基于支持度变换的几何活动轮廓模型轮廓提取方法

Geometric active contour method based on support value transform for contour extraction

提出了一种新的轮廓提取方法,该方法将几何活动轮廓模型与映射最小二乘向量机(mapped LS-SVM)相结合。首先用映射最小二乘向量机推导出支持度滤波器,通过在基本支持度滤波器中填充零的方法得到一系列的多尺度支持度滤波器。然后通过支持度变换(SVT)计算出支持度图像。在此基础上,用支持度图像计算几何活动轮廓模型的边缘指示函数,使得曲线演化快速地收敛到期望位置。实验结果表明该方法的轮廓提取效果较好,收敛速度更快。

A novel contour extraction method was proposed, which combined geometric active contours and the mapped least squares support vector machine （ mapped LS-SVM）. It used the mapped IS-SVM to deduce the support value filter. With the basic support value filter, a series of multi-scale support value filters were obtained by filling zeros in it. The support value image was obtained by using support value transform. Then the geometric active contours method used the support value image to compute the edge indicator and was implemented on the feature image, the evolving curve stoped when it arrived to the object boundaries. The experimental results demonstrate that the proposed method has advantages over the direct geometric active contours in converging speed and contour extraction accuracy.