【摘要】 传统图割算法一般基于图像的局部关系构建分割模型,由于缺乏图像的结构层信息,导致它们较难分割包含噪声和纹理的图像。针对上述问题,论文提出一种基于多尺度超像素和图割的交互式图像分割算法。首先利用线性迭代聚类算法对图像进行多尺度预分割,用获取到的超像素代替像素构建加权图。然后通过融合多尺度超像素信息,基于小尺度超像素的局部近邻性约束克服过分割,基于大尺度超像素的长范围连通性约束克服欠分割,来进一步提高图像分割质量。最后通过实验验证了该算法的有效性。更多还原

【Abstract】 The conventional graph-theory-based methods only utilize the neighboring relationships between pixels for the segmentation,which causes them limit to images with noise and texture due to underutilizing the structure information of the image. To address the above problems,an interactive image segmentation algorithm based on multi-scale superpixel and graph cut is proposed. Firstly,the simple linear iterative clustering(SLIC)algorithm is used to pre-segment image in multi-scale,and a weighted graph is constructed with the obtained superpixels instead of pixels. By fusing multi-scale superpixel information,the local neighborhood constraint of small-scale superpixel is utilized to overcome the over-segmentation,and the long range connectivity constraint of large-scale superpixel is utilized to overcome the under-segmentation. Finally,the experiment results demonstrate the effectiveness of the proposed algorithm.更多还原