Classification of Style in Fine-Art Paintings Using Transfer Learning and Weighted Image Patches

With the ongoing expansion of digitized artworks, the automated analysis and categorization of fine art paintings have become a rapidly growing research field. However, due to the implicit subjectivity and nuances separating different artistic movements, numerical art analysis implies significant challenges. This paper describes a new efficient method that improves the classification accuracy of fine-art paintings compared to the existing baseline methods. The proposed approach is based on transfer learning and classification of sub-regions or patches of the painting. A weighted sum of the individual-patch classification outcomes gives the final stylistic label of the analyzed painting. The patch weights are optimized to maximize the overall style recognition accuracy. Experimental validation based on two standard art classification datasets and six different pre-trained convolutional neural network (CNN) models (AlexNet, VGG-16, VGG-19, GoogLeNet, ResNet-50 and Inceptionv3) shows that the proposed approach outperforms the baseline techniques and offers low computational and data costs.

• Publication year

  2018

• Venue

  International Conference on Signal Processing and Communication Systems

• Publication date

  2018-12-01

• Fields of study

  Art, Computer Science

• Identifiers
  DOI 10.1109/ICSPCS.2018.8631731
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Shape of Art History in the Eyes of the Machine

  2018influential reference
• Image Style Classification Based on Learnt Deep Correlation Features

  2018cited by this paper
• Convolution Neural Networks With Two Pathways for Image Style Recognition

  2017cited by this paper
• Artistic Movement Recognition by Boosted Fusion of Color Structure and Topographic Description

  2017influential reference
• Deep Multibranch Neural Network for Painting Categorization

  2017cited by this paper
• Ceci n'est pas une pipe: A deep convolutional network for fine-art paintings classification

  2016cited by this paper
• Pandora: Description of a painting database for art movement recognition with baselines and perspectives

  2016cited by this paper
• Fine tuning CNNS with scarce training data — Adapting imagenet to art epoch classification

  2016cited by this paper
• From impressionism to expressionism: Automatically identifying van Gogh's paintings

  2016cited by this paper
• Deep Residual Learning for Image Recognition

  2015influential reference
• Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature

  2015cited by this paper
• Rethinking the Inception Architecture for Computer Vision

  2015influential reference
• ImageNet Large Scale Visual Recognition Challenge

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014influential reference
• Painting-91: a large scale database for computational painting categorization

  2014cited by this paper
• Going deeper with convolutions

  2014influential reference
• Recognizing Image Style

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012influential reference
• Towards automated classification of fine-art painting style: A comparative study

  2012cited by this paper
• Impressionism, expressionism, surrealism: Automated recognition of painters and schools of art

  2010cited by this paper
• The classification of style in fine-art painting

  2005cited by this paper

• DAVA: Decoding Art With Visual Analytics Through Feature Modeling and Multi-Agent Collaboration

  2026cites this paper
• From image processing to artificial intelligence-driven tools: A comprehensive survey on the evolution of feature extraction methods in paintings

  2025cites this paper
• A survey of computational techniques for fine art painting classification

  2025cites this paper
• Evaluation of CNN Models with Transfer Learning in Art Media Classification in Terms of Accuracy and Class Relationship

  2024cites this paper
• Measuring Style Similarity in Diffusion Models

  2024cites this paper
• Gesture Classification in Artworks Using Contextual Image Features

  2024cites this paper
• Classification of painting styles based on the difference component

  2024cites this paper
• An Artificial Intelligence System for Automatic Recognition of Punches in Fourteenth-Century Panel Painting

  2023cites this paper
• Proposals Generation for Weakly Supervised Object Detection in Artwork Images

  2022cites this paper
• Learning and Reasoning for Cultural Metadata Quality: Coupling Symbolic AI and Machine Learning over a Semantic Web Knowledge Graph to Support Museum Curators in Improving the Quality of Cultural Metadata and Information Retrieval

  2022cites this paper
• How deep is your art: An experimental study on the limits of artistic understanding in a single-task, single-modality neural network

  2022cites this paper
• Recognizing the style of a fine-art painting with EfficientNet and Transfer learning

  2022cites this paper
• Image recommender system based on compact convolutional transformer image style recognition

  2022cites this paper
• Leveraging Computer Vision Application in Visual Arts: A Case Study on the Use of Residual Neural Network to Classify and Analyze Baroque Paintings

  2022cites this paper
• Improving art style classification with synthetic images from self-attention generative adversarial network.

  2022cites this paper
• Learning and Reasoning for Cultural Metadata Quality

  2022cites this paper
• A deep-learning framework for human perception of abstract art composition

  2021cites this paper
• ARTificial intelligence raters: Neural networks for rating pictorial expression

  2021cites this paper
• Artificial Neural Networks and Deep Learning in the Visual Arts: a review

  2021cites this paper
• How to Generate Synthetic Paintings to Improve Art Style Classification

  2021cites this paper
• Discovering artistic influences of painters from expressionism, impressionism, and surrealism art movements using convolutional neural network

  2021cites this paper
• Hierarchical classification of fine-art paintings using deep neural networks

  2020cites this paper
• Classification of Fine-Art Paintings with Simulated Partial Damages

  2020cites this paper
• Deep Ensemble Art Style Recognition

  2020influential citation
• OmniEyes: Analysis and Synthesis of Artistically Painted Eyes

  2019cites this paper
• Two-Stage Deep Learning Approach to the Classification of Fine-Art Paintings

  2019cites this paper