图 书 馆
学习全成对的光谱分割的亲和力Learning Full Pairwise Affinities for Spectral Segmentation |
|
| 课程网址: | http://videolectures.net/cvpr2010_hoon_kim_lfpa/ |
| 主讲教师: | Tae Hoon Kim |
| 开课单位: | 首尔国立大学 |
| 开课时间: | 信息不详。欢迎您在右侧留言补充。 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. The overall quality of the spectral segmentation depends mainly on the pairwise pixel affinities. By employing a semi-supervised learning technique, optimal affinities are learnt from the test image without iteration. We first construct a multi-layer graph with pixels and regions, generated by the mean shift algorithm, as nodes. By applying the semi-supervised learning strategy to this graph, we can estimate the intra- and inter-layer affinities between all pairs of nodes together. These pairwise affinities are then used to simultaneously cluster all pixel and region nodes into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Our algorithm provides high-quality segmentations with object details by directly incorporating the full range connections in the spectral framework. Since the full affinity matrix is defined by the inverse of a sparse matrix, its eigendecomposition is efficiently computed. The experimental results on Berkeley and MSRC image databases demonstrate the relevance and accuracy of our algorithm as compared to existing popular methods. |
| 关 键 词: | 图像分析; 计算机科学; 计算机视觉 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-12-19：cwx |
| 阅读次数: | 68 |