Ni, H;
Weixin, Y;
Lianwen, J;
Terry, L;
(2017)
Rotation-free online handwritten character recognition using dyadic path signature features, hanging normalization, and deep neural network.
In:
Proceedings of the 2016 23rd International Conference on Pattern Recognition (ICPR).
(pp. pp. 4083-4088).
IEEE
Preview |
Text
Ni_Rotation-free OLHCR using Dyadic Path Signature Features Hanging Normalization and DNN - 201604018.pdf - Accepted Version Download (777kB) | Preview |
Abstract
The path signature feature (PSF) which was initially introduced in rough paths theory as a branch of stochastic analysis, has recently been successfully applied to the field of pattern recognition for extracting sufficient quantity of information contained in a finite trajectory, but with potentially high dimension. In this paper, we propose a variation of path signature representation, namely the dyadic path signature feature (D-PSF), to fully characterize the trajectory using a hierarchical structure to solve the rotation-free online handwritten character recognition (OLHCR) problem. We adopt the deep neural network (DNN) as classifier, and investigate three hanging normalization methods to improve the robustness of the DNN to rotational distortions. Extensive experiments on digits, English letters, and Chinese radicals demonstrated that the proposed D-PSF, jointly with hanging normalization and DNN, achieved very promising results for rotated OLHCR, significantly outperforming previous methods.
Type: | Proceedings paper |
---|---|
Title: | Rotation-free online handwritten character recognition using dyadic path signature features, hanging normalization, and deep neural network |
Event: | 2016 23rd International Conference on Pattern Recognition (ICPR) |
Location: | Cancun, Mexico |
Dates: | 04 December 2016 - 08 December 2016 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/ICPR.2016.7900273 |
Publisher version: | http://dx.doi.org/10.1109/ICPR.2016.7900273 |
Language: | English |
Additional information: | This version is the author accepted manuscript]. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Feature extraction, Character recognition, Trajectory, Distortion, Handwriting recognition, Biological neural networks, rotation-free recognition, online handwritten character recognition, path signature feature, rotation normalization, neural network |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics |
URI: | https://discovery.ucl.ac.uk/id/eprint/10045824 |
Archive Staff Only
View Item |