CNN training with graph-based sample preselection: application to handwritten character recognition

Frederic Rayar; Masanori Goto; Seiichi Uchida

doi:10.1109/DAS.2018.10

CNN training with graph-based sample preselection: application to handwritten character recognition

Frederic Rayar, Masanori Goto, Seiichi Uchida

Real world robotics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

Abstract

In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.

Original language	English
Title of host publication	Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	19-24
Number of pages	6
ISBN (Electronic)	9781538633465
DOIs	https://doi.org/10.1109/DAS.2018.10
Publication status	Published - Jun 22 2018
Event	13th IAPR International Workshop on Document Analysis Systems, DAS 2018 - Vienna, Austria Duration: Apr 24 2018 → Apr 27 2018

Publication series

Name	Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

Other

Other	13th IAPR International Workshop on Document Analysis Systems, DAS 2018
Country/Territory	Austria
City	Vienna
Period	4/24/18 → 4/27/18

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/DAS.2018.10

Cite this

Rayar, F., Goto, M., & Uchida, S. (2018). CNN training with graph-based sample preselection: application to handwritten character recognition. In Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018 (pp. 19-24). (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DAS.2018.10

CNN training with graph-based sample preselection: application to handwritten character recognition. / Rayar, Frederic; Goto, Masanori; Uchida, Seiichi.
Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 19-24 (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rayar, F, Goto, M & Uchida, S 2018, CNN training with graph-based sample preselection: application to handwritten character recognition. in Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 19-24, 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, Vienna, Austria, 4/24/18. https://doi.org/10.1109/DAS.2018.10

Rayar F, Goto M, Uchida S. CNN training with graph-based sample preselection: application to handwritten character recognition. In Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 19-24. (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018). doi: 10.1109/DAS.2018.10

Rayar, Frederic ; Goto, Masanori ; Uchida, Seiichi. / CNN training with graph-based sample preselection : application to handwritten character recognition. Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 19-24 (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018).

@inproceedings{5159bd03b25642828ae9341eb2fa040a,

title = "CNN training with graph-based sample preselection: application to handwritten character recognition",

abstract = "In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.",

author = "Frederic Rayar and Masanori Goto and Seiichi Uchida",

note = "Funding Information: ACKNOWLEDGEMENT This research was partially supported by MEXT-Japan (Grant No. 17H06100). Publisher Copyright: {\textcopyright} 2018 IEEE.; 13th IAPR International Workshop on Document Analysis Systems, DAS 2018 ; Conference date: 24-04-2018 Through 27-04-2018",

year = "2018",

month = jun,

day = "22",

doi = "10.1109/DAS.2018.10",

language = "English",

series = "Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "19--24",

booktitle = "Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018",

address = "United States",

}

TY - GEN

T1 - CNN training with graph-based sample preselection

T2 - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

AU - Rayar, Frederic

AU - Goto, Masanori

AU - Uchida, Seiichi

PY - 2018/6/22

Y1 - 2018/6/22

N2 - In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.

AB - In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.

UR - http://www.scopus.com/inward/record.url?scp=85050259581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050259581&partnerID=8YFLogxK

U2 - 10.1109/DAS.2018.10

DO - 10.1109/DAS.2018.10

M3 - Conference contribution

AN - SCOPUS:85050259581

T3 - Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

SP - 19

EP - 24

BT - Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 24 April 2018 through 27 April 2018

ER -

CNN training with graph-based sample preselection: application to handwritten character recognition

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this