摘要
数字图像中目标对象的周长是一个十分重要的目标形态特征,二维图像中的目标周长估算在图像特征提取、目标识别等方面具有十分重要的作用。目前已有的估算方法对二维灰度图像目标边界模糊和图像含噪声估算精确度不高,针对这一现状,结合图像森林变换(IFT),提出基于IFT的改进的目标周长估算方法。利用IFT方法优化图像目标厚度边界信息来估算灰度图像的边界周长,从而提高周长估计的精确性和鲁棒性。为了获得图像目标的标准周长,实验采用人工合成的图像。对具有不同边界厚度的目标、含噪的图像的目标进行周长估算实验。提出的改进算法在图像目标边界模糊和含噪声情况下所得的结果均具有较高的精确度。提出的改进的灰度周长估算方法,在模糊图像与含噪图像的处理中具有更好的适应性和稳定性。
The perimeter of a target boundary in a 2D image is an essential object feature in image analysis. It plays an important role in image feature extraction and target recognition. However,this feature is usually inaccurately estimated owing to blurred target boundaries and noise. Many reported methods do not play well in these situations.Accordingly,this study proposes an improved method for perimeter estimation based on the image foresting transform( IFT). The proposed method utilized IFT to estimate the target perimeters for different boundary thicknesses and noise. The improved algorithm proposed in this paper has higher precision for the image targets having blurred boundary and noise. The experimental results demonstrate that our improved method provides better adaptability and stability while calculating the perimeter of targets having blurred boundary and noise.
出处
《智能系统学报》
CSCD
北大核心
2017年第3期341-347,共7页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金项目(61170121)
关键词
特征提取
周长估计
IFT
模糊边界
含噪图像
灰度边界
边界厚度
feature extraction
perimeter estimation
the image foresting transform
blur image
noise image
gray boundary
boundary thickness