Identifying image transformations for improving optical character recognition quality
US-2016092754-A1 · Mar 31, 2016 · US
US10095946B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10095946-B2 |
| Application number | US-201615204419-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 7, 2016 |
| Priority date | Jul 7, 2016 |
| Publication date | Oct 9, 2018 |
| Grant date | Oct 9, 2018 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
The present disclosure is directed to systems and methods for strike through detection and, more particularly, to systems and methods for detecting a strike through in an address block of a mailpiece. The method is implemented in a computing device and includes: generating edges of lines within a text block identified through optical character recognition processes; locating text lines within the text block; characterizing the edges within the text lines and outside of the text lines; and grouping identified edges of the characterized edges outside of the text lines into co-linear groups.
Opening claim text (preview).
What is claimed is: 1. A method implemented in a computing device, comprising: generating edges of lines within a text block identified through optical character recognition processes; locating text lines within the text block; identifying each of the edges outside of the text lines as strike through; grouping the identified edges outside of the text lines into co-linear groups comprising at least the strike through; and identifying, as the strike through, edges within the text lines that extend from the identified edges outside of the text lines. 2. The method of claim 1 , further comprising excluding any edges or groups above a certain threshold from being identified as the strike through, and identifying the edges or groups above the certain threshold as text. 3. The method of claim 1 , further comprising adjusting the text lines both vertically and horizontally prior to the identifying. 4. The method of claim 3 , further comprising grouping the identified edges within the text lines with the edges in the co-linear groups comprising at least the strike through. 5. The method of claim 4 , wherein the lines within the text lines that do not extend from the identified edges outside of the text lines are identified as text. 6. The method of claim 1 , wherein the edges within the text lines that do not extend from the identified edges outside of the text lines are identified as text. 7. The method of claim 1 , further comprising generating a report of an identified strike through in the text block. 8. The method of claim 1 , wherein the text block is an address block of a mailpiece. 9. The method of claim 1 , wherein the edges are white to black or black to white transitions that are spatially related. 10. A computer program product for identifying a strike through in an address block, the computer program product comprising program code embodied in a computer-readable storage medium, the program code is readable/executable by a computing device to: obtain an address block with accompanying information using optical character recognition processes; detect edges of all marks within the address block; locate text lines within the address block; adjust the text lines both vertically and horizontally; identify each of the edges outside of the text lines as the strike through; and group together the identified strike through and additional edges within the text lines which extend from the identified strike through in a substantially same direction, and exclude edges that are above a certain threshold as text within the text lines. 11. The computer program product of claim 10 , wherein the detecting the edges of all marks including detecting transition between white to black or black to white that are spatially related. 12. The computer program product of claim 11 , wherein the edges will disconnect the strike through from the text. 13. The computer program product of claim 11 , wherein the identifying the edges includes identifying edges within the text lines and outside of the text lines. 14. The computer program product of claim 13 , wherein the edges within the text lines are mainly excluded. 15. The computer program product of claim 10 , wherein the edges are invariant to connectivity such that edge domains remain relatively constant in connected text and lightly broken text. 16. The computer program product of claim 10 , wherein the groups are co-linear groups representing a strike through. 17. The computer program product of claim 16 , wherein the co-linear groups span at least one text line and between the text lines. 18. A system comprising: a hardware processor, a computer readable memory and a computer readable storage medium associated with a computing device; program instructions to obtain an address block with accompanying information using optical character recognition processes; program instructions to detect edges of all marks within the address block; program instructions to adjust text lines both vertically and horizontally; program instructions to identify each of the edges outside of the text lines as strike through; and program instructions to group together the edges that are identified as the strike through, wherein the program instructions are stored on the computer readable storage medium for execution by the hardware processor via the computer readable memory. 19. The system of claim 18 , wherein: the detecting the edges includes detecting a transition between white to black or black to white that are spatially related; the identifying the edges includes identifying edges within the text lines and outside of the text lines; the groups are co-linear groups representing a strike through spanning at least one text line and between the text lines. 20. The system of claim 18 , wherein the edges are invariant to connectivity such that edge domains remain relatively constant in connected text and lightly broken text.
by analysing segments intersecting the pattern · CPC title
Inclination or skew detection or correction of characters or of image to be recognised · CPC title
Postal images, e.g. labels or addresses on parcels or postal envelopes · CPC title
using recognition of characters or words · CPC title
Document-oriented image-based pattern recognition · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.