A comparison of local feature detectors and descriptors for visual object categorization by intra-class repeatability and matching

Intuitive and easily interpretable performance measures, repeatability and matching performance, for local feature detectors and descriptors were introduced by Mikolajczyk et al. [10, 9]. They, however, measured performance in a wide baseline setting that does not correspond to the visual object cat...

Full description

Saved in:
Bibliographic Details
Main Authors: Lankinen, J., Kangas, V., Kamarainen, J-K
Format: Conference Proceeding
Language:English
Subjects:
Computer vision
Detectors
Feature extraction
Performance evaluation
Robustness
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Intuitive and easily interpretable performance measures, repeatability and matching performance, for local feature detectors and descriptors were introduced by Mikolajczyk et al. [10, 9]. They, however, measured performance in a wide baseline setting that does not correspond to the visual object categorisation problem which is a popular application of the detectors and descriptors. The limitation has been recognised and ad hoc evaluations proposed. To the authors' best knowledge, our work is the first which extends the original repeatability and matching performance measures to the case of object classes. Using the novel evaluation framework we test state-of-the-art detectors and descriptors with the popular Caltech-101 dataset and report the object category level (intra-class) repeatability and matching performances.
ISSN:1051-4651
2831-7475