Residual context refinement network architecture for optical character recognition
US11308354B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 30, 2020 |
| Grant date | Apr 19, 2022 |
| Priority date | — |
| Expiry date | Jun 13, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/18057
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual feature sequence from the extracted features; performing selective contextual refinement at least one selective contextual refinement block of a stack of selective contextual refinement blocks to generate a text prediction by: generating a contextual feature map and combining the contextual feature map with the visual feature sequence into a visual feature space, and applying a selective decoder that utilizes a two-step attention on the visual feature space to generate a text prediction, wherein the two-step attention includes performing a 1-D self-attention computation to generate attentional features and decoding the attentional features to generate the text prediction; and outputting the generated text prediction.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.