(19) United States
`(12) Patent Application Publication (10) Pub. No.: US 2005/0289182 A1
`(43) Pub. Date:
`Dec. 29, 2005
`Pandian et al.
`
`US 20050289182A1
`
`(54) DOCUMENT MANAGEMENT SYSTEM
`WITH ENHANCED INTELLIGENT
`DOCUMENT RECOGNITION CAPABILITIES
`
`(75) Inventors: Suresh S. Pandian, Cupertino, CA
`(US); Thyagarajan Swaminathan,
`Cupertino, CA (US); Subramaniyan
`Neelagandan, Santa Clara, CA (US);
`Krishna K. Srinivasan, Fremont, CA
`(US); Randal J. Martin, Naples, FL
`(Us)
`
`Correspondence Address:
`NIXON & VANDERHYE, PC
`901 NORTH GLEBE ROAD, 11TH FLOOR
`ARLINGTON, VA 22203 (US)
`
`(73) Assignee: Sand Hill Systems Inc., Sunnyvale, CA
`(Us)
`10/894,338
`
`(21) Appl. No.:
`
`(22) Filed:
`
`Jul. 20, 2004
`
`Related US. Application Data
`
`(60) Provisional application No. 60/579,277, ?led on Jun.
`15, 2004.
`
`Publication Classi?cation
`
`(51) Int. Cl? ................................................... .. G06F 17/00
`(52) US. Cl. ........................................................ .. 707/104.1
`
`ABSTRACT
`(57)
`An intelligent document recognition-based document man
`agement system includes modules for image capture, image
`enhancement, image identi?cation, optical character recog
`nition, data extraction and quality assurance. The system
`captures data from electronic documents as diverse as fac
`simile images, scanned images and images from document
`management systems. It processes these images and presents
`the data in, for example, a standard XML format. The
`document management system processes both structured
`document images (ones Which have a standard format) and
`unstructured document images (ones Which do not have a
`standard format). The system can extract images directly
`from a facsimile machine, a scanner or a document man
`agement system for processing.
`
`Image
`Collaborator
`Server # 1
`
`Image
`Collaborator
`Server # 2
`
`Image
`Collaborator
`Server # n
`
`gangs?) U
`Hub
`
`20
`
`Quality Assurance
`Desktop
`
`_
`
`% .’— 26
`lg
`I:
`:1
`I:
`Eng
`
`Database Server
`
`Line of Business Application
`
`Page 1 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 1 0f 35
`
`US 2005/0289182 A1
`
`/
`
`6
`
`IE1
`Ff?
`lg
`:1
`I:
`[:1
`
`20%
`
`IEEI
`@I
`lg]
`:1
`:1
`:1
`
`‘5.0%
`
`I I I
`
`12
`
`Image
`Collaborator
`Server # 1
`
`Image
`Collaborator
`Server # 2
`
`IE
`I%
`@
`l:
`:1
`I:
`
`50%
`
`18
`
`Image
`Collaborator
`Server # n
`
`Quality Assurance
`Desktop
`
`g 26
`%
`lg
`I:I
`1%
`/ % <i:> %
`z, z,
`50%
`2%:
`
`24
`
`Database Server
`
`Line of Business Application
`
`Figure 1
`Image Collaborator
`Hardware Configuration
`
`Page 2 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 2 0f 35
`
`US 2005/0289182 A1
`
`
`
`@w 2262 9:285 ncm 2968mm 25mm
`
`
`
`
`
`
`
`
`
`mm 063w QEQEQP
`
`
`100 cozmuzzcmg EwEmocmgcw
`
`2282 2262 22.62
`
`mums: ommg
`
`
`
`>595 om vm mm mmmc:
`
`
`R 2352 coaombxw $8
`35252 2298
`
`
`
`Nv ow mm om
`
`
`
`
`
`moms: b23026 mmmc: 85626::
`
`
`
`mEwwwooE mEwwwQoE
`
`<N 22E
`
`S58E60 ommc: 9F
`
`Page 3 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 3 of 35
`
`US 2005/0289182 A1
`
`$m.mn_
`
`
`
`b_E_xo._n_>.m.:o=o_D
`
`
`
`
`
`wemc_mmmoo.n_mE.on_uo._Bo::w
`
`
`
`Fm.2bmE_._9m_aEm._.
`
`NV
`
`
`
`xomgummaxomnoooa
`
`
`:.xomo_Uwmn_Nu2a_E_o8Nu2a_Eo£u8.§_.m__
`
`
`qoo._moommmc:moms.
`canm5c_c;ow._.cum:u_c;om._.
`
`
`
`onSmmmmE_uwocmccm
`
`—.anw:c_ccow.r—.xxm_..c_ccom._.
`
`mm
`
`mm
`
`xomonwwa
`
`2.
`
`mm939“.
`
`
`
`
`
`93oo_.EE<_o..Eonw__o0mmmE_
`
`
`
`
`
`m_muo_>_m>=o_um:n_wEotwoqmmwzzwmm
`
`Page 4 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 4 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 4 0f 35
`
`US 2005/0289182 A1
`
`ww
`
`92: @9200
`
`may
`
`,
`
`
`
`m2... vmxmuE
`
`_
`
`fwo
`
`
`
`>EQ> ucm hooi
`Emu 9:
`
`[6
`
`fa
`
`umNEmooom
`EoEzooQ
`
`
`wocoN vwEowQw
`
`-Ew: Eoc Emu Hogxm
`
`
`
`55582
`66920 $250 on
`
`rs
`
`
`
`
`
`wmmmc: nomwoooa E0:
`
`ow 29.265
`
`m oSmE
`
`Page 5 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 5 of 35
`
`US 2005/0289182 A1
`
`
`
`
`
`mmco_.mo_..._Emv_mmmE_mmmmE_cm_.E:mu_$28mm.mmE_n__m>:_
`
`
`
`
`
`
`
`mmmmE_E_m>c_
`
`5.co=mu__m.>
`
`_w>m_Vm.5m_n_-.$e88Emfie:32...._s_xV9%8%o>
`
`
`
`
`
`_..aEE%_::
`
`mwmmE_
`
`
`
`EoEoocm;:oommE_
`
`8_.8=_E%_-mon_
`
`E
`
`>.::m-Emcozo_Q
`
`
`
`
`
`8:6ucmmmbmcozoficozumtxm_b_.
