基于非下采样Contourlet变换和分水岭算法的图像分割方法

Image Segmentation Based on the Nonsubsampled Contourlet Transform and Watershed Algorithm

图像分割技术在数字图像处理中占有非常重要的地位。提出基于非下采样Contourlet变换的图像分割方法,有效地将非下采样Contourlet变换与数学形态学中的分水岭算法结合起来,既减少了分水岭变换的过分割现象,又有效地保持了图像中的边缘信息。实验结果表明,此方法是可行的,并能得到良好的分割效果。

Image segmentation plays a very important role in digital image processing. A novel image segmentation method based on the nonsubsampled contourlet transform is proposed, which efficiently combines the nonsubsampied contourlet transform and watershed algorithm in mathematical morphology. This method does not only avoid the oversegmentation, but also preserves the edge information. The experimental results show that the p method is feasible and can give better image segmentation.