Skip to content
intermediateimage

WikiArt Artwork Classification

Art classification by style, genre, and artist (Saleh & Elgammal, 2015). Classify paintings into artistic movements, genres, and predict artist attribution.

Labels:outdoornatureurbanpeopleanimal+−

Configuration Fileconfig.yaml

This Potato config reproduces the annotation task. Save it as config.yaml and run potato start config.yaml to try it.

yaml
# WikiArt Artwork Classification Configuration
# Based on Saleh & Elgammal, 2015

annotation_task_name: "WikiArt Art Classification"
task_dir: "."

data_files:
  - "sample-data.json"

item_properties:
  id_key: "id"
  text_key: "image_url"
  context_key: "context"

user_config:
  allow_all_users: true

annotation_schemes:
  - annotation_type: "radio"
    name: "art_style"
    description: "Select the artistic style/movement"
    labels:
      - name: "impressionism"
        tooltip: "Impressionism (Monet, Renoir)"
      - name: "post_impressionism"
        tooltip: "Post-Impressionism (Van Gogh, Cézanne)"
      - name: "expressionism"
        tooltip: "Expressionism (Munch, Kandinsky)"
      - name: "cubism"
        tooltip: "Cubism (Picasso, Braque)"
      - name: "surrealism"
        tooltip: "Surrealism (Dalí, Magritte)"
      - name: "abstract"
        tooltip: "Abstract Art"
      - name: "romanticism"
        tooltip: "Romanticism"
      - name: "realism"
        tooltip: "Realism"
      - name: "renaissance"
        tooltip: "Renaissance"
      - name: "baroque"
        tooltip: "Baroque"
      - name: "pop_art"
        tooltip: "Pop Art"
      - name: "minimalism"
        tooltip: "Minimalism"
      - name: "other"
        tooltip: "Other style"

  - annotation_type: "radio"
    name: "genre"
    description: "Select the painting genre"
    labels:
      - name: "portrait"
        tooltip: "Portrait"
      - name: "landscape"
        tooltip: "Landscape"
      - name: "still_life"
        tooltip: "Still Life"
      - name: "religious"
        tooltip: "Religious/Mythological"
      - name: "historical"
        tooltip: "Historical painting"
      - name: "genre_scene"
        tooltip: "Genre scene (everyday life)"
      - name: "abstract"
        tooltip: "Abstract/non-representational"
      - name: "cityscape"
        tooltip: "Cityscape/urban"
      - name: "nude"
        tooltip: "Nude"
      - name: "animal"
        tooltip: "Animal painting"

  - annotation_type: "multiselect"
    name: "visual_elements"
    description: "Select dominant visual elements"
    labels:
      - name: "bold_colors"
        tooltip: "Bold, vibrant colors"
      - name: "muted_colors"
        tooltip: "Muted, subtle colors"
      - name: "geometric"
        tooltip: "Geometric shapes"
      - name: "organic"
        tooltip: "Organic, flowing forms"
      - name: "high_contrast"
        tooltip: "High contrast"
      - name: "soft_focus"
        tooltip: "Soft, blurred edges"
      - name: "detailed"
        tooltip: "Fine detail"
      - name: "loose_brushwork"
        tooltip: "Loose, visible brushwork"

  - annotation_type: "radio"
    name: "era"
    description: "Estimated era"
    labels:
      - name: "pre_1500"
        tooltip: "Before 1500 (Medieval, Early Renaissance)"
      - name: "1500_1700"
        tooltip: "1500-1700 (Renaissance, Baroque)"
      - name: "1700_1850"
        tooltip: "1700-1850 (Rococo, Neoclassicism)"
      - name: "1850_1945"
        tooltip: "1850-1945 (Modern Art)"
      - name: "post_1945"
        tooltip: "After 1945 (Contemporary)"

  - annotation_type: "text"
    name: "artist_guess"
    description: "Artist attribution guess (if recognizable)"

interface_config:
  item_display_format: "<img src='{{text}}' style='max-width:100%; max-height:500px;'/><br/><small>{{context}}</small>"

output_annotation_format: "json"
output_annotation_dir: "annotations"

Sample Datasample-data.json

json
[
  {
    "id": "art_001",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg/1200px-Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg",
    "context": "Classify this artwork by style, genre, visual elements, and era."
  },
  {
    "id": "art_002",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/6/66/VanGogh-starry_night_ballance1.jpg/1200px-VanGogh-starry_night_ballance1.jpg",
    "context": "Art classification task. Identify the artistic movement and genre."
  }
]

// ... and 1 more items

Get This Design

View on GitHub

Clone or download from the repository

Quick start:

git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/image/specialized/wikiart
potato start config.yaml

Dataset & paper

Saleh & Elgammal, 2015

Official dataset ↗Read the paper ↗

Citation (BibTeX)

bibtex
@article{saleh2015large,
    title = "Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature",
    author = "Saleh, Babak  and Elgammal, Ahmed",
    journal = "arXiv preprint arXiv:1505.00855",
    year = "2015",
    url = "https://arxiv.org/abs/1505.00855"
}

Details

Annotation Types

multiselectradiotext

Domain

Computer VisionArt History

Use Cases

Art ClassificationStyle RecognitionCultural Heritage

Tags

wikiartartpaintingstylegenreartist

Found an issue or want to improve this design?

Open an Issue

Related Designs

CUB-200-2011: Fine-Grained Bird Species Dataset

CUB-200-2011 is a fine-grained bird image dataset of 11,788 photos across 200 species, each labeled with parts, attributes, and a bounding box (Wah et al., 2011). This Potato config reproduces the labeling task.

multiselectradio

FLAIR: French Land Cover from Aerospace Imagery

Land use and land cover classification from high-resolution aerial imagery. Annotators classify the primary land use category of aerial image patches and identify any secondary land uses present. Based on the FLAIR dataset from the French National Institute of Geographic and Forest Information (IGN).

multiselectradio

iWildCam Wildlife Detection & Classification

Camera trap image classification for wildlife monitoring (Beery et al., CVPR 2019). Classify wildlife species from camera trap images across diverse ecosystems worldwide.

multiselectradio