http://www.informatik.uni-trier.de/~ley/db/conf/das/das2006.html
DAS 2006
http://dx.doi.org/10.1007/11669487_25	24	Towards Versatile Document Analysis Systems	acta addison address algorithm analysis associative baird balanced barcelona bentley best binary breiman brooks case cation character classi cole commun communications computer conf consistent content context data database delorenzo design document duda edition expected extraction finkel freidman friedman front grove haralick hart iapr icdar icpr ieee image intelligence isogenous jose king knuth large lecture logarithmic machine massachusetts matches math modern moll multidimensional nagy nding nonnemaker olshen optical order paci pages pami partial pattern patterns pavlidis phillips prize proc quad reading recognition references region regression retrieval samet sarkar scale search searches searching second seth simulation softw spain spatial spie standard statistics stone stork structures studies style thirty time trans transactions trees twenty typefaces used veeramachaneni versatile wadsworth wesley wiley with wong worst year years york
http://dx.doi.org/10.1007/11669487_19	18	Segmentation of On-Line Handwritten Japanese Text Using SVM for Improving Text Recognition	advances aizawa arbitrary bilan burges cambridge character classification conference constrains constraint cristianini direction duda edinburgh edition edits england features formalization free from handwritten hart horii icdar icpr ieice improving international introduction japan japanese joachims kernel korea large learning line lkopf machines making means method methods multiple nakagawa network neural odaka okamoto online onuma orientation pattern physical practical press proc real recognition references report scale second segmentation seoul shawe smola sons statistical stork string stroke support talor technical text theory time transactions university using vapnik vector wakahara wiley yamamoto yosikawa
http://dx.doi.org/10.1007/11669487_48	47	Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval	analysis application based bmvc building camera cameras capturing cartographic cbdar clark combinations computational computer constant database databases descriptors detection distortion document documents doermann duplicates engineering feature flusser fosyth geometric hancock hashing huet hull icdar ieee ijdar image images indexing into invariant invariants iwamura kise liang library local matching mirmehdi model multiple mundy nakai overview pages pattern pilu point points pollard proc progress projective real recognising recognition references remotely retrieval rigoutsos rothwell scenes science sensed survey systems text time understanding using vision wacv with wolfson zisserman
http://dx.doi.org/10.1007/11669487_10	9	Extraction of Handwritten Text from Carbon Copy Medical Form Images	adaptive ahmadi algorithm analysis applications approach automation background based beigi binarising binarization binary biomedical boyle brown bruckstein bureau camera canceling care cbms center character chassaing chen chinese chung circuits clean cliffs comparison computer computing conference congress contents cursive cvgip cybernetics dance degraded department digital document documents driven dynamic edition eighth electronic emergency engineering englewood enhancement estimation europe evaluation extraction fast fingerprint from frontiers ganapathy gatos global govindaraju graphics gray grayscale growing haapakoski hall handwriting handwritten hatami health histogram historical hlavac hospital hosseini huang icpr ieee image images imaging information international introduction iscas jolion journal kamarei kamel leedham letters level lexicon liao line localization logical machine manmatha marukawa medical method methods milewski modeling models multi multilevel multimedia niblack normalization otsu pami parameter patankar pathological pattern perantonis pietikainen pixels pratikakis prehospital prentice preprocessing proc proceedings processing publishing quality real recognition references region regional report reports research safar sauvola schurmann science seeger segmentation selection selective separating seppanen services seventeenth shape signal society sonka spie stage state stylpen symposium system systems taxt technique techniques text thakor threshold thresholding time trans transactions tremor trier varma vision volume wavelet western wolf word workshop world xerox yang yanowitz york zhao
http://dx.doi.org/10.1007/11669487_9	8	Virtual Example Synthesis Based on PCA for Off-Line Handwritten Character Recognition	advances analytic approach arti based bunke chapter character characters cial classi combined creating cumulative cvpr database densities development ectiveness erformance erturbation example examples from generating generation generative ghosh girosi given hananoi hand handwritten high historical http icdar icpr ieee images improved incorp ipdb iwfhr jaeger japanese joachims kanji kernel kernels knowledge large learning lieu likelihood line lkopf machine make making maruyama matsakis method methods miller miyao models mori multiple nakagawa nakano niyogi normalizing numeral online orating otheses pami pattern poggio practical press printed prior proc rate realistic recognition references research review scale shared shibaprasad smola statistical suen svms synthesized technique theory through trans transformation tuat using vapnik velek viola virtual warping wiley with yamamoto york
