Image patch matching using convolutional descriptors with euclidean distance
Melekhov, Iaroslav; Kannala, Juho; Rahtu, Esa (2017-03-16)
Melekhov I., Kannala J., Rahtu E. (2017) Image Patch Matching Using Convolutional Descriptors with Euclidean Distance. In: Chen CS., Lu J., Ma KK. (eds) Computer Vision – ACCV 2016 Workshops. ACCV 2016. Lecture Notes in Computer Science, vol 10118. Springer, Cham
© Springer International Publishing AG 2017. This is a post-peer-review, pre-copyedit version of an article published in ACCV 2016: Computer Vision – ACCV 2016 Workshops. The final authenticated version is available online at: https://doi.org/10.1007/978-3-319-54526-4_46.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2019060518462
Tiivistelmä
Abstract
In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L₂ norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular hand-crafted descriptors, such as SIFT. According to the results, our approach outperforms state-of-the-art L₂-based descriptors and can be considered as a direct replacement of SIFT. In addition, we conducted experiments with batch normalization and histogram equalization as a preprocessing method of the input data. The results confirm that these techniques further improve the performance of the proposed descriptor. Finally, we show promising preliminary results by appending our CNNs with recently proposed spatial transformer networks and provide a visualisation and interpretation of their impact.
Kokoelmat
- Avoin saatavuus [32022]