Method and apparatus for identifying regions of different content in an image
US7840071B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 12, 2006 |
| Grant date | Nov 23, 2010 |
| Priority date | — |
| Expiry date | Sep 22, 2029 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/413
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of identifying regions of different content in an image comprises dividing image data into a plurality of pixel blocks, extracting features of the pixel blocks and classifying the content of the pixel blocks based on extracted features. Extracting comprises, for each pixel block, convolving a magic square filter with the pixels of the pixel block and summing the results, and calculating the percentage of background pixels in the pixel block. The magic square filter is a 3×3 kernel that has a specific selectivity towards the statistical appearance and geometric alignment of a document based text of various fonts, sizes and styles. The complete sum of the magic square filter, as well as the sum of the rows, columns and diagonals of the magic square filter are zero.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.