`
`moE
`
`
`
`wmmmoooamn_m..._o>._mw
`
`
`
`wmmmoooaou_m-Eo__o
`
`
`
`mo_=._s_xnmuomzxwuw=_.m>::
`
`
`
`
`
`mm._m_.Em>Ema
`
`m2
`
`mcozmoiqm
`
`
`
`
`
`
`
`mm:o=__._mooo.__mEom.m;o_mo_EOm_w_n\w,>c_._m%_%._m¢_nmvww....#.._____8
`
`mm
`
`
`
`EmEmo:mr_commmE_
`
`
`
`
`
`
`
`mmmmE_u__m>
`
`
`
`
`
`co__.mo=_Ewc_-9n_co=mu__m>mmmE_5.9.2qzxoaommE_
`
`\22
`
`Page 6 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 6 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`
`
`
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 6 0f 35
`
`US 2005/0289182 A1
`
`105 \
`File
`System
`
`109 \
`—
`API
`
`108
`
`Raw Image
`111
`
`Data Image Not
`Supported
`Valid Supported
`Image
`
`Rejected
`Image
`
`113
`
`Veri?ed Supported
`Image
`
`115
`
`Image
`Enhance
`ment
`
`Pre Identi?cation
`Enhanced Image
`
`117 \
`
`Form
`Identi?cation
`
`119
`
`ScanSoft
`Img
`Enhancement
`
`116
`
`Unstructured and
`Semi-structured
`Forms
`
`Form Fix
`Enhanced
`Image
`
`Identi?ed
`Structured
`Form
`
`Enhanced
`Enhanced Image
`
`118
`
`Save the
`Enhanced
`File
`
`123
`
`Figure 5A
`
`Submitlt Server
`Structured Image
`Processing
`
`Page 7 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 7 0f 35
`
`US 2005/0289182 A1
`
`Doc Speci?c
`Gesture
`
`Doc Specific
`Gesture
`Found for
`all fields
`
`No Doc Speci?c
`Gesture Found for
`either document or
`?eld
`
`145
`
`147
`
`Verified XML
`& Index Files
`
`Unverified
`XML
`
`I
`
`‘
`
`unveri?ed XML /
`\44
`151
`
`< 148
`Verified XML
`§___
`dex Files
`in
`
`Figure 5B
`
`Collation
`
`Page 8 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 8 0f 35
`
`US 2005/0289182 A1
`
`7
`
`Look for a file in the
`image Pickup folder
`
`175
`
`Find one ?
`
`177
`
`181
`
`Is the file a
`TIF image ?
`
`Yes
`
`Process the file for
`image verification
`
`Don't process the file A
`183
`
`Figure 6
`
`Look for a file that needs _\
`~ image verification
`190
`
`Find one '?
`
`192
`
`Does the file
`satisfy the file properties
`for OCR ?
`
`Yes
`
`196 \
`
`Process the file for
`pre-identi?cation
`enhancement
`
`Drop the file in the Invalid Files /_\
`folder for the user to correct
`198
`
`Figure 7
`
`Page 9 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 9 0f 35
`
`US 2005/0289182 A1
`
`Look for a file that needs
`pre-identification
`enhancement
`
`200
`
`Find one ?
`
`202
`
`Preform pre—identi?cation
`enhancement
`l
`Process the file for image
`identi?cation
`
`\
`204
`
`\
`206
`
`gure 8
`
`For every input file
`i
`Match the file against the templates
`
`225
`
`227
`
`Drop the ?le in the
`Unidentified File
`folder
`
`\ 231
`
`Did it match
`one ?
`
`229
`
`Does a
`package exist
`for the file?
`
`Yes
`
`233
`
`Create a package and drop the file in it
`
`(- 235
`Drop the ?le in the
`corresponding folder
`
`237
`
`No
`
`Have all the
`files been
`processed
`'2
`
`239
`
`/_ 241
`Begin post identi?cation enhancement
`
`Figure 9
`
`Page 10 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 10 0f 35
`
`US 2005/0289182 A1
`
`‘————>
`
`For every identified source image
`
`/ 250
`
`V
`Fetch the corresponding zone ?les
`
`/ 252
`
`'
`Apply zone information from the zone ?les
`
`/ 254
`
`256
`/
`
`No
`
`Have all the
`files been
`processed?
`
`258
`/
`Q Stop post Identi?cation enhancement D
`
`_
`Fig u re 1 O
`
`————-—->
`
`_
`For every source image
`
`/ 275
`
`277
`Yes
`
`Is the image
`identi?ed?
`
`/ 279
`
`OCR only the zones
`
`_
`,
`OCR the entire image
`
`/ 281
`
`283
`
`Have all the files
`been processed
`?
`
`Yes
`
`C Stop optical characterreoognition j Figure
`
`285
`
`Page 11 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 11 0f 35
`
`US 2005/0289182 A1
`
`—> For every HTML source ?le
`
`Convert the HTML source ?le into a single string
`
`/ 300
`
`/ 302
`
`l
`l
`l
`
`_
`304
`Write the contents of the <body> tags to a TXT ?le /
`
`Apply the dictionary to the TXT
`files
`
`/ 306
`
`No
`
`Have all the
`?les been
`processed?
