Universe

ETDs70-90 Computer Vision Dataset

bynew-workspace-nt9bxTask:
Object Detection
License:Public Domain91 views
See all 3.3k imagesETDs70-90 Metadata sample showing Chapter Title, paragraphETDs70-90 Metadata sample showing Chapter Title, paragraphETDs70-90 Metadata sample showing foot note, page number, paragraphETDs70-90 Metadata sample showing Chapter Title, page number, paragraphETDs70-90 Metadata sample showing page number, paragraphETDs70-90 Metadata sample showing figure, page numberETDs70-90 Metadata sample showing page number, paragraphETDs70-90 Metadata sample showing figure, figure captionETDs70-90 Metadata sample showing foot note, page number, paragraphETDs70-90 Metadata sample showing foot note, page number, paragraphETDs70-90 Metadata sample showing Chapter Title, paragraphETDs70-90 Metadata sample showing foot note, page number, paragraph

About ETDs70-90 Dataset

Here are a few use cases for this project:

  1. Academic Research: The ETDs70-90 model could be used by scholars and researchers to find specific metadata elements from a repository of academic papers and dissertations. This could significantly speed up the literature review process by swiftly identifying relevant academic texts.

  2. Bibliographical Management Tools: This model could be integrated into citation management software, making it easier to automatically generate bibliographies by identifying key information such as authors, dates, titles, and universities directly from academic resources.

  3. AI-Based Reading Assistance: Educational technology platforms could utilize this model to help students with physical or learning disabilities. By identifying and reading out metadata classes such as paragraph text, equations, and footnotes, the tool can make educational content more accessible.

  4. Academic Search Engines: The ETDs70-90 model could improve academic search engines by categorizing and indexing papers more accurately, enhancing the efficiency and precision of search results. It could also assist in eliminating duplicate entries in the repository.

  5. Automated Content Creator: In publishing industry, this model can help automate the creation of tables of contents, lists of figures or tables, or indexes by accurately identifying and categorizing the relevant metadata classes. This could significantly reduce the time and effort required to prepare a book or a research paper for publication.

Use Free Table, Date and Title 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": "table, date, Title, abstract heading, abstract text"
  },
  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

LicensePublic Domain

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

@misc{ etds70-90_dataset,
  title = { ETDs70-90 Dataset },
  type = { Open Source Dataset },
  author = { new-workspace-nt9bx },
  howpublished = { \url{ https://universe.roboflow.com/new-workspace-nt9bx/etds70-90 } },
  url = { https://universe.roboflow.com/new-workspace-nt9bx/etds70-90 },
  journal = { Roboflow Universe },
  publisher = { Roboflow },
  year = { 2022 },
  month = { apr },
  note = { visited on 2026-07-29 },
}

Similar Projects

See More