Two-Stage Deep Learning Approach to the Classification of Fine-Art Paintings

Sandoval Rodriguez, C, Pirogova, E and Lech, M 2019, 'Two-Stage Deep Learning Approach to the Classification of Fine-Art Paintings', IEEE Access, vol. 7, pp. 41770-41781.


Document type: Journal Article
Collection: Journal Articles

Title Two-Stage Deep Learning Approach to the Classification of Fine-Art Paintings
Author(s) Sandoval Rodriguez, C
Pirogova, E
Lech, M
Year 2019
Journal name IEEE Access
Volume number 7
Start page 41770
End page 41781
Total pages 12
Publisher Institute of Electrical and Electronics Engineer
Abstract Due to the digitization of fine art collections, pictures of fine art objects stored at museums and art galleries became widely available to the public. It created a demand for efficient software tools that would allow rapid retrieval and semantic categorization of art. This paper introduces a new, two-stage image classification approach aiming to improve the style classification accuracy. At the first stage, the proposed approach divides the input image into five patches and applies a deep convolutional neural network (CNN) to train and classify each patch individually. At the second stage, the outcomes from the individual five patches are fused in the decision-making module, which applies a shallow neural network trained on the probability vectors given by the first-stage classifier. While the first stage categorizes the input image based on the individual patches, the second stage infers the final decision label categorizing the artistic style of the analyzed input image. The key factor in improving the accuracy compared to the baseline techniques is the fact that the second stage is trained independently on the first stage using probability vectors instead of images. This way, the second stage is effectively trained to compensate for the potential mistakes made during the first stage. The proposed method was tested using six different pre-trained CNNs (AlexNet, VGG-16, VGG-19, GoogLeNet, ResNet-50, and Inceptionv3) as the first-stage classifiers, and a shallow neural network as a second-stage classifier. The experiments conducted using three standard art classification datasets indicated that the proposed method presents a significant improvement over the existing baseline techniques.
Subject Image Processing
Keyword(s) Art
Painting
Feature extraction
Standards
Task analysis
Semantics
Support vector machines
DOI - identifier 10.1109/ACCESS.2019.2907986
Copyright notice © 2019 IEEE
ISSN 2169-3536
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in Thomson Reuters Web of Science Article | Citations
Altmetric details:
Access Statistics: 9 Abstract Views  -  Detailed Statistics
Created: Mon, 29 Apr 2019, 13:04:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us