Learning to detect and match keypoints with deep architectures
Research output: Contribution to conference › Paper › Research › peer-review
Feature detection and description is a pivotal step in many computer vision pipelines. Traditionally, human engineered features have been the main workhorse in this domain. In this paper, we present a novel approach for learning to detect and describe keypoints from images leveraging deep architectures. To allow for a learning based approach, we collect a large-scale dataset of patches with matching multiscale keypoints. The proposed model learns from this vast dataset to identify and describe meaningful keypoints. We evaluate our model for the effectiveness of its learned representations for detecting multiscale keypoints and describing their respective support regions.
Original language | English |
---|---|
Publication date | 2016 |
DOIs | |
Publication status | Published - 2016 |
Externally published | Yes |
Event | 27th British Machine Vision Conference, BMVC 2016 - York, United Kingdom Duration: 19 Sep 2016 → 22 Sep 2016 |
Conference
Conference | 27th British Machine Vision Conference, BMVC 2016 |
---|---|
Country | United Kingdom |
City | York |
Period | 19/09/2016 → 22/09/2016 |
Sponsor | ARM, Disney Research, et al., HP, Ocado Technology, OSRAM |
Bibliographical note
Funding Information:
We would like to thank Michael Wilber and Tsung-Yi Lin for their valuable input. This work was supported by the KACST Graduate Studies Scholarship.
Publisher Copyright:
© 2016. The copyright of this document resides with its authors.
ID: 301828084