TU Darmstadt / ULB / TUbiblio

How Good are Local Features for Classes of Geometric Objects

Stark, Michael and Schiele, Bernt (2007):
How Good are Local Features for Classes of Geometric Objects.
In: 11th IEEE International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, [Conference or Workshop Item]

Abstract

Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. As such descriptors explicitly code local appearance they have shown impressive results on objects with sufficient local appearance statistics. However, many important object classes such as tools, cups and other man-made artifacts seem to require features that capture the respective shape and geometric layout of those object classes. Therefore this paper compares, on a novel data collection of 10 geometric object classes, various shape-based features with more appearance based descriptors such as SIFT. The analysis includes a direct comparison of feature statistics as well as the results within standard recognition frameworks. The results suggest that there are indeed differences between shape- based and more appearance-based features but that those differences do not always conform with what one might expect.

Item Type: Conference or Workshop Item
Erschienen: 2007
Creators: Stark, Michael and Schiele, Bernt
Title: How Good are Local Features for Classes of Geometric Objects
Language: German
Abstract:

Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. As such descriptors explicitly code local appearance they have shown impressive results on objects with sufficient local appearance statistics. However, many important object classes such as tools, cups and other man-made artifacts seem to require features that capture the respective shape and geometric layout of those object classes. Therefore this paper compares, on a novel data collection of 10 geometric object classes, various shape-based features with more appearance based descriptors such as SIFT. The analysis includes a direct comparison of feature statistics as well as the results within standard recognition frameworks. The results suggest that there are indeed differences between shape- based and more appearance-based features but that those differences do not always conform with what one might expect.

Title of Book: 11th IEEE International Conference on Computer Vision (ICCV 2007)
Divisions: 20 Department of Computer Science
Event Location: Rio de Janeiro, Brazil
Date Deposited: 31 Dec 2016 10:04
Identification Number: iccv2007stark
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item