Information extraction from images using neural network techniques and anchor words
US11847806B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Jan 20, 2021 |
| Grant date | Dec 19, 2023 |
| Priority date | — |
| Expiry date | Oct 24, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Scene text information extraction of desired text information from an image can be performed and managed. An information management component (IMC) can determine an anchor word based on analysis of an image. To facilitate determining desired text information in the image, IMC can re-orient the image to zero or substantially zero degrees if it determines that the orientation is skewed. IMC can utilize a neural network to determine and apply bounding boxes to text strings in the image. Using a rules-based approach or machine learning techniques, employing a trained machine learning component, IMC can utilize the anchor word along with inline grouping of textual information in the image, deep text recognition analysis, or bounding box prediction to determine or predict the desired text information in the image. IMC can facilitate presenting the desired text information, anchor word, or other information obtained from the image in an editable format.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.