摘要
本文讨论在简单背景下,对飞机图像进行轮廓提取,以及在此基础上的多边形拟合技术。首先根据掏空内部点的准则和"探测准则",经过边界跟踪,得到只有一个像素宽度的飞机图像边界曲线。然后采用一种基于弦高度的多边形拟合算法,对得到的边界曲线进行拟合,从而得到了轮廓多边形。实验证明,该拟合算法去除了大量的冗余像素点,保留了重要的特征点,拟合效果令人满意,为进一步几何特征向量的提取奠定了基础。
This paper discussed how to take contour extraction for the airplane image with simple background, along with it, researched on polygon approximation technology. Firstly, according to the rule of drawing out interior point and detection, the contour curve with a pixel width can be gained after boundary tracking. Then taking approximation for contour curve by a polygon approximation algorithm based on chord height, the contour polygon can be derived. Being validated of experiment , this approximation algorithm wiped offabundant redundant pixel, retained important character point. The effect of approximation was satisfied, and established the basis to acquire the geometry characteristic vector.
出处
《长春理工大学学报(自然科学版)》
2009年第3期447-449,471,共4页
Journal of Changchun University of Science and Technology(Natural Science Edition)
关键词
目标识别
轮廓提取
多边形拟合
弦高度
target recognition
contour extraction
polygon approximation
chord height