Correcting text input by machine translation and classification

“person holding eyeglasses” by David Travis on Unsplash

Recently, I am working on a Optical Character Recognition (OCR) related project. On of the challenge is that pre-trained OCR model output incorrect text. Besides the performance of OCR model, image quality and layout alignment are other major source to text error.

After reading this post, you will understand:

• Optical Character…