http://dx.doi.org/10.1007/11669487_40	39	Finding Hidden Semantics of Text Tables	adamantis advanced alrashed analysis approach approaches based bodo bornhovd bruce california christof clara commerce computer conf conference conversion croft data database dealing debashish department deriving detection diamantop digital document doermann dryden ecommerce edinburgh electronic ernetics fear first florida form from functions gray heterogeneity hori hurst icdar ieee images informatics information integrate integration international interpretation isas issues knowledge large libraries link logical london madnick many matthew metadata method multiconference niyogi orlando oulos oxdriven pallavi press princeton proc proceedings pyreddy reasoning recognition references retrieval robust saleh santa scale schlegelmilch science seattle semantic semantics society structure suny synthesis system systemics systems table tables tabular taking text third tintin torisawa tsujii university utilising very vlbd vldb vmldb volume washington wecwis wide with workshop world yoshida
http://dx.doi.org/10.1007/11669487_35	34	A Shared Fragments Analysis System for Large Collections of Web Pages	acceleration andyc apache applications approach appserv appserver architecture arun augmentation automated automatic based broder buttler caching ccfinder challenger chun ciently clone code communications computer conf consortium containment content creating data datta detection digest document documents domhash douglis dynamic dynamically edge editors engineering eople erneko extraction fingerprinting fragments framework fred fully generated group guide html http icdcs ieee implementation includes index infocom intl ject kamiya lakshmish large ling lyengar management method methods microsoft model multilinguistic neko network ocelli oracle pages parser proceeding proceedings processing products proxy publishing rabin ramaswamy recommendation references resemblance santis scale science security sequences server side sigmod simple software some source springer system token transactions vaccaro values verlag weblogic webservers websphere wide working world york yuan zhang zheng zhigang
http://dx.doi.org/10.1007/11669487_18	17	Extraction and Analysis of Do cument Examiner Features from Vector Skeletons of Grapheme ‘th’	accurate addison algorithm algorithms allied also analysis annual appeared applied arlington arora arti aurora authentication automatic bala based biometric book brill brown brunswick bulacu cambridge canada case cation character characterizing characters chaudhuri chayko chen chennai cial classi compare comparison computation computer computing conf congress conn constructive court crossover daubert decision department designed development discriminatory distal distance document documents edinburgh eger elements establishing evidence evolutionary examination examinations examiner examiners expert expertise extraction facts fast feature features fielding florida forensic found from fundamentals gemmert genetic george goldberg graphonomics groups guerra gulliver gummadidala hall handwriting handwritten harrison headrick heterogeneous hilton honavar huang huber hybrid icdar identi ieee ijcai illinois individuality intell intelligence inter international invited iowa irrelevant iwda jacob john joint jong journal kaufmann kohavi kulikowski learn learning lecture leedham letter level lindblom machine martin mason melikhov merrel methods montreal morgan nelson nets network networks neural numerals optimization parametric parekh parui pattern pervouchine pharmaceuticals pilot piscataway power prediction press problem proc professional program publishers quantitative questioned recognition references report robertson roger rogers rutgers salcedo santa schmittat schomaker science sciences scienti scottsdale search seattle selection signature sita skeletonisation smith society sparse spatial srihari state statistics strategies study subset suspect symposium syst systems syswerda technical techniques teulings that their tomai tool tools trans trees uniform university used using vafaie validating washington wechsler weiss wesley whitley with words workshop writer yang zhang
