Need of benchmark data set with even distribution to evaluate our current OCR model.
Key Concepts
Benchmark dataset: The dataset is used as a reference point for performance evaluation.
OCR: Optical Character Recognition.
Context
Need of a benchmark data set to evaluate the OCR model with even distribution including printing modes, source of image or pdf(organization name). Creating such data set would give us a clear understanding of where the model underperforms and counter measures could be taken to improve the model.
Outputs
A line to text image with data with even distribution.
RFW0133: Creating a benchmark dataset for OCR
Summary
Need of benchmark data set with even distribution to evaluate our current OCR model.
Key Concepts
Benchmark dataset: The dataset is used as a reference point for performance evaluation. OCR: Optical Character Recognition.
Context
Need of a benchmark data set to evaluate the OCR model with even distribution including printing modes, source of image or pdf(organization name). Creating such data set would give us a clear understanding of where the model underperforms and counter measures could be taken to improve the model.
Outputs
A line to text image with data with even distribution.
Inputs
OpenPecha-Data OpenPecha-Data catalog
Timeline
Specify the expected delivery date for the project.
References
Include any relevant links or resources for additional context or information.