`
`308
`
`(Stop dictionary-entry extraction)
`
`/ 310
`
`Figure 12
`
`Page 12 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 12 0f 35
`
`US 2005/0289182 A1
`
`For every TXT ?le
`
`Search lor regular expression pattern for
`document-level key dictionary entry
`
`325
`
`/
`327 /
`
`329
`
`Yes
`
`Document
`level key
`dictionary
`entry found?
`
`V
`Search for regular expression pattern of
`the dictionary entries de?ned from the
`delaull section 0! clues
`
`/ 331
`
`Search tor the regular expression pattern
`of all the other dictionary entries de?ned
`for the speci?c document
`
`339
`
`Yes
`
`W th
`I
`expiissr?iiitiin
`for me dictionary
`entry speci?c to the
`document found?
`
`'
`rilltfé'x’lliiiin
`panem for a
`dictionary entry
`from default section
`oi clues tile?
`
`333
`
`Yes
`
`335
`
`/
`
`Store the dictionary entry and its
`co'respondmg Vaiue '“ a tame
`
`‘
`
`341
`/
`Store nothing against the corresponding
`dictionary entry in the table
`
`343
`
`Table containing
`dictionary entries and
`their corresponding
`extracted values
`
`345 \
`
`Write the dictionary entries and the
`corresponding values lrorn the table in to
`an XML file along with the zone
`coordinates where the data was found
`
`Have all the
`TXT ?les
`been
`processed?
`
`347
`
`NO
`
`349
`
`Figure 13
`
`Stop applying the dictionary
`
`Page 13 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 13 0f 35
`
`US 2005/0289182 A1
`
`351 ‘(
`
`Start
`
`)
`
`353
`
`_
`
`V
`Input the list
`of images
`
`V
`355 \ Sort the Image documents
`Document name / Datetime
`
`V
`
`/ 357
`
`Send each Document through
`FormFix to identify the package
`i
`Image
`recognlzed as
`cover
`?
`
`359
`
`361
`/
`Current package (if exist) is
`completed and store in the ?le
`system
`
`Creates a new package
`based on the Cover
`\
`363
`
`365
`\ Add the documents to the
`current package
`l
`367 \ Save the image into the
`package ?le system
`l
`369 \ Delete the image from Input
`Queue (File System)
`
`371
`
`Are all the
`documents
`processed ’?
`
`373
`
`Figure 14
`Image Batch Splitter
`
`Page 14 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 14 0f 35
`
`US 2005/0289182 A1
`
`375
`
`377
`
`input the
`image
`
`379
`
`Input the
`Enhancement type
`i
`381 \ Read the tbl ?le for Image
`Enhancement
`
`393\ Load the Enhancement
`Section from tbl ?le
`
`‘ l
`
`387 \
`
`Load the Pre-Enhancement
`section from tbl ?le
`
`389 the Options
`Loaded Correctly
`
`NO
`
`395
`
`/ 391
`
`Default: default
`Options de?ned in the
`enhancement lNl
`
`397
`\
`Default: default
`Options de?ned
`in the
`enhancement
`|N|
`
`I
`the OptlOl'lS
`Loaded Correctly
`?
`|————————> Yes
`
`Y
`A
`w
`
`l
`
`399\ Apply the Enhancement
`Options
`
`401
`
`Any Error,
`.
`Exceptlon
`
`7
`
`No
`
`405
`
`"
`End
`
`/ 403
`Log the Error and Pass the
`Error Object to Calllng
`.
`.
`Appllcatlon
`
`Figure 15
`Image Enhancement
`
`Page 15 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 15 0f 35
`
`US 2005/0289182 A1
`
`425
`
`Start
`
`429 Data from OCR
`
`Engine
`
`Synchronous
`.
`Process! ng?
`
`Yes
`
`431
`
`Data from
`Database
`
`‘7
`
`Identify the package
`dictionary
`l
`Fetch the Dictionary
`metadata
`
`/ 433
`
`/ 435
`
`,
`_
`—"-> For each File in the Package
`
`/ 437
`
`No
`
`l
`Apply the relevant
`Extraction Logic
`l
`Save the Data in the
`Package _ Details table
`
`/ 439
`
`/ 441
`
`443
`
`Are all ?les processed ?
`
`Yes
`+
`Save the Consolidated Data / 445
`in the Package Table
`l
`Wait for next Package
`
`/ 447
`
`--
`
`Figure 16
`
`Page 16 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 16 0f 35
`
`US 2005/0289182 A1
`
`450
`
`(
`
`Start
`
`i’
`
`V
`452
`Event from IC that Package has been /
`created
`i
`For each Files in the
`package ‘
`
`454
`
`V
`
`OCR the whole page
`
`/ 456
`
`458
`
`Synchronous Pattern
`Matching?
`
`Yes —>
`
`460
`/
`Send the data to
`Pattern Matching
`Component
`
`No
`
`462
`
`Store Data in the
`Database?
`
`Yes
`+
`Save the data in the
`database
`
`/ 464
`
`V
`
`466
`
`All ?les
`processed?
`
`Yes
`i
`Wait for the next event
`
`/ 468
`
`‘
`End
`
`470
`
`Figure 17
`
`Page 17 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 17 0f 35
`
`US 2005/0289182 A1
`
`mctmF U6 co=mv=m>
`
`115m
`
`Ema v6 cozombxw
`
`“29w
`
`f
`
`
`
`
`
`\wccmto cowmoccg ECE
`
`
`
`Hm Qmuw Ema touxw
`
`K QmHw
`
`2 23mm
`
`
`
`bmcozo? 690
`
`UP $5
`
`820 EQEJQQQ wccwo
`
`
`
`
`
`Page 18 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 18 0f 35
`
`US 2005/0289182 A1
`
`2 23mm
`
`w( 02.. m
`
`amcozui EmEzuoo
`
`23 .32 l g
`
`20a uc?wmooi
`
`55am mmmxomm
`
`
`
`Em 0 SB: 0
`
`.296 0
`
`
`
`“9.5% 5:8.33.
