Download now Free registration required
When several approaches on image-based modeling of 3D plants/trees were successfully developed, they usually applied a subjective inspection to assess the quality of synthesized plants/trees based on their given image data. For this reason, the authors propose a preliminary study on objective approaches in evaluating the synthesized plants from the given image data. Two measures, in a general name of "Resemblance Index (RI)", are defined and investigated based on the normalized mutual information (RINI), and Coincident-Bit-Counting criterion (RICBC), respectively. They propose a strategy of hierarchical evaluations on different attributes of objects. In this paper, they apply the proposed approach in evaluations of 3D plants but only consider the geometrical and crown distribution attributes.
- Format: PDF
- Size: 1014 KB