Selective Search for Object Recognition
2014-12-09 16:07
561 查看
object localisation的几种方式,Exhaustive search, segmentation.
Sliding window, part-based object localisation.
论文中的算法先对image在不同的表达下做over segmentation, 然后不断 hierarchical,在这个过程中不停产生box.算法描述非常明确。
关于两个region的similarity的计算比较复杂,为了效率必须保证合并时可以很容易生成新region的描述。similarity包括了color,texture,size,fill
initial solution的参数含义
sigma: Used to smooth the input image before segmenting it.
k: Value for the threshold function.
min: Minimum component size enforced by post-processing.
Sliding window, part-based object localisation.
论文中的算法先对image在不同的表达下做over segmentation, 然后不断 hierarchical,在这个过程中不停产生box.算法描述非常明确。
关于两个region的similarity的计算比较复杂,为了效率必须保证合并时可以很容易生成新region的描述。similarity包括了color,texture,size,fill
initial solution的参数含义
sigma: Used to smooth the input image before segmenting it.
k: Value for the threshold function.
min: Minimum component size enforced by post-processing.
相关文章推荐
- Segmentation as Selective Search for Object Recognition
- Selective Search for Object Recognition解读
- Selective Search for Object Recognition
- 论文笔记《Selective Search for object recognition》
- 论文笔记《Selective Search for object recognition》
- Selective Search for Object Recognition----论文笔记
- R-CNN之前的准备:Selective Search for Object Recognition
- Selective Search for Object Recognition(IJCV 2013) 论文及代码解读
- 论文阅读笔记--Selective Search for Object Recognition
- 【学习笔记】Selective Search算法--Selective Search for Object Recognition
- Selective Search for Object Recognition解读
- Selective Search for Object Recognition
- 【转】R-CNN学习笔记1:Selective Search for Object Recognition
- Selective Search for Object Recognition
- 论文笔记《Selective Search for object recognition》
- Selective Search for Object Recognition
- Selective Search for Object Recognition解读
- Selective Search for Object Recognition
- 【计算机视觉】Selective Search for Object Recognition论文阅读2
- R-CNN学习笔记1:Selective Search for Object Recognition