`
`Page 19 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 19 0f 35
`
`US 2005/0289182 A1
`
`cm 9:3
`
`L. __ . i _%_@@mé_..t
`
`
`
`
`
`so: .525 conud. 2E
`
`muaimm
`
`Page 20 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 20 of 35
`
`US 2005/0289182 A1
`
`
`
`.3...aE___§e_.Z3.:o§m9_22o%__8&ms_m_._m.,n__..,._._25&5E=__e..5
`
`
`
`
`
`
`
`8__%m___E%__.Baaoésm9_22o%__8m.mE_$_m8522E.5%._§8oo_n_
`
`
`
`
`
`rm259”.
`
`
`
`....2o_22.Bang.
`
`
`
`wu__a.__u__m>c_.,.3uoo_n_/SmQ{o.Eonm__ouummE_mIwin.ou_o_awe_u__m>c_nm._ocom_
`
`
`
`
`
`_m.___mmmxumm
`
`
`
`
`
`a.__u_B.m__§.=s39%9_%a%__8%E_mxm,.o.0223%..ommE_338gm
`
`
`
`
`
`
`
`-L._u
`
`2339.5EHEEE
`
`
`
`maczuwm:a:mu__n_a<
`
`Page 21 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 21 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 21 of 35
`
`US 2005/0289182 A1
`
`mm939”.
`
`REE
`
`
`
`_nm__m>xmuc_xnm:_zmmco:m.u__n__.._<,_m__cou{B2opo__ouumoE_mIm/UoEo_nm_fi>:02:oumE_
`
`
`
`
`
`
`
`__u.m§mm__u__o_oe.$m.mommms_.m_._9:_n_E_2Bm__on_mmme_$56co_.8_..m_23.2B38
`
`
`
`wmszmmmuo,.mmc_zmmco_.mo__aa.3m=cou{o.23n__ooomoE_mzmzuuwewmcsom50
`
`
`
`
`
`
`
`
`
`53:0muD,.mwmoo_n7m.m.o{2Eonm__oummmE_m:m/OBB0.Emam.m_boE§..____£m:om_
`
`
`
`_s...n__,,%:_._m.m§8__&5m__=ou,._o.m._2_m.__on_m.mm.e_mxmflma_m.mEm_mnmc_xo9._oommE_
`
`
`
`
`
`28E383
`
`
`
`maczuwm:o:m.u__aac.
`
`
`
`.._m.GH:.un..u_.__m
`
`
`
`_m:__nmmmmxomm
`
`EmD.3..3DSoQ3..._:_
`
`
`
`o_Bmno10.2mo_E_2oE.xmm_mQomoE_.mIm1:303
`
`
`
`
`
`Page 22 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 22 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 22 of 35
`
`US 2005/0289182 A1
`
`_Ex.mo._3moo_...78_um_.m.m/z_9.o.m_onm__oummmE_mxm/U.
`
`
`
`.io__uh_3._....o_..%.mm.=_n3o_m,
`
`mm9:?
`
`
`
`2....swan.
`
`no.mm.$uE4.B=oo£__u;so;..m
`
`
`
`fia_..w...m_,4.._._a._m....._...o..._w___i.M..__3
`
`
`
`..__uafiw....
`
`
`
`museumco:mu__na<a.
`
`Page 23 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 23 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 23 of 35
`
`US 2005/0289182 A1
`
`
`
`man...Em:n_.>E:::u_o3wzUEMZ>.m.:o:u_o_@_
`
`H.a.o._......_£Eo:uE
`
`
`
`
`
`
`
`
`
`
`
`.\u_a.a2o_.o_n;mz.2az.%§u_o.»E§._%s§2.35
`
`vme:m_u_
`
`Page 24 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 24 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 24 of 35
`
`US 2005/0289182 A1
`
`
`
`
`
`_iEm=mm,E=__mo..3.:u:.m=un_Emucflm..
`
`
`
`
`
`mm9:9“.
`
`aim:D3.5:D$_2.,_.3D_2.,_-ED3:.:.8D32.5”DEmD3o~._2,_.:DSenecaD38.3._%zDEozmn_
`__mEm_H_
`
`
`
`Sagan.o__oE:zm.._n__<_H_
`
`
`
`
`
`
`
`
`
`_.u._.=3.u..=u=un_u...___.___o__.a_u._..=a_.._._u.
`
`
`
`
`
`fl._=m_z":_—.—fl._.
`
`
`
`Fzuh_...U_d.@
`
`Page 25 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 25 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 25 of 35
`
`US 2005/0289182 A1
`
`E 5!
`
`Synonym Name: I
`
`;l;|_reJJ%‘J
`
`Cy Modify Synonym
`
`Synonym Name: IEuropean dale
`
`Visual Blue: for line selected ‘Synonym’ :-
`
`—+I ;I A E]
`E-urn n=and-a|»:-
`er dteforal
`
`Pflomyi E LI
`E
`
`Positional Attrbutes
`
`'
`
`Texlua|Attribul:es
`Line No’ I
`Para No.
`I
`Col Nn.I
`Row No.
`I
`
`Size:
`
`Font S tylez
`
`Figure 27
`
`Page 26 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 26 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 26 of 35
`
`US 2005/0289182 A1
`
`5 Jade Monkey
`W Jaan
`..|e:2:I.er
`
`Joy Circuit
`3
`'-53 Julassic
`0 Latha
`553 Letter Gothic MT
`
`Figure 28
`
`Page 27 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 27 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 27 of 35
`
`US 2005/0289182 A1
`
`...§E8L
`
`O
`
`38..:._o_m2L3.02L3.5.2,.L
`
`3__~._2,:._L
`
`BomstmL
`
`3.52:L
`
`.25..LEmL
`
`O_.UF:...ZMr_
`
`__mEm
`
`2%
`
`..9er.mL
`
`
`
`5905Sma.3o..£m.._o.0use.m..=.>
`
`
`
`momw._:m_n_<oNmSm_n_
`
`
`
`
`
`5.._$._=n=__£2.6.0-.0.:=1.:5:
`
`
`
`_%..:...q._
`
`
`
`Nu:NQflumE..u3mn_U—.__.—UQ‘f
`
`
`
`N.—OunwumHCLUHHMLUCCUD‘I
`
`Page 28 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 28 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`
`
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 28 of 35
`
`US 2005/0289182 A1
`
`o:__=32b_
`
`.98428L 22..3._u__e.mLoc__o_a:_wI_ 4
`
`m3Eozon_22.5.D“
`._u._o:_a_mL »
`
`
`
`uEa§n:_o_._Eum
`
`
`
`
`
`Soum_o:u_.0.cfiunoiuulimo:
`
`
`
`
`
`..+..:mom3.._m_..szobxmume:Eofiecmxmcm.5.3xoa«X9«.5umo:_
`
`
`
`
`
`N2...Naux...zzufiomvccuo\u
`
`
`
`
`
`
`
`
`
`Bad.w:oaao;—m_._>>man2cause..»u:2u_2_u:.a._..or:m:_xo__ob._.
`
`
`
`
`
`m£Em__.._m_;2E9.or:2xon2.:c_3c_u«mE9.:coxu__u.:...:mE_23oou3mm
`
`
`
`axe._uo;9mE
`
`
`
`
`
`.»co_3oExu._2:uo._case.53oc_.._u_3_...:2»2..3_u__3mBozm.u_u=o
`
`
`
`
`
`
`
`omm9%:
`
`Page 29 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 29 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 29 of 35
`
`US 2005/0289182 A1
`
`com9:5
`
`
`
`m_m.om._mr_uE3E_:_E.0H*
`
`
`
`m_m.om._m._.._n_E3E_xmE.0u_
`
`
`
`m.ufi=__.Emw.mzum=w.__omama.inIm_.
`
`
`
`N.._ONnwumuchuuuwtU..__.._UDWu‘
`
`
`..Bmwwm._nxm_
`
`
`
` .m_=_mmEu_u.mo.UHW”30.m.a.om.m.__U_m_UaauMe:.m::m_nN
`
`Page 30 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 30 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 30 of 35
`
`US 2005/0289182 A1
`
`
`
`
`
`
`
`aowuuzzmunauumwsuEH:m5am>Uwuuamm5m=.=u5uaumuouum=auaboumou>ummumua:umUHHanna.
`
`
`
`
`
`32.3._.useco_.m__uEou.2E__omm.mu__m>as..3o3_o>.2:33.25..Vo:_m>Sac.._s2on_
`
`.2;2.8a_a$>
`
`
`
`
`
`=auaauanusuaumnouuums»maauduumau5o>mhhumumwam=ummauouunuwmD
`
`<89.a_“_
`
`
`
`uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuInufinudonwawnaounnnuuunnnnnnnnnununuuanununn
`
`Aufiadbumumuumdm.mmnnounmuwmD.msumumuonuu.>duu4unua
`
`uudnonmuumuumvaamb
`
`soauundumam
`
`au>u5ncHuu3aabwuumumu5m
`
`wsnunmsuuumuonuu
`
`
`
`vunauumuuavaaabcownucfimmsaabmuumumwfimsmwzuouumnumb.m5udumuouuw.uuadugaAmbvznfin
`
`
`
`
`
`
`
`
`
`u_n_._uu_._u:_._..O.—E_..um_._o_um_.__m>_u>u._»coE_..uoo@
`
`
`
`
`
`Page 31 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 31 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 31 of 35
`
`US 2005/0289182 A1
`
`
`
`
`
`cowuufldmunauumwnufin.mdam>wwummmb5m=.:mvuaumuauuu=wuabounonhnmmmwumdmuumumuoz.
`
`
`
`32.muou.n___omm>
`
`
`
`wsambuwumwmofim.um2nouumuumD.m5uapmuouuu.uudawn.am>u5n:Huunfluumouavwaabcoauunsm
`
`
`
`
`
`mam9%:
`
`avsuubvuumoumfim.mm=uonuunwmD.mfiuuumuouumuhauudnuna
`
`anmuunfiuumaumduamb
`
`noauunsmwam
`
`
`
`
`
`
`
`3:23._.uco.._o__m__aEoo.2.a_.om2m_u_.o>9:.23.9,.:..._c_32BEwvo:_m>Sac.u_=m_mo
`
`
`
`LMDEDZHCDDUUCu-.:._W.—.._O._untum..E_umU__m.>
`
`
`
`
`
`Page 32 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 32 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 32 of 35
`
`US 2005/0289182 A1
`
`o5.Em..su8
`
`3.2mm.23cos:no2858
`
`.
`$353:_...,5ouu<3333£53E3.«w......=mv.a......§.:.nn.=61._.
`
`
`
`
`
`
`
`
`
`Guam5.:5..:.:._z~33«S3...£3.a_5u.3....a_.5Rm...
