The IDA (Intelligent Document Analysis) software suite claims to offer outstanding Optical Character Recognition (OCR) accuracy by leveraging patented core technology, thereby minimizing the risk of “garbage in, garbage out”. This white paper is intended to serve as a benchmark for comparing commercial and open-source OCR solutions.

Open-source Engines: easyOCR, MMOCR, PaddleOCR, Tesseract

Commercial Engines: Amazon, Azure, Google, IDA (PLANET AI)

Visual-based Engines: GPT4 Vision Preview (OpenAI)

By downloading the OCR Benchmark, you gain access to the 15-page white paper with the results. If you are interested in the dataset of 200 documents, please feel free to contact us.