Synthetic Medical Prescription OCR Dataset

Synthetic images of medical prescriptions comprise this dataset, which is designed for Optical Character Recognition (OCR) and document analysis. The collection simulates realistic healthcare documents featuring multiple medicine entries per page to support model training without privacy risks.

Use Cases

• Training OCR models to recognize specific medicine names within a prescription layout
• Developing document layout analysis algorithms to segment headers from medicine lists
• Testing text extraction pipelines on multi-line medical orders

Strengths

• Synthetic generation ensures zero risk of exposing Protected Health Information (PHI)
• Simulates complex layouts with multiple medicine entries per document
• Targeted specifically for medical-domain OCR tasks

Limitations

• Synthetic nature may not capture the full range of real-world handwriting variability or physical document degradation
• Lack of documented record count or ground truth format makes initial assessment difficult

Provenance

Collection Method

synthetic