University of Oulu

I. Melekhov, J. Kannala and E. Rahtu, "Siamese network features for image matching," 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, 2016, pp. 378-383. doi: 10.1109/ICPR.2016.7899663

Siamese network features for image matching

Saved in:
Author: Melekhov, Iaroslav1; Kannala, Juho1; Rahtu, Esa2
Organizations: 1Department of Computer Science, Aalto University, Finland
2Center for Machine Vision Research, University of Oulu
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.9 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2019090526960
Language: English
Published: Institute of Electrical and Electronics Engineers, 2016
Publish Date: 2019-09-05
Description:

Abstract

Finding matching images across large datasets plays a key role in many computer vision applications such as structure-from-motion (SfM), multi-view 3D reconstruction, image retrieval, and image-based localisation. In this paper, we propose finding matching and non-matching pairs of images by representing them with neural network based feature vectors, whose similarity is measured by Euclidean distance. The feature vectors are obtained with convolutional neural networks which are learnt from labeled examples of matching and non-matching image pairs by using a contrastive loss function in a Siamese network architecture. Previously Siamese architecture has been utilised in facial image verification and in matching local image patches, but not yet in generic image retrieval or whole-image matching. Our experimental results show that the proposed features improve matching performance compared to baseline features obtained with networks which are trained for image classification task. The features generalize well and improve matching of images of new landmarks which are not seen at training time. This is despite the fact that the labeling of matching and non-matching pairs is imperfect in our training data. The results are promising considering image retrieval applications, and there is potential for further improvement by utilising more training image pairs with more accurate ground truth labels.

see all

ISBN: 978-1-5090-4847-2
ISBN Print: 978-1-5090-4848-9
Pages: 378 - 383
DOI: 10.1109/ICPR.2016.7899663
OADOI: https://oadoi.org/10.1109/ICPR.2016.7899663
Host publication: 2016 Proceedings of 23rd Internaltional conference on Pattern Recognition (ICPR 2016)
Conference: International Conference on Pattern Recognition
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Subjects:
Copyright information: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.