An Oil Painters Recognition Method Based on Cluster Multiple Kernel Learning Algorithm

Zhifang Liao, Le Gao, Tian Zhou, Xiaoping Fan, Yan Zhang, Jinsong Wu

Research output: Contribution to journalArticle

4 Downloads (Pure)

Abstract

A lot of image processing research works focus on natural images, such as in classification, clustering, and the research on the recognition of artworks (such as oil paintings), from feature extraction to classifier design, is relatively few. This paper focuses on oil painter recognition and tries to find the mobile application to recognize the painter. This paper proposes a cluster multiple kernel learning algorithm, which extracts oil painting features from three aspects: color, texture, and spatial layout, and generates multiple candidate kernels with different kernel functions. With the results of clustering numerous candidate kernels, we selected the sub-kernels with better classification performance, and use the traditional multiple kernel learning algorithm to carry out the multi-feature fusion classification. The algorithm achieves a better result on the Painting91 than using traditional multiple kernel learning directly.
Original languageEnglish
Pages (from-to)26842-26854
Number of pages13
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 14 Feb 2019

Fingerprint

Learning algorithms
Oils
Painting
Feature extraction
Image processing
Classifiers
Fusion reactions
Textures
Color

Keywords

  • feature extraction
  • painting
  • kernel
  • image colour analysis
  • oils
  • art
  • histograms
  • oil painters recognition
  • multiple kernel learning

Cite this

Liao, Zhifang ; Gao, Le ; Zhou, Tian ; Fan, Xiaoping ; Zhang, Yan ; Wu, Jinsong. / An Oil Painters Recognition Method Based on Cluster Multiple Kernel Learning Algorithm. In: IEEE Access. 2019 ; Vol. 7. pp. 26842-26854.
@article{c903ff53291241cab92c94b9c3732860,
title = "An Oil Painters Recognition Method Based on Cluster Multiple Kernel Learning Algorithm",
abstract = "A lot of image processing research works focus on natural images, such as in classification, clustering, and the research on the recognition of artworks (such as oil paintings), from feature extraction to classifier design, is relatively few. This paper focuses on oil painter recognition and tries to find the mobile application to recognize the painter. This paper proposes a cluster multiple kernel learning algorithm, which extracts oil painting features from three aspects: color, texture, and spatial layout, and generates multiple candidate kernels with different kernel functions. With the results of clustering numerous candidate kernels, we selected the sub-kernels with better classification performance, and use the traditional multiple kernel learning algorithm to carry out the multi-feature fusion classification. The algorithm achieves a better result on the Painting91 than using traditional multiple kernel learning directly.",
keywords = "feature extraction , painting , kernel , image colour analysis , oils , art, histograms, oil painters recognition, multiple kernel learning",
author = "Zhifang Liao and Le Gao and Tian Zhou and Xiaoping Fan and Yan Zhang and Jinsong Wu",
note = "Acceptance from webpage",
year = "2019",
month = "2",
day = "14",
doi = "10.1109/ACCESS.2019.2899389",
language = "English",
volume = "7",
pages = "26842--26854",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

An Oil Painters Recognition Method Based on Cluster Multiple Kernel Learning Algorithm. / Liao, Zhifang; Gao, Le; Zhou, Tian; Fan, Xiaoping; Zhang, Yan; Wu, Jinsong.

In: IEEE Access, Vol. 7, 14.02.2019, p. 26842-26854.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Oil Painters Recognition Method Based on Cluster Multiple Kernel Learning Algorithm

AU - Liao, Zhifang

AU - Gao, Le

AU - Zhou, Tian

AU - Fan, Xiaoping

AU - Zhang, Yan

AU - Wu, Jinsong

N1 - Acceptance from webpage

PY - 2019/2/14

Y1 - 2019/2/14

N2 - A lot of image processing research works focus on natural images, such as in classification, clustering, and the research on the recognition of artworks (such as oil paintings), from feature extraction to classifier design, is relatively few. This paper focuses on oil painter recognition and tries to find the mobile application to recognize the painter. This paper proposes a cluster multiple kernel learning algorithm, which extracts oil painting features from three aspects: color, texture, and spatial layout, and generates multiple candidate kernels with different kernel functions. With the results of clustering numerous candidate kernels, we selected the sub-kernels with better classification performance, and use the traditional multiple kernel learning algorithm to carry out the multi-feature fusion classification. The algorithm achieves a better result on the Painting91 than using traditional multiple kernel learning directly.

AB - A lot of image processing research works focus on natural images, such as in classification, clustering, and the research on the recognition of artworks (such as oil paintings), from feature extraction to classifier design, is relatively few. This paper focuses on oil painter recognition and tries to find the mobile application to recognize the painter. This paper proposes a cluster multiple kernel learning algorithm, which extracts oil painting features from three aspects: color, texture, and spatial layout, and generates multiple candidate kernels with different kernel functions. With the results of clustering numerous candidate kernels, we selected the sub-kernels with better classification performance, and use the traditional multiple kernel learning algorithm to carry out the multi-feature fusion classification. The algorithm achieves a better result on the Painting91 than using traditional multiple kernel learning directly.

KW - feature extraction

KW - painting

KW - kernel

KW - image colour analysis

KW - oils

KW - art

KW - histograms

KW - oil painters recognition

KW - multiple kernel learning

U2 - 10.1109/ACCESS.2019.2899389

DO - 10.1109/ACCESS.2019.2899389

M3 - Article

VL - 7

SP - 26842

EP - 26854

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -