A CNN-LSTM framework for authorship classification of paintings

Kevin Alfianto Jangtjik, Trang Thi Ho, Mei-Chen Yeh, Kai Lung Hua

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

Abstract

The authenticity of digital painting image is an urgent demand in the field of art. Yet, determining the authorship of a certain painting is a challenging task due to two reasons: (1) various artists might share similar painting styles; and (2) an artist could create different styles. In this paper, we present a novel method for authorship classification of paintings based on a CNN-LSTM framework. First, a multiscale pyramid is constructed from a painting image. Second, a CNN-LSTM model is learned and it returns possibly multiple labels for one image. To aggregate the final classification result, an adaptive fusion method is employed. Experimental results show that the proposed method has superior classification performance compared with the state-of-the-art techniques.

LanguageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages2866-2870
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

Fingerprint

Painting
Labels
Fusion reactions

Keywords

  • Convolutional neural network
  • Digital image classification
  • Long short-term memory networks
  • Multiscale pyramid representation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Jangtjik, K. A., Ho, T. T., Yeh, M-C., & Hua, K. L. (2018). A CNN-LSTM framework for authorship classification of paintings. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 2866-2870). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296806

A CNN-LSTM framework for authorship classification of paintings. / Jangtjik, Kevin Alfianto; Ho, Trang Thi; Yeh, Mei-Chen; Hua, Kai Lung.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 2866-2870.

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

Jangtjik, KA, Ho, TT, Yeh, M-C & Hua, KL 2018, A CNN-LSTM framework for authorship classification of paintings. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 2866-2870, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17/9/17. https://doi.org/10.1109/ICIP.2017.8296806
Jangtjik KA, Ho TT, Yeh M-C, Hua KL. A CNN-LSTM framework for authorship classification of paintings. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 2866-2870 https://doi.org/10.1109/ICIP.2017.8296806
Jangtjik, Kevin Alfianto ; Ho, Trang Thi ; Yeh, Mei-Chen ; Hua, Kai Lung. / A CNN-LSTM framework for authorship classification of paintings. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 2866-2870
@inproceedings{cbc5d614a7ab4702aba9c84b97dc050d,
title = "A CNN-LSTM framework for authorship classification of paintings",
abstract = "The authenticity of digital painting image is an urgent demand in the field of art. Yet, determining the authorship of a certain painting is a challenging task due to two reasons: (1) various artists might share similar painting styles; and (2) an artist could create different styles. In this paper, we present a novel method for authorship classification of paintings based on a CNN-LSTM framework. First, a multiscale pyramid is constructed from a painting image. Second, a CNN-LSTM model is learned and it returns possibly multiple labels for one image. To aggregate the final classification result, an adaptive fusion method is employed. Experimental results show that the proposed method has superior classification performance compared with the state-of-the-art techniques.",
keywords = "Convolutional neural network, Digital image classification, Long short-term memory networks, Multiscale pyramid representation",
author = "Jangtjik, {Kevin Alfianto} and Ho, {Trang Thi} and Mei-Chen Yeh and Hua, {Kai Lung}",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296806",
language = "English",
volume = "2017-September",
pages = "2866--2870",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A CNN-LSTM framework for authorship classification of paintings

AU - Jangtjik, Kevin Alfianto

AU - Ho, Trang Thi

AU - Yeh, Mei-Chen

AU - Hua, Kai Lung

PY - 2018/2/20

Y1 - 2018/2/20

N2 - The authenticity of digital painting image is an urgent demand in the field of art. Yet, determining the authorship of a certain painting is a challenging task due to two reasons: (1) various artists might share similar painting styles; and (2) an artist could create different styles. In this paper, we present a novel method for authorship classification of paintings based on a CNN-LSTM framework. First, a multiscale pyramid is constructed from a painting image. Second, a CNN-LSTM model is learned and it returns possibly multiple labels for one image. To aggregate the final classification result, an adaptive fusion method is employed. Experimental results show that the proposed method has superior classification performance compared with the state-of-the-art techniques.

AB - The authenticity of digital painting image is an urgent demand in the field of art. Yet, determining the authorship of a certain painting is a challenging task due to two reasons: (1) various artists might share similar painting styles; and (2) an artist could create different styles. In this paper, we present a novel method for authorship classification of paintings based on a CNN-LSTM framework. First, a multiscale pyramid is constructed from a painting image. Second, a CNN-LSTM model is learned and it returns possibly multiple labels for one image. To aggregate the final classification result, an adaptive fusion method is employed. Experimental results show that the proposed method has superior classification performance compared with the state-of-the-art techniques.

KW - Convolutional neural network

KW - Digital image classification

KW - Long short-term memory networks

KW - Multiscale pyramid representation

UR - http://www.scopus.com/inward/record.url?scp=85045346024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045346024&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296806

DO - 10.1109/ICIP.2017.8296806

M3 - Conference contribution

VL - 2017-September

SP - 2866

EP - 2870

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -