Table grid detection and separation
AssigneeDigital Business Processes, Inc.
InventorHuanfeng Ma
Life of this patent
Estimating the term…
Abstract
A technique is described for table grid detection and separation during the analysis and recognition of documents containing table contents. The technique includes the steps of table detection, grid separation, and table cell extraction. The technique is characterized by the steps of detecting the grid lines of a table using, for example, inverse cell detection, separating noise and touching text from the grid lines, and extracting the cell contents for OCR recognition.
Claims63
A computer-implemented method for detecting a table grid in a received digital document and extracting the table grid from the received digital document, comprising:
- extracting connected components from the received digital document to identify table grid candidates;
- extracting inverse cells from said table grid candidates;
- extracting grid line components from said table grid candidates;
- validating the grid line components as belonging to a table grid;
- and
- extracting regular cells from said validated grid line components.
A computer-implemented method for detecting a table grid in a received digital document and extracting the table grid from the received digital document, comprising:
- extracting connected components from the received digital document to identify table grid candidates;
- extracting grid line components from said table grid candidates;
- validating the grid line components as belonging to a table grid;
- separating noise, graphics, handwriting, and/or touching text from validated grid line components;
- and
- extracting regular cells from said validated grid line components.
A system for detecting a table grid in a received digital document and extracting the table grid from the received digital document, comprising:
- a memory that stores a received digital document for processing;
- and
- a processor that extracts connected components from the received digital document to identify table grid candidates, extracts inverse cells from said table grid candidates, extracts grid line components from said table grid candidates, validates the grid line components as belonging to a table grid, and extracts regular cells from said validated grid line components.
A system for detecting a table grid in a received digital document and extracting the table grid from the received digital document, comprising:
- a memory that stores a received digital document for processing;
- and
- a processor that extracts connected components from the received digital document to identify table grid candidates, extracts grid line components from said table grid candidates, validates the grid line components as belonging to a table grid, separates noise, graphics, handwriting, and/or touching text from validated grid line components, and extracts regular cells from said validated grid line components.
A computer readable storage medium containing instructions stored thereon that when processed by a processor implements method for detecting a table grid in a received digital document and extracting the table grid from the received digital document by:
- extracting connected components from the received digital document to identify table grid candidates;
- extracting inverse cells from said table grid candidates;
- extracting grid line components from said table grid candidates;
- validating the grid line components as belonging to a table grid;
- and
- extracting regular cells from said validated grid line components.
A computer readable storage medium containing instructions stored thereon that when processed by a processor implements method for detecting a table grid in a received digital document and extracting the table grid from the received digital document by:
- extracting connected components from the received digital document to identify table grid candidates;
- extracting grid line components from said table grid candidates;
- validating the grid line components as belonging to a table grid;
- separating noise, graphics, handwriting, and/or touching text from validated grid line components;
- and
- extracting regular cells from said validated grid line components.
Dependencies are inferred from the claim text.