`
`
`
`
`
`HHHHNHHHUUIIDIIII“NHHflhutluflflflflflIIIB0III"-nnhnunnnnD)TII..nHHn..flUfl..flUflfl.lll3|I.F.“flflnuflflflnflflfl
`
`
`
`
`
`
`
`¢...8:.2tsouumFund.355.uzE<..3u
`
`
`
`
`
`
`
`
`
`
`
`
`
`IIIFLHHflflfllllIllIllcliullnflflnlluulllllliIIIHIIIUIIIIIIFIlllllllnallllIlllrhruflflflfll'-'."h
`
`
`
`
`
`
`
`
`
`
`
`§.;o.»..........cwxmo
`
`
`
`
`
`C..om....n2.Jfixwo.$...:..d.G..2:2
`
`
`
`I...zm2u...<.wwmoazuI
`
`
`3....~».Fm.c._~\~.u
`mm.~$.w2...mime
`
`om.3».m:...B22.
`
`
`$.m...m.mnm..auxuo
`$..;.n3..22..
`.:..mm«.::...2:8
`
`om..3......$._.mime
`2634.2...2:3
`
`_‘mw._:m_u_
`
`
`
`uo.,...§§__.....H...m:-...:un
`
`
`
`nuz<.2m...........u_u..3mozficm...........n.:.¢o
`
`
`
`
`
`fl
`
`HH
`
`a1>_.a.8a..m
`
`quacuouefiu
`
`xcmm2.o_o»m
`
`
`
`S8:E.-8“.
`
`..com328
`
`
`
`ounnuulBnw
`
`952...:
`
`...Bu8£aZ.sm
`
`£nn_o1I._oun§_
`
`
`
`memo>__.u>fi
`
`Page 33 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 33 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 33 of 35
`
`US 2005/0289182 A1
`
`mmmmmmmmmu
`
`uoaeazu:=ouu<
`
`__um2:3282:.S.3
`
`
`~=o~\Hn\~¢~¢o~\c~\oo
`
`uunweouuumuaun
`Baaaouaum3:2.
`
`.
`
`
`
`38.3.1.8um
`
`
`
`oun>;omLmaaumzo
`
`$0HOUWL
`
`.4..8.§._.§§m
`
`.xa9sEBsfin._9.s3§.u9_§sa3u&§_m:9u
`
`oofimnmnfi
`
`E
`
`mHnnunnunnnuuunnnnnnnnnunu
`
`..-...........-nngmgamgma
`
`n1>_a.8ua._.a.
`
`1.50C$039.50
`
`undone-.E=w
`
`38:33“.
`
`8~&Bn~_
`
`mm9:5
`
`Page 34 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 34 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 34 of 35
`
`US 2005/0289182 A1
`
` - <Col|ated><ML>
`+ <document lmage="c:\SHSlmagecnllaburator\Dala\Process\Un|dentlf|edFlles\Bankstmts1_Page_01.l|f'
`Page:"1' IsDocumentRecognized='True'>
`+ <dacumant lmage="c:\SHSlmageCn||abnrator\Data\Pracess\Un|clentlfledF||es\BankStmts1_Page_l'J2.tif'
`Page="1' Isoocumenmecognized:'Trua">
`</Co||ated><ML>
`
`Figure 33
`
`
`
` — <CulIated><ML>
`— <document Image-="C:\SHSImagecollaborator\Dala\Process\UnidentifiedFiIes\BankStmts1_Paqe_lJ1.tif"
`Page="1" 1sDocumentRecognized="True“>
`<Au:countNumber
`Image="C:\SHSlmageCollaburatur\Data\Prucess\UnidentifiedFiles\BankStmts1__Page_lJ1.tif“
`Page="1" Caption="Account Number" I5Genera1Gesture=“FaIse" Zone><="419.1" ZoneY="91.5"
`ZoneWIdth="10EI.9“ 2oneHeight="BiB5" Accuracy="1UU" Verified="Yes" Error='”' SuggestedValue='1B47EI868
`test" Initia|Value="1847DB6B">1B47IJB6I3</Au:r:ountNurnber>
`<BankName
`Image="c:\SHSImageca[laboratur\Data\Prnaess\UnidentifiedFi|es\BankStmts1_Page_U1.tif"
`Page="1" Captu:n="Bank" IsGenera|Gesture="Fa|se" ZoneX="6E.1" ZoneV="4U" ZoneWidth="145.3"
`Zonal-ieight="17.5" Accuran:y="10D' ducld="“ Venfied=“Yes' InitialValue="Escrow Bank">Escrow
`Bank</BankName>
`<FromDate
`Irnage="C:\sHSImageC0Ilaburatnr\Data\Prucess\UninlenliliudFi|us\BankStmls1_Page_O1.tif"
`Page="l" Capti0n="FromDale" IsGeneralGesture="True" Zone><="359.'I" ZuneY="91.15" Z0r1eWid:h="4B.45"
`ZoneHeight="9.55" AcI:uracy="1EID' Verified=“Yes' Errum"" SuggestedVa|ue="fl2/28/I12"
`Initia|Va|ue="02/28/02">02/2B/02</Fr0mData>
`<Tn:nDate Image-='C:\sHsImagecollaburator\Data\Prncess\UnidentifiedFiles\Bankstmts1_Page_01.tif"
`Page="1" Capti0rn="To Date" Iscenera|Gesture="FaIse" 2one><=":J59.7“ 2oneY="91.15" ZoneWidth="4B.45'
`ZoneHeight="9.55" Accuracy="10(J' Verified="Yes" InitiaIValue:"02/2B/D2">D2/2B/02</ToDate>
`</documem>
`— <d0cument 1rnage="(.‘.:\SHSImageCoI|aburatnr\Data\Prucess\UnidentifiedFilas\Bankslmts1_Page_02.tif"
`Page="1" I5DocumentRecognized="True">
`<AccountNumber
`
`T
`
`-
`
`[mage=''C:\SHSImageCn||aboratur\Data\Pruoess\UnidentifiecIFi|es\BankStmts1_Page_U2.tif''
`
`;]
`
`Figure 34
`
`Page 35 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 35 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`Patent Application Publication Dec. 29, 2005 Sheet 35 of 35
