This project contains source code and supporting files for a serverless application that extracts text from documents using AWS Textract. The application can be deployed with the SAM CLI and includes ...

pytesseract: Interface Python para o Tesseract OCR. pillow: Biblioteca de processamento de imagens. pdf2image: Converte PDFs em imagens para poder aplicar o OCR. boto3: Biblioteca da AWS para ...

AWS' Textract, which leverages machine learning algorithms to detect and extract text and data from a range of document types, is now generally available.

Amazon Textract gained support for handwriting recognition in English, as well as new languages, including Spanish and German.

Amazon says no machine learning expertise is needed to use the to use the service, which automatically extracts text and data from tables or forms.