Preprocessing images for OCR using character pixel height estimation and cycle generative adversarial networks for better character recognition
US11176410B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 27, 2019 |
| Grant date | Nov 16, 2021 |
| Priority date | — |
| Expiry date | Oct 27, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A text extraction computing method that comprises calculating an estimated character pixel height of text from a digital image. The method may scale the digital image using the estimated character pixel height and a preferred character pixel height. The method may binarizes the digital image. The method may remove distortions using a neural network trained by a cycle GAN on a set of source text images and a set of clean text images. The set of source text images and clean text images are unpaired. The source text images may be distorted images of text. Calculating the estimated character pixel height may include summarizing the rows of pixels into a horizontal projection, and determining a line-repetition period from the projection, and quantifying the portion of the line-repetition period that corresponds to the text as the estimated character pixel height. The method may extract characters from the digital image using OCR.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.