Share Email Print

Proceedings Paper

Trainable Siamese keypoint descriptors for real-time applications
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Computing image patch descriptors for correspondence problems relies heavily on hand-crafted feature transformations, e.g. SIFT, SURF. In this paper, we explore a Siamese pairing of fully connected neural networks for the purpose of learning discriminative local feature descriptors. Resulting ANN computes 128-D descriptors, and demonstrates consistent speedup as compared to such state-of-the-art methods as SIFT and FREAK on PCs as well as in embedded systems. We use L2 distance to reflect descriptor similarity during both training and testing. In this way, feature descriptors we propose can be easily compared to their hand-crafted counterparts. We also created a dataset augmented with synthetic data for learning local features, and it is available online. The augmentations provide training data for our descriptors to generalise well against scaling and rotation, shift, Gaussian noise, and illumination changes.

Paper Details

Date Published: 8 February 2017
PDF: 5 pages
Proc. SPIE 10253, 2016 International Conference on Robotics and Machine Vision, 1025306 (8 February 2017); doi: 10.1117/12.2266351
Show Author Affiliations
Fedor A. Fedorenko, Moscow Institute of Physics and Technology (Russian Federation)
Alena A. Ivanova, Institute for Information Transmission Problems (Russian Federation)
Elena E. Limonova, Smart Engines Ltd. (Russian Federation)
Ivan A. Konovalenko, Institute for Information Transmission Problems (Russian Federation)

Published in SPIE Proceedings Vol. 10253:
2016 International Conference on Robotics and Machine Vision
Alexander V. Bernstein; Adrian Olaru; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?