基于改进梯度向量流动态轮廓模型的图像检测  

Image Detection Based on Improved GVF Snake Model

作　　者：胡鹏博[1] 刘晓利[1] 白宏阳[2] 

机构地区：[1]南京理工大学瞬态物理国家重点实验室,江苏南京210094 [2]南京理工大学能源与动力工程学院,江苏南京210094

出　　处：《探测与控制学报》2013年第5期26-30,36,共6页Journal of Detection & Control

摘　　要：针对人造目标图像检测现有算法逐点扫描、计算分形维效率低的缺点,提出了基于分形理论和改进梯度向量流(GVF)动态轮廓(Snake)模型的算法。该算法应用微分计盒快速算法确定Snake初始轮廓,基于改进GVF模型确定目标真实轮廓。实验表明,该算法克服了其他分形算法逐点扫描效率低的缺陷,并较好地从自然背景中提取了目标图像的轮廓。For the shortcoming that general fractal algorithm scanning by points is of low efficiency, an algo- rithm was proposed based on fractal theory and improved GVF Snake model. The initial contour of the Snake model is identified through fast differential box-counting algorithm. The real contour of the target is determined on the basis of improved GVF model. Simulation showed that the proposed algorithm overcame the shortcoming that general fractal algorithm scanning by points at low efficiency. The contour of the target image was better extracted from natural background.

关 键 词：图像识别 目标检测 人造目标 分形 微分计盒算法 梯度向量流 动态轮廓模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]