文件名称:BSR_source
- 所属分类：
- 图形图像处理(光照,映射..)
- 资源属性：
- [C/C++]
- 上传时间：
- 2017-09-25
- 文件大小：
- 29.14mb
- 下载次数：
- 0次
- 提 供 者：
- aa11****
- 相关连接：
- 无
- 下载说明：
- 别用迅雷下载，失败请重下，重下不扣分！
介绍说明－－下载内容均来自于网络，请自行研究使用
Contour Detection and Hierarchical Image Segmentation (UC Berkeley)
MATLAB/C++混编
Arbela?ez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898–916. https://doi.org/10.1109/TPAMI.2010.161(This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization fr a mework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.)
MATLAB/C++混编
Arbela?ez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898–916. https://doi.org/10.1109/TPAMI.2010.161(This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization fr a mework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.)
(系统自动生成,下载前可以参看下载内容)
下载文件列表
BSR_source.tgz