欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对传统骨架提取算法中出现影响骨架识别的毛刺问题，特别是其中对物体形状的描述会产生很大影响的绷带骨架，在骨架的权值的基础上提出了一种新的骨架修剪算法。算法的核心是通过距离变换获取骨架权值并在骨架修剪过程中把表征骨架重要性的权值作为骨架分支是否被去除的依据。实验结果表明，作为目标骨架表示和识别的预处理手段，基于权值的骨架修剪算法能使骨架更能准确的反应目标物体的稳定结构。
英文摘要：
Aimed at the appearance of burr in the skeleton extraction algorithm, especially the ligature which have a significant impact on object shape descriptions, a skeleton pruning algorithm based on the skeleton weight is proposed. The core of the algorithm is that gain skeleton weight through the distance transform and whether the skeleton branches should be removed based on the importance of skeleton branches namely skeleton weight. The experimental results show that as a pretreatment method for skeleton target identification, a skeleton pruning algorithm based on weight could make the skeleton accurately express stable structure of object.
同期刊论文项目
同项目期刊论文
An improved approximation approach incorporating particle swarm optimization and a priori informatio
A new constrained learning algorithm for function approximation by encoding a priori information int
Modified constrained learning algorithms incorporating additional functional constraints into neural
期刊信息
位置：