Chapter 9:Segmentation by Clustering
9.1 Human Vision: Grouping and Gestalt
A key feature of the human vision systemis that context affects how things are perceived.A common experience of segmentation is the way that an image can resolve itself into a figure— typically, the significant, important object—and aground—the background on which the figure lies.
The Gestalt school used the notion of a gestalt as central components in their ideas. Their work was characterized by attempts to write down a series of rules by which image elements would be associated together and interpreted as a group.
There are a variety of factors, some of which postdate the main Gestalt movement:
- Proximity: Tokens that are nearby tend to be grouped.
- Similarity: Similar tokens tend to be grouped together.
- Common fate: Tokens that have coherent motion tend to be grouped together.
- Common region: Tokens that lie inside the same closed region tend to be
grouped together.
- Parallelism: Parallel curves or tokens tend to be grouped together.
- Closure: Tokens or curves that tend to lead to closed curves tend to be
grouped together.
- Symmetry: Curves that lead to symmetric groups are grouped together.
- Continuity: Tokens that lead to continuous—as in joining up nicely, rather
than in the formal sense—curves tend to be grouped.
- Familiar configuration: Tokens that, when grouped, lead to a familiar
object tend to be grouped together.
但是,如何把上面这些rules用于形成算法还有难度,如无法把握何时选用哪条规则。
9.2 Important Applications
- 9.2.1 Background Subtraction
- 9.2.2 Shot Boundary Detection
长video是由很多短镜头(shots) 组成的,每个镜头中大多物体是不变的,每个shot可以用一个关键帧表示。
A shot boundary detection algorithm must find frames in the video that are significantly different from the previous frame. 可以用distance表示,计算distance有几种方法,目前不太需要,此处略去,有需要可以翻看原书。
- 9.2.3 Interactive Segmentation
- 9.2.4 Forming Image Regions