We have been developing an image recognition system which has an ability to automatically acquire a model of an object class from image examples. The model is described in hierarchical relationship of segmented regions and 2-D features of the regions. The system generates a model according to the correspondence among regions of the segmentation trees. In this paper, we will discuss new model description based on contour information of the regions.
|Number of pages||6|
|Journal||Research Reports on Information Science and Electrical Engineering of Kyushu University|
|Publication status||Published - Mar 1997|
All Science Journal Classification (ASJC) codes
- Computer Science(all)
- Electrical and Electronic Engineering