Universe

wx_3 Computer Vision Dataset

bywx_dlTask:
Object Detection
License:CC BY 4.096 views8 downloads
See all 1.1k imageswx_3 metal sample showing heiyin, keceng, scratchwx_3 metal sample showing heiyin, keceng, scratchwx_3 metal sample showing scratchwx_3 metal sample showing heiyin, scratchwx_3 metal sample showing heiyin, scratchwx_3 metal sample showing keceng, scratchwx_3 metal sample showing scratchwx_3 metal sample showing heiyin, scratchwx_3 metal sample showing scratchwx_3 metal sample showing heiyin, scratchwx_3 metal sample showing keceng, scratchwx_3 metal sample showing keceng, scratch

About wx_3 Dataset

Here are a few use cases for this project:

  1. Quality Control in Manufacturing: The "wx_3" model could be useful in automating the quality inspection process in manufacturing industries. It can alert personnel when the detected metal class or defects (scratch, heiyin, keceng) do not meet the acceptance criteria.

  2. Scrap Metal Sorting: The identification of different metal classes can aid in automated sorting of scrap metal, improving speed and accuracy and reducing manual work in recycling facilities.

  3. Artifact Examination: Museums or archeological institutions might use the model to analyze metallic artifacts. It could help detect signs of wear and tear such as scratches or other imperfections and aid in categorizing the items based on the metal class.

  4. Automotive Industry: Within the car manufacturing and maintenance sector, the "wx_3" model could be used to detect and classify damage in the metal parts of the vehicles.

  5. Machinery Maintenance: In industries where heavy machinery is used, the model could be used to predict machinery failure by detecting and classifying signs of deterioration on the machinery's metal components.

Use Free Scratch, Heiyin and Keceng 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": "scratch, heiyin, keceng"
  },
  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{ wx_3_dataset,
  title = { wx_3 Dataset },
  type = { Open Source Dataset },
  author = { wx_dl },
  howpublished = { \url{ https://universe.roboflow.com/wx_dl/wx_3 } },
  url = { https://universe.roboflow.com/wx_dl/wx_3 },
  journal = { Roboflow Universe },
  publisher = { Roboflow },
  year = { 2022 },
  month = { jul },
  note = { visited on 2026-07-29 },
}

Similar Projects

See More