Universe

chess3 Computer Vision Dataset

byHUSTTask:
Object Detection
License:CC BY 4.0135 views10 downloads
See all 400 imageschess3 chess-piece sample showing white-bishopchess3 chess-piece sample showing black-king, black-knight, black-pawn, black-rook, white-bishop, white-king, white-pawn, white-queen, white-rookchess3 chess-piece sample showing white-queenchess3 chess-piece sample showing black-bishopchess3 chess-piece sample showing white-knightchess3 chess-piece sample showing black-king, black-knight, black-pawn, black-rook, white-bishop, white-king, white-pawn, white-queen, white-rookchess3 chess-piece sample showing white-queenchess3 chess-piece sample showing black-knightchess3 chess-piece sample showing black-queenchess3 chess-piece sample showing black-bishopchess3 chess-piece sample showing black-knightchess3 chess-piece sample showing black-knight

About chess3 Dataset

Here are a few use cases for this project:

  1. Chess Game Digitization: The "chess3" model could be used to digitize physical chess games. By taking regular pictures of an ongoing chess game, the AI can interpret the state of the board and digitize the movements for record-keeping, online sharing or analysis purposes.

  2. Chess Coaching: This model can be part and parcel of a chess coaching application where users place their physical board and pieces according to a setup provided by the app. The model can recognize if the user has placed the pieces correctly and give feedback.

  3. Board Game Manufacturing Quality Control: In a board game manufacturing setup, the model could be used to automate quality inspection, identifying whether all the necessary chess pieces are included in the packaged set or not.

  4. Automated Chess Referee: It can be used in a chess competition where it acts as a referee, ensuring that all moves by players are legal and correctly carried out according to the standard chess rules.

  5. Augmented Reality Chess: The model can also be used in an Augmented Reality game, identifying the real-world chess pieces and superimposing virtual effects or information like possible moves, piece history, etc. onto it.

Use Free Black-bishop, Black-king and Black-knight Detection API

Powered by general detection model

Code
pip install inference-sdk
# 1. Import the library
from inference_sdk import InferenceHTTPClient

# 2. Connect to your workspace
client = InferenceHTTPClient(
  api_url="https://serverless.roboflow.com",
  api_key="API_KEY"
)

# 3. Run your workflow on an image
result = client.run_workflow(
  workspace_name="<YOUR_WORKSPACE>",
  workflow_id="<YOUR_WORKFLOW_ID>",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  parameters={
    "classes": "black-bishop, black-king, black-knight, black-pawn, black-queen"
  },
  use_cache=True  # cache workflow definition for 15 minutes
)

# 4. Get your results
print(result)

Run on custom image

Drop an image here or click to upload

Detecting classes:
Or try a test image 

Cite This Project

LicenseCC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{ chess3-xo7ei_dataset,
  title = { chess3 Dataset },
  type = { Open Source Dataset },
  author = { HUST },
  howpublished = { \url{ https://universe.roboflow.com/hust-a0h9q/chess3-xo7ei } },
  url = { https://universe.roboflow.com/hust-a0h9q/chess3-xo7ei },
  journal = { Roboflow Universe },
  publisher = { Roboflow },
  year = { 2025 },
  month = { oct },
  note = { visited on 2026-07-29 },
}

Similar Projects

See More