presents a robust method to recognize linear object that synthesizes the edge extraction based on directional wavelet transform and the skeleton tracking based on direction priority for searching. T he recognition of fiber suggests that this method is robust and reliable

关 键 词：线状目标 方向小波 骨架线跟踪 识别 

分 类 号：TB879[一般工业技术—摄影技术]