自适应气球力主动轮廓的图像分割

集成图像的先验信息到模型中是改善主动轮廓模型分割复杂背景图像性能的一种重要方法．采用统计方法确定目标区域，根据区域自适应地决定主动轮廓模型气球力的方向，对测地线主动轮廓模型进行改进．结果表明：主动轮廓曲线的收敛仅依赖图像梯度这一局部性质的情形被改变，主动轮廓曲线的收缩或扩张和目标区域联系起来．图像分割实验说明改进的模型能较好地对带噪声且为弱边缘的人工合成图像、医学超声图像得到理想的目标边缘轮廓．自适应气球力主动轮廓分割图像能提高在图像弱边缘处的定位能力和精确度，减少对噪声的敏感性，加快曲线收敛到目标边界的速度．

Images Segmentation Using an Adaptive Balloon Force Active Contour

It was an important method that prior information was integrated active contour for improving the performance of image segmentation in complex context. A target region was extracted in image by statistical method. The adaptive balloon forces relating to the target region information was introduced for improving the geodesic active contour model. The result shows that the convergence of active contourl curve is not only depended on the image gradient, but also the target region. A better boundary contour is achieved by processing the objects with weak edges and medical data imagery. The model provides an accurate segmentation to weak edges and noise image and speed up the curve convergence to target region boundary.