| H. M. Gomes. Model learning in iconic vision. PhD Thesis, Division of Informatics, Edinburgh University, to be submitted, August 2000. 9 |
No context found.
H. M. Gomes. Model learning in iconic vision. PhD Thesis, Division of Informatics, Edinburgh University, to be submitted, August 2000. 9
....these features were found. The lower diagonals of the sub tables are not shown because they are symmetric. The feature types d and e have only one instance and therefore were not included in the table, their coordinates are as follows: P d = 314; 226) and P e = 441; 215) available in [4]. An important di erence between the way we learn models and the existing traditional approaches is that our system is designed to search the visual eld for objects in an attentive way, like humans and some other animals do. In this way, the relative position of clustered features can be recorded ....
H. M. Gomes. Model learning in iconic vision. PhD Thesis, Division of Informatics, Edinburgh University, to be submitted, August 2000. 9
....a sequence of scenes. We found that structured models can indeed be learned in such a context by using a graph based representation and algorithm. In a case study we have shown how our approach works in practice. More complex case studies are currently under development and will be available in [4]. An important di erence between the way we learn models and the existing traditional approaches is that our system is designed to search the visual eld for objects in an attentive way, like humans and some other animals do. In this way, the relative position of clustered features can be recorded ....
H. M. Gomes. Model learning in iconic vision. PhD Thesis, Division of Informatics, Edinburgh University, to be submitted, August 2000.
No context found.
H. M. Gomes, Model Learning in Iconic Vision, PhD Thesis, School of Informatics, The University of Edinburgh, May, 2002.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC