Summary: The article compares six AI OCR tools: AWS Textract, Microsoft Azure Document Intelligence, Google Cloud Document AI, Rossum.ai, Super.ai and Eden.ai. It then does a deep comparison between Azure and Google, the two leading choices, in several aspects: initial setup, auto labelling data, text detection and recognition, custom labelling, auto-label accuracy, auto-label result verification, data training speed, data regions and compliance. The article concludes that Azure is the better choice.
For a project I’m working on, we are looking at different AI OCR (Optical Character Recognition) options that would allow us to import documents with various layouts and extract relevant data from them with high enough accuracy. Due to the nature of these documents and the information contained in them, it is paramount that there would be an easy way for us to train the AI models using our documents.
Without revealing exactly what types of documents we are working with, as they’re commercially sensitive, the basic premise is to: