优化的离散λ-中轴骨架提取算法

Skeleton Extracting Algorithm via Optimized Discrete λ-Medial Axis

离散λ-中轴(DLMA)是一种快速、健壮的中轴变换算法,选择合适的参数λ可以提取物体较为精准的单像素骨架.针对DLMA算法的缺点,提出一种融合欧氏距离变换局部极大值点思想和背景点空间思想的DLMA优化算法.该算法将DLMA算法分成2步,先使用一个小λ阈值获得骨架的粗提取结果,计算过程中将其N4邻域简化为N2邻域;然后在粗提取的结果下设计骨架生长阈值自动调整策略,使其对宽度变化具有足够的适应性.实验结果表明,与原DLMA算法相比,文中提出的优化算法不仅具有更快的计算速度,鲁棒性和自适应能力均有显著提高.

The discreteλ-medial axis(DLMA)is a fast and robust medial axis transformation.It can be appliedin extracting single-pixel accurate skeletons.But an appropriate parameterλis needed to set in advance.Meanwhile,it relies on the single threshold filters.Thus,it is hard to select the highly adaptive parameterλ,when the shapes have complex topology.We propose a method combining the local maxima of Euclideandistance transform and the idea of background space.The proposed algorithm divides the DLMA algorithminto two steps.Firstly,a smallλthreshold is used to obtain the rough skeleton and the N4neighborhood isreduced to N2neighborhood.Secondly,a strategy with the automatic adjustment of threshold is designed toensure that the skeleton growth is well adaptable to the change of the width of the shape.The experimentalresults showed that the proposed optimized algorithm is more adaptable,faster and more robust.