NOAA has used historical documents such as ship logs and many other resources to collect weather data critical to modeling global and regional climate and weather conditions

The National Oceanic and Atmospheric Administration (NOAA) awarded a $149,882 Small Business Innovation Research (SBIR) Program Project Grant to the International Association of Virtual Organizations, Incorporated doing business as Iavo Research and Scientific.

Under this award, Iavo Research and Scientific will develop and test a custom optical character recognition and text extraction application using OpenCV, Tesseract, and PyTorch. The application aims to improve NOAA's ability to recognize handwritten text and reliably extract data from historical documents such as ship logs. These documents contain weather data critical to modeling global and regional climate and weather conditions. The proposed integration of OpenCV, Tesseract and PyTorch is intended to provide more flexible pre-processing without undue complexity, require less post-processing, and establish an automation framework. The period of performance for this NOAA SBIR Program Project Grant is from September 1, 2021 through February 28, 2022 in Durham, North Carolina.

To date, the optical character recognition (OCR) technology developed over the past three decades remains limited in the ability to recognize handwriting and reliably extract text in context. Machine learning (ML) algorithms can help improve the processes. Given the importance of accuracy for weather data, we propose the development and testing of a custom OCR/text extraction application built using opencv and tesseract. Both are open-source and operate within the open-source python environment. Pytorch will be evaluated as the deep learning library to optimize the opencv and tesseract integration and post processing. We submit that this integration will provide more flexible pre-processing without undue complexity and understanding, require less post-processing, and establish a framework to add automation to pre/