`
`US 2005/0289182 A1
`
`
`— <1-.variab|es>
`
`<variable>BankName<;’\.rariab|e>
`<variab|e:>AccountNumber«:/variable)
`<variab|e}FrnmDate=:/variable>
`<:variab|e>ToDate</variab|e>
`</variab|es>
`
`" Figure 35A”
`
`
`
`
`— <index LastPage="D">
`<BankNamez-BANK ONE</BankName>
`<AccountNumbar:>0EIOIJl]1580877197</AccountNumber>
`<FrornDate>Dec 1</FromDate>
`<ToDate>Dec 31, 2lJO1</ToDate>
`</inde><>
`
`Figure 35B
`
`- <dncument lmage="c:\sHslmagecollaboralor\Data\Process\Unidentlf|edF|les\Bankstmts1_Page_17.tif‘ Page='1'
`IsDon:umentRecugni2ed='True'>
`<t.ccuuntNumb9r lmaga-="C:\SHSImagecullaborator\Data\|1ro1:ess\UnidentifiedFiIes\BankStmts1_l3age_17 .tif'
`;3age='1" Captinn='Accnunt Number" IsGenera|Gesture="FaIse” Znne><="10fl.5" ZoneY="5D.1" ZoneWidth="I13.95'
`ZoneHanght='9.2“ A-:curacy=‘1Ufl" Verified="No' Error="' SuggestedValue="21D0lJ18924429
`test">21lJEIIJ1B924429</Ar:I:nuntNumher>
`<EankNarne Image="C:\SHSImagecollaboratnr\Data\Process\unidentifiedFi|es\BankStmts1_Page_17.tif" Page='1"
`Caption="Bank" Ist3eneralGesture='Fa|sa" Zune><="1UlJ.5' ZoneV='5IJ.1" ZoneWidth="11:3.95" 2oneHeight="9.2"
`Ar.r.nrar.:y="1Dfl' rinnId='*" Verifio.=.d=”Nn".>First Union National Bank</BankNama>
`<FromDate Image="c:\sHS[magecollaborator\Data\Prucess\UnidentifiedFi|es\BankStmts1__Page_17.tif“ Page='-1"
`Captnon="FromDate" IsGeneraIGesture='”rrua“ Zone><='IJ” Zone\'='ll' Zone-Widr.h='U" ZoneHa‘ght=“l]" Accuracy='1[)D"
`'v‘en'fied="No" Error=’”' SuggestadVaIue="" />
`<ToDate Imagu.=='C:\SHSlmagecollabnrator\Data\Pro|:ess\UnidentifiedFi|es\BankStmts1__Page_17.tif" Page="—1"
`caption="ToData" IsGenara|L‘:esture='TruB" zoneX="u' ZuneY=“0" zansWidth=“0“ ZoneHeight='u" Accuracy="1l'Jo"
`Verified="No" />
`</doI:ument>
`
`Figure 36
`
`
`— <document Image=“C:\SHSImagecollaborator\Data\Process\unidentifiedFiles\Bank8tmts1_Page_D7.tif" FJage='1'
`IsDncumentRecognized="True">
`<AccountNumb-er Image="C:\SHSImagecullaharatnr\Data\Prm:ess\Un|dentIfiedFlIes\BankStmts1_Page_D7.tII’
`Page='1' Caption="Accuunt Number" Isceneralsesture="False' Zone><='49D.75' ZnneV="74.95" Zonewidth="59.6'
`ZoneHaiqht="9.2' Accuracv="l0D" Verified='Yes" Error="" Suggastem/aIue="1235325581 test"
`InitialVa|ue='1235325581'>12353255B1</AccountNL.mber>
`<BankName Image="C:\SHSImagecollabDrator\Data\Process\Uniden!ifiedFi|es\Bankstmts]_F|age_[]7.tif" Page="l"
`Caption="Bank" IsGerIera|Gesture='Falsa' Zone><='113.8" ZonaY=“37.5' ZoneWLdth='123.7" ZoneHeIght='16i4“
`Act:uracy="1lJD" docId="' Verifie-d="Yes“ Ini:ialVa|ue='Bank Of America'>Ban|< Of AmerIca</Ban|<Name>
`<FromDate Imags='C:\sHSlmageCulIaburator\Data\Process\UnidentifiadFiles\BankStmts1_Page_u7.tif" Dage="1“
`Caption="From Date" IsGeneraIGesture="Fa|se“ Zona><=“125' Zonev=“26IJ.7" Zonewidth='60.65" zoneHeight='2o.:I5"
`Accuracy=“1IJD“ repIaceCharacters='.,' Verified='Yes" Error="' SuggestedVa|ue="O6/29/2002"
`Initia|Value='EI6/29/2lJ02'>06/29/201]2</FromDate>
`<ToDaie Image='c:\sHSImagecollabnrator\Data\Prucess\UnidenlifiedFiles\BankStmts1_Page_lJ7.tIf" Page="1'
`Caption="To Date" ZsGenera|Gesture="False“ Zone><='2u2.75" zoneY="262.E5" ZoneWidth='6u.65' zoneHeight="11"
`Accurar:y=“1Uu" rep|an:eCharacters='.,' verified:'Yes" 1n1tia!Va|ue="D7/3 1/2UD2'>I]7/31/2DIJ2</ToDate>
`</document)
`
`Figure 37
`
`Page 36 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 36 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`US 2005/0289182 A1
`
`Dec. 29, 2005
`
`DOCUMENT MANAGEMENT SYSTEM WITH
`ENHANCED INTELLIGENT DOCUMENT
`RECOGNITION CAPABILITIES
`
`CROSS-REFERENCE TO RELATED
`APPLICATION
`
`[0001] This application claims the benefit of Provisional
`Application No. 60/579,277, filed on Jun. 15, 2004, which
`application is hereby incorporated by reference in its
`entirety.
`
`FIELD OF THE INVENTION
`
`[0002] The invention generally relates to methods and
`apparatus for managing documents. More particularly, the
`present
`invention relates to methods and apparatus for
`document management, which capture image data from
`electronic document sources as diverse as facsimile images,
`scanned images, and other document management systems
`and provides, for example, indexed, accessible data in a
`standard format which can be easily integrated and reused
`throughout an organization or network-based system.
`BACKGROUND AND SUMMARY OF THE
`INVENTION
`
`efficiently managing
`[0003] For many organizations,
`documents and transaction-centric business processes is a
`major challenge. Key business processes involving the use
`of numerous printed documents and/or document images are
`far too often fraught with inefficiencies and opportunities for
`error.
`
`[0004] Without a mechanism for efficiently capturing and
`accessing documents and related content on-line, organiza-
`tions have little opportunity to use and build on the vast
`information in their documents by integrating such infor-
`mation with the companies business processes, such as, for
`example, its customer relationship management process.
`
`[0005] The widespread use of paper and form-based pro-
`cesses also limits an organization’s ability to take full
`advantage of the information flowing into, within and out of
`the company.
`
`[0006] Many organizations are moving toward the goal of
`a paperless office by implementing document-management
`solutions which allow them to store documents and forms as
`
`electronic images in a document management repository. In
`many organizations, a document is received, scanned and
`then a bit-mapped document image is circulated among
`relevant personnel. Although this approach may eliminate
`multiple circulating hard copies of documents,
`the docu-
`ments must be read, understood, and often times later
`retrieved by the various personnel quickly from different
`applications.
`
`[0007] A need exists for a document management system
`which efficiently analyzes and indexes such bit mapped
`images of documents to determine the nature of the docu-
`ment, and to efficiently generate index information for the
`document. Such index information, for example, would
`identify that
`the document
`is a bank statement from a
`particular bank, for a particular month.
`
`[0008] The inventors have recognized that a need exists
`for methods and apparatus for efficiently storing, retrieving,
`searching and routing electronic documents so that users can
`easily access them.
`
`[0009] The illustrative embodiments describe exemplary
`document management systems which increase the effi-
`ciency of organizations so that they may quickly search,
`retrieve and reuse information that is embedded in printed
`documents and scanned images. The illustrative embodi-
`ments permit manually associating key words as indices to
`images using the described document management system.
`In this fashion, key words are extracted and data from the
`images become automatically available for reuse in various
`other applications.
`
`[0010] The illustrative embodiments provide integrated
`document management applications which capture and pro-
`cess all the types of documents an organization receives,
`including e-mails, faxes, postal mail, applications made over
`the web and multi-format electronic files. The document
`
`management applications process these documents and pro-
`vide critical data in a standard format which can be easily
`integrated and reused throughout an organization’s net-
`works.
`
`In an illustrative embodiment of the present inven-
`[0011]
`tion, a client-server application referred to herein as the
`“Image Collaborator” is described. Image collaborator is
`also referred to herein as IMAGEdox, which may be viewed
`as an illustrative embodiment of the Image Collaborator. The
`Image Collaborator is used as part of a highly scalable and
`configurable universal platform based server which pro-
`cesses a wide variety of documents: 1) printed forms, 2)
`handwritten forms, and 3) electronic forms,
`in formats
`ranging from Microsoft Word to PDF images, Excel spread-
`sheets, faxes and scanned images. The described server
`extracts and validates critical content embedded in such
`
`documents and stores it, for example, as XML data or
`HTML data,
`ready to be integrated with a company’s
`business applications. Data is easily shared between such
`business applications, giving users the information in the
`form they want it. Advantageously, the illustrative embodi-
`ments make businesses more productive and significantly
`reduce the cost of processing documents and integrating
`them with other business applications.
`
`In accordance with an exemplary embodiment
`[0012]
`described herein, the Image Collaborator-based document
`management system includes modules for image capture,
`image enhancement, image identification, optical character
`recognition, data extraction and quality assurance. The sys-
`tem captures data from electronic documents as diverse as
`facsimile images, scanned images and images from docu-
`ment management systems. It processes these images and
`presents the data in, for example, a standard XML format.
`
`[0013] The Image Collaborator described herein, pro-
`cesses both structured document images (ones which have a
`standard format) and unstructured document images (ones
`which do not have a standard format). The Image Collabo-
`rator can extract images directly from a facsimile machine,
`a scanner or a document management system for processing.
`
`In accordance with an exemplary embodiment, a
`[0014]
`sequence of images which have been scanned may be, for
`example, a multiple page bank statement. The Image Col-
`laborator may identify and index such a statement by, for
`example, identifying the name of the associated bank, the
`range of dates that the bank statement covers, the account
`number and other key indexing information. The remainder
`of the document may be processed through an optical
`
`Page 37 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`Page 37 of 79
`
`ROTHSCHILD EXHIBIT 1003
`
`

`
`US 2005/0289182 A1
`
`Dec. 29, 2005
`
`character recognition module to create a digital package
`which is available for a line of business application.
`
`[0015] The system advantageously permits unstructured,
`non-standard forms to be processed by processing a scanned
`page and extracting key words from the scanned page. The
`system has sufficient intelligen