Line-Detection-UrduOCR Object Detection Dataset and Pre-Trained Model by UrduOCR

Images

1500 images

Explore Dataset

Here are a few use cases for this project:

Automated Urdu Literature Analysis: This model can be utilized in literature study, where it would scan physical texts of Urdu literature, detect lines and then with a subsequent OCR, extract and digitize the data for further analysis.
Urdu Manuscript Digitization: Historical Urdu manuscripts that need preservation can be scanned, with this model identifying lines and then an OCR tool converting those lines into digital formats to help create a digital library.
Urdu Exam Paper Corrections: Schools and universities could utilize the Line-Detection-UrduOCR model to digitally assess handwritten or printed Urdu test papers, reducing the grading workload of teachers.
Urdu Newspapers Digitization: To transform printed Urdu newspapers or magazines into digital versions, the CV model can detect lines to structure the information correctly in a digital format.
Assisting Visually Impaired: The model can be used in an app that assists visually impaired persons by scanning Urdu texts, identifying lines, and subsequently converting them into audio using a text-to-speech solution.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite this Project

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

@misc{ line-detection-urduocr_dataset,
    title = { Line-Detection-UrduOCR Dataset },
    type = { Open Source Dataset },
    author = { UrduOCR },
    howpublished = { \url{ https://universe.roboflow.com/urduocr/line-detection-urduocr } },
    url = { https://universe.roboflow.com/urduocr/line-detection-urduocr },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2023 },
    month = { jun },
    note = { visited on 2023-12-01 },
}