Abstract | ||
---|---|---|
In this paper, we present a new information-theoretic framework for object understanding. From a visibility channel between a set of viewpoints and the polygons of an object, and three specific information measures introduced in the field of neural systems, we analyze and visualize the information associated with an object. Our approach is twofold since we present several forms of representing the shape information in the object space and different ways of capturing this information from the viewpoint space. First, we introduce several information measures associated with the polygons of the object. The way we visualize, this polygonal information provides us with different forms of perceiving the shape of the object. Second, we present several ways of evaluating the shape information from the observer’s point of view. To do this, the polygonal information is “projected” onto the viewpoints to quantify the information associated with a viewpoint and is used to select the \(N\) best views and to explore the object. A number of experiments show the behavior of all proposed measures. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/s11760-013-0449-y | Signal, Image and Video Processing |
Keywords | Field | DocType |
computer vision,information theory,form perception | Information theory,Computer vision,Visibility,Polygon,Object model,Communication channel,Specific-information,Artificial intelligence,Ambient occlusion,Mathematics,Form perception | Journal |
Volume | Issue | ISSN |
7 | 3 | 1863-1711 |
Citations | PageRank | References |
2 | 0.36 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xavier Bonaventura | 1 | 9 | 2.59 |
Miquel Feixas | 2 | 637 | 45.61 |
Mateu Sbert | 3 | 1108 | 123.95 |