Recent advancements in the area of Optical Character Recognition (OCR) using deep learning techniques made it possible to use for real world applications with good accuracy. In this paper we present a system named as OCRXNet. OCRXNetv1, OCRXNetv2 and OCRXNetv3 are proposed and compared on different identity documents. Image processing methods and various text detectors have been used to identify best fitted process for custom ocr of identity documents. We also introduced the end to end pipeline to implement OCR for various use cases.
Copyrights © 2020