Duplicate Image Object Level
8 Develop Efficient Rule Sets
This chapter instructs you in using available tools to build efficient and reusable rule sets and other ruleware. It enables you to benefit from the tools of the development
environment.
Use Hierarchical Image Object Levels on page 193
Focus Processes by Using the Domain Concept on page 197 About Classification on page 208
Use Variables in Rule Sets on page 257 Use Customized Features on page 269
Reuse Process Sequences with Customized Algorithms on page 276 Work with Thematic Layers on page 284
Working with Polygons and Skeletons on page 291 Automate the Workspace Processing on page 296 Create Action Libraries on page 307
We recommend that you simultaneously consult the About Strategies chapter, focusing on composing rule sets based on the Definiens Cognition Network Language (CNL).
How to Approach Developing a Rule Set on page 326
This chapters is the second of three chapters about rule set development.
Three Chapters About Rule Set Development on page 123 How to Learn Developing Rule Sets on page 121
8.1 Use Hierarchical Image Object Levels
Although you can perform some image analysis on a single image object level, the full power of the Definiens object oriented image analysis unfolds when using multiple image object levels. On each of these levels, a number of objects is defined by the image objects on the level below that are considered their sub-objects. In the same manner, the lowest level image objects are defined by the pixels of the image that belong to them.
In this hierarchical structure, the image object hierarchy, each image object provides access to information about its neighbors, sub- and super-objects at all times. By connecting image objects vertically, access to scale and advanced texture properties is possible. The image object hierarchy allows the representation of image information at different spatial resolutions simultaneously.
Figure 152: Within the image object hierarchy, each image object is linked to its neighbors, its superobject, and its subobjects.
The image object levels of an image object hierarchy range from fine resolution on the lowest image object level to coarse resolution on the highest image object level. On its superlevel, every image object has only one image object, the superobject. On the other hand an image object may have—but is not required to have—multiple subobjects.
To better understand the concept of the image object hierarchy, imagine a meaningful
Image Object Hierarchy on page 26
Navigate Within the Image Object Hierarchy on page 114
hierarchy of image object levels, each representing a meaningful structure in an image.
These meaningful image object levels are related to the various resolutions (coarse, medium, fine) of the image objects. The hierarchical positioning of the image object levels arranges subordinate image structures below generic image structures. See the following examples from biology and geography:
Figure 153: Meaningful image object levels within an image object hierarchy.
Two trivial image object levels are always implicitly given: the partition of the image into pixels, called the pixel level, and the level with only one object covering the entire image. Together they represent the boundaries of the image object hierarchy.
You can create an image object level by using either segmentation algorithms or the copy image object level algorithm. Commonly image object levels are added above the existing one. Some of the algorithms enable you to choose if the new image object level is inserted above or below the existing one.
A new image object level can only be created between two already existing image object levels. The shapes of image objects on these super- and sublevels will constrain the shape of the objects in the new level.
The hierarchical network of an image object hierarchy is topologically definite. For example, the border of a superobject is consistent with the borders of its subobjects. The area represented by a specific image object is defined by the sum of its subobject's areas. The Definiens technology accomplishes this quite easily, because all
segmentation techniques used in Definiens Developer use region-merging algorithms.
For this reason, not all the algorithms used to analyze images allow a level to be created below an existing one. Each image object level is constructed based on its direct subobjects. For example, the subobjects one level are merged into larger image objects on the next higher level. This merge is limited by the borders of exiting superobjects;
adjacent image objects cannot be merged if they have different superobjects.
Create Image Object Levels With Segmentation Algorithms on page 195 Duplicate Image Object Level on page 195
8.1.1 Create Image Object Levels With Segmentation Algorithms
You can create an image object level by using different segmentation algorithms.
1. You can select relevant settings within the Edit Process dialog box.
2. Go to the drop-down list box within the Image Object Domain group box and select an available image object level. To switch to another image object level, select the currently active image object level and click the Parameters button to select another image object level in the Select Level dialog box.
3. For some segmentation algorithms, you choose to insert the new image object level either above or below the one selected in the image object level. Go to the Algorithm Parameters group box and look for a Level Usage parameter. If available, you can select from the options; if not available the new image object level is created above.