Information measures for object understanding

Full Text
Information-measures.pdf embargoed access
Request a copy
When filling the form you are requesting a copy of the article, that is deposited in the institutional repository (DUGiDocs), at the autor or main autor of the article. It will be the same author who decides to give a copy of the document to the person who requests it, if it considers it appropriate. In any case, the UdG Library doesn’t take part in this process because it is not authorized to provide restricted articles.
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 ​
​Tots els drets reservats