Patent US4453067A successfully refreshed from Google Patents.
Patent US6360010B1 successfully refreshed from Google Patents.
← Back to Patent Explorer
US6360010B1 Expired / Lapsed US ⏱️ 0.0 years remaining

E-mail signature block segmentation

Assignee: Alcatel Lucent SAS
•
Filing: 1998-08-12
•
Granted: 2002-03-19
•
Expires: 2018-08-12
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A technique for segmenting a loosely constrained text block, such as an e-mail signature block into sub-blocks by performing line segment extraction and connected component analysis on the foreground characters and background characters and recursively repeating connected component analysis on both the foreground and background characters and line segment extraction on the background characters until a text output includes no mixed reading blocks. A technique for correcting over segmentation errors in a line of text from a loosely constrained text block which has undergone geometrical analysis.

Inventors

  • 👤 Jianying Hu
  • 👤 Richard W. Sproat
  • 👤 Hao Chen

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-05 18:44
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40; G06V30/41; G06V30/416; G06V30/10; G06V30/19; G06V30/196; G06V30/1983; G06V30/1985; G06V30/414

Claims Analysis

Total Claims: 12
Claim 1
Independent Claim 99 words
A method of dividing a loosely constrained text block into reading blocks, comprising the steps of: (a) performing line segment extraction on foreground characters in the loosely constrained text block; (b) performing connected component analysis on the foreground characters in the loosely constrained text block; (c) performing line segment extraction on background characters in the loosely constrained text block; (d) performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; and (e) recursively repeating said steps (b)-(d) until the text output of said step (d) includes no mixed reading blocks.
Claim 2
Independent Claim 99 words
A method of dividing a loosely constrained text block into reading blocks, comprising the steps of: (a) performing line segment extraction on foreground characters in the loosely constrained text block; (b) performing connected component analysis on the foreground characters in the loosely constrained text block; (c) performing line segment extraction on background characters in the loosely constrained text block; (d) performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; and (e) recursively repeating said steps (b)-(d) until the text output of said step (d) includes no mixed reading blocks.
Claim 3
Dependent Claim 19 words
The method of claim 1 , wherein said method is part of a preprocess performed in e-mail text-to-speech rendering.
Claim 4
Dependent Claim 18 words
The method of claim 1 , wherein the loosely constrained text block is an e-mail message signature block.
Claim 5
Dependent Claim 151 words
A processor for dividing a loosely constrained text block into reading blocks, comprising: a foreground line segment extraction processing unit for performing line segment extraction on foreground characters in the loosely constrained text block; a foreground connected component analysis processing unit for performing connected component analysis on the foreground characters in the loosely constrained text block; a background line segment extraction processing unit for performing line segment extraction on background characters in the loosely constrained text block; and a background connected component processing unit for performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; wherein said foreground connected component analysis processing unit, said background line segment extraction processing unit, and said background connected component analysis processing unit recursively process the loosely constrained text block until the text output of said background connected component analysis processing unit includes no mixed reading blocks.
Claim 6
Dependent Claim 151 words
A processor for dividing a loosely constrained text block into reading blocks, comprising: a foreground line segment extraction processing unit for performing line segment extraction on foreground characters in the loosely constrained text block; a foreground connected component analysis processing unit for performing connected component analysis on the foreground characters in the loosely constrained text block; a background line segment extraction processing unit for performing line segment extraction on background characters in the loosely constrained text block; and a background connected component processing unit for performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; wherein said foreground connected component analysis processing unit, said background line segment extraction processing unit, and said background connected component analysis processing unit recursively process the loosely constrained text block until the text output of said background connected component analysis processing unit includes no mixed reading blocks.
Claim 7
Dependent Claim 19 words
The processor of claim 4 , wherein said processor is part of a preprocessor performed in e-mail text-to-speech rendering.
Claim 8
Dependent Claim 18 words
The processor of claim 4 , wherein the loosely constrained text block is an e-mail message signature block.
Claim 9
Dependent Claim 165 words
A computer program embodied on a computer-readable medium for dividing a loosely constrained text block into reading blocks, comprising: a foreground line segment extraction source code segment for performing line segment extraction on foreground characters in the loosely constrained text block; a foreground connected component analysis source code segment for performing connected component analysis on the foreground characters in the loosely constrained text block; a background line segment extraction source code segment for performing line segment extraction on background characters in the loosely constrained text block; and a background connected component analysis source code segment performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; wherein said foreground connected component analysis source code segment, said background line segment extraction source code segment, and said background connected component analysis source code segment recursively process the loosely constrained text block until the text output of said background connected component analysis source code segment includes no mixed reading blocks.
Claim 10
Dependent Claim 165 words
A computer program embodied on a computer-readable medium for dividing a loosely constrained text block into reading blocks, comprising: a foreground line segment extraction source code segment for performing line segment extraction on foreground characters in the loosely constrained text block; a foreground connected component analysis source code segment for performing connected component analysis on the foreground characters in the loosely constrained text block; a background line segment extraction source code segment for performing line segment extraction on background characters in the loosely constrained text block; and a background connected component analysis source code segment performing connect component analysis on the background characters in the loosely constrained text block to produce a text output; wherein said foreground connected component analysis source code segment, said background line segment extraction source code segment, and said background connected component analysis source code segment recursively process the loosely constrained text block until the text output of said background connected component analysis source code segment includes no mixed reading blocks.
Claim 11
Dependent Claim 19 words
The computer program of claim 7 , wherein said computer program is a preprocess performed in e-mail text-to-speech rendering.
Claim 12
Dependent Claim 19 words
The computer program of claim 7 , wherein the loosely constrained text block is an e-mail message signature block.

References Cited (Backward Citations)

US5631984A Cited
US5781884A Cited
US6021202A Cited
US5892843A Cited
US6061718A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2005-03-18 2005-09-17 2006-03-19 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2009-03-18 2009-09-17 2010-03-19 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2013-03-18 2013-09-17 2014-03-19 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag