A robust dissimilarity-based neural network for temporal pattern recognition

Brian Kenji Iwana, Volkmar Frinken, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages265-270
Number of pages6
ISBN (Electronic)9781509009817
DOIs
Publication statusPublished - Jan 10 2017
Event15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 - Shenzhen, China
Duration: Oct 23 2016Oct 26 2016

Publication series

NameProceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
ISSN (Print)2167-6445
ISSN (Electronic)2167-6453

Other

Other15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016
CountryChina
CityShenzhen
Period10/23/1610/26/16

Fingerprint

Pattern recognition
Neural networks
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Iwana, B. K., Frinken, V., & Uchida, S. (2017). A robust dissimilarity-based neural network for temporal pattern recognition. In Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 (pp. 265-270). [7814074] (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICFHR.2016.0058

A robust dissimilarity-based neural network for temporal pattern recognition. / Iwana, Brian Kenji; Frinken, Volkmar; Uchida, Seiichi.

Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 265-270 7814074 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iwana, BK, Frinken, V & Uchida, S 2017, A robust dissimilarity-based neural network for temporal pattern recognition. in Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016., 7814074, Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, Institute of Electrical and Electronics Engineers Inc., pp. 265-270, 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016, Shenzhen, China, 10/23/16. https://doi.org/10.1109/ICFHR.2016.0058
Iwana BK, Frinken V, Uchida S. A robust dissimilarity-based neural network for temporal pattern recognition. In Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 265-270. 7814074. (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR). https://doi.org/10.1109/ICFHR.2016.0058
Iwana, Brian Kenji ; Frinken, Volkmar ; Uchida, Seiichi. / A robust dissimilarity-based neural network for temporal pattern recognition. Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 265-270 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR).
@inproceedings{5ad14e02b5f74a5e82d3df21a7f442fa,
title = "A robust dissimilarity-based neural network for temporal pattern recognition",
abstract = "Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods.",
author = "Iwana, {Brian Kenji} and Volkmar Frinken and Seiichi Uchida",
year = "2017",
month = "1",
day = "10",
doi = "10.1109/ICFHR.2016.0058",
language = "English",
series = "Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "265--270",
booktitle = "Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016",
address = "United States",

}

TY - GEN

T1 - A robust dissimilarity-based neural network for temporal pattern recognition

AU - Iwana, Brian Kenji

AU - Frinken, Volkmar

AU - Uchida, Seiichi

PY - 2017/1/10

Y1 - 2017/1/10

N2 - Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods.

AB - Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85012915455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012915455&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2016.0058

DO - 10.1109/ICFHR.2016.0058

M3 - Conference contribution

AN - SCOPUS:85012915455

T3 - Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR

SP - 265

EP - 270

BT - Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -