【摘要】 分水岭变换是一种适用于图像分割的强有力的形态工具。然而，基于分水岭变换的图像分割方法的性能在很大程度上依赖于用来计算待分割图像梯度的算法。本文首先提出了一种计算图像形态梯度的多尺度算法，对阶跃边缘和“模糊”边缘进行了有效的处理：其次，提出了一种去除因噪声或量化误差造成的局部“谷底”的算法。实验结果表时，采用本文算法后进行分水岭变换，即使不进行区域合并也能产生有意义的分割，极大地减轻了计算负担。更多还原

【Abstract】 Watershed transformation is a powerful morphological tool for image segmentation. However, the performance of the image segmentation methods based on watershed transtormation depends largely on the algorithm for computing the gradient of the image to be segmented. In this paper we present a multiscale algorithm for computing morphological gradient images, with effective handling of both step and blurred edges. We also present an algorithm to eliminate the local minima produced by noise and quantiation error. Experimental results indicate that watershed transformation with the algorithms proposed in this paper produces meaningful segmentations, even without a region merging step. The proposed algorithm can significantly reduce the computational load of watershed-based image segmentation methods.更多还原