Statistical Methods for Descriptor Matching

Olivier Collier

ISBN 10: 363971539X / ISBN 13: 9783639715392

Published by Scholars' Press Apr 2014, 2014

About this Item

This item is printed on demand - it takes 3-4 days longer - Neuware -Many applications, as in computer vision or medicine, aim at identifying the similarities between several images or signals. Thereafter, it is possible to detect objects, to follow them, or to overlap different pictures. In every case, the algorithmic procedures that treat the images use a selection of keypoints that they try to match by pairs. The most popular algorithm nowadays is SIFT, that performs keypoint selection, descriptor calculation, and provides a criterion for global descriptor matching. We considered changing the classical descriptor, which resulted in a shift testing problem that we solved in the minimax frame. Then, we gave a rigorous statistical formulation for the global descriptor matching problem and studied it in some special cases. 128 pp. Englisch.

Seller Inventory # 9783639715392

Bibliographic Details

• Title: Statistical Methods for Descriptor Matching
• Publisher: Scholars' Press Apr 2014
• Publication Date: 2014
• Language: English
• ISBN 10: 363971539X
• ISBN 13: 9783639715392
• Binding: Taschenbuch
• Condition: Neu

About this title

Synopsis

Many applications, as in computer vision or medicine, aim at identifying the similarities between several images or signals. Thereafter, it is possible to detect objects, to follow them, or to overlap different pictures. In every case, the algorithmic procedures that treat the images use a selection of keypoints that they try to match by pairs. The most popular algorithm nowadays is SIFT, that performs keypoint selection, descriptor calculation, and provides a criterion for global descriptor matching. We considered changing the classical descriptor, which resulted in a shift testing problem that we solved in the minimax frame. Then, we gave a rigorous statistical formulation for the global descriptor matching problem and studied it in some special cases.

About the Author

Olivier Collier is a former student of the Ecole Normale Supérieure de Cachan. He obtained his PhD under the supervision of Arnak Dalalyan at Université Paris-Est (France). He is now a postdoctoral researcher at Ecole des Mines de Paris and Institut Curie.