http://dx.doi.org/10.1007/11669487_36	35	Offline Handwritten Arabic Character Segmentation with Probabilistic Model∗	acsa advances algorithm amin amounts analysis anddynamic angela approach arabic automatic barney based bennamoun bergmann bortolozzi bushofa character characters checks cheung coding conf conference contour correction cursive cybern cybernetics database david dehghan digital discrete document edited editors eighth elgammal elisa enit extraction fakir feature fourth framework french frontiers geometric geometry gmag graph graphics handwriting handwritten hassani holistic iapr icdar icpr ieee information intelligence international internationalconference ismail iwda karhunen kazem khuraidly latecki latin lecourtier leroux lethelier line loeve longin machine maergner mari method methodology miled modeling motawa mount najoua nawaz noureddine numeral offline olivier optical pakker part pattern pechwitz poste printed proc proceedings processing programming reading recent recognition references retrieval robust romeo sabourin sadoun sarat sarfraz sari script segmentation selforganizing sellami seventh shaddad signal sixth smith sodeyama souici spann spie statistical syst system systems taghva technique text their third tolba transactions transform udpa using vision volume wang word words workshop xiii yousefi
http://dx.doi.org/10.1007/11669487_17	16	Writer Identification for Smart Meeting Room Systems	accepted acoustics acquired actions adaptation adapted algorithm analysis applications audio authentication automatic barnard baron based bengio bett biometric biometrics browsing bunke cation centre changes classi collobert communication comparative computer computing conf connell corpus cursive czyz data database delay dempster denver digital direction document drygajlo dunn dynamic edwards electronics ellis engineering english events expression face facial fasel fast features ferret flynn from fusion gatica gaussian gelbart graphonomics griess group grudin guillemot guyon handwriting handwritten henderson hidden human humanities icsi identi identity idiap ieee illumination incomplete indicated intelligence interaction internal jaeger jain janin johansson journal komatsu laird language lathoud learning letters library likelihood line liwicki luettin machine malkin manke manual marcel mariethoz markov maximum mccowan meeting meetings methods mixture models modular moore morgan multimodal multiple nagao networks neural norway norwegian notes npen ondb online paliwal pattern perez person pfau proc processing programming project publication quatieri recognition recognizer recognizers recorded references reichert reiter report representations reynolds richiardi rigoll rogina room royal rubin sanderson scalability schenkel schlapbach schomaker schultz script segmentation sentence shriberg sigmm signal signature smart society software speaker speech spoken statistical stiefelhagen stolcke study survey systems tagged task technical technologies text time torch trans under user using vandendorpe veri video vision visual volume waibel wellner whiteboard with workshop writer yamazaki yang zhang
http://dx.doi.org/10.1007/11669487_28	27	On Benchmarking of Invoice Analysis Systems	accuracy adaptable adaptive agne algorithms amia analysis andreas andrew annual applications approach approaches april association august automated automatic automatisierte autonomous bagdanov baird baltimore based benchmarking berrin bertin beth biomedicine breuel burgun butterworths california canada casimir categorization cation ceusters changsong chapter chen chinchor cimino city classi columbia commercial computer conf conference construction content cornell daniel data david davis defect dengel development ding discovery document earb ecial edinburgh edition editor editors edward eighteenth eitung electronic elkin enchmarking erformance ergen ersicht estimate evaluating evaluation fall february fidel fifth fordan forum fourth frank frontiers general george germany gorman ground grove grover handwriting henry high iapr icdar ieee image imaging industrial information ingwersen inhaltsverzeichnis institute intel international invoice issue january japan jenkins jiangying jirong jose journal july june junichi kaiserslautern kalet kanai kasturi kaufmann kevin kgkd kieninger kingdom kkus klein krnn kulikowski kumar language lawrence learn learning lehnert lewis liangrui ligence line lncs logical lopresti machine magazine marktp marktub markus maryland mclean message method metrics ming models montr morgan nagano nagy nakano nancy nartker natural nevada novemb nowak octob ontologies optimizing otential otting paci page pages pattern peng perfect performance peter preliminary press problem proceedings publishers quality questions randriamasy rangachar raya reading rechnungseingangsb recognition rector references region rehders report representations research results retrieval rgner rice rijsb rogers rogger rohrschneider sabine scheme schneider schulz science scotland sdair seattle second segmentation septemb sholom sigir sixth smartfix smith society spackman speech spie spitz springer stefan stephen structure studie study summers sundheim symposium synthetic system systems table technical technologies technology test text textanalysis that their thesis third thomas three thulke transactions trends true truthing tsukuba understanding united university uses using vegas vincent virginia vision volume wagner washington weiss wendy winkler wittner workshop xiaoqing yanikoglu zaccagini zheng zhou zoning zweigenbaum
http://dx.doi.org/10.1007/11669487_6	5	Gray-Scale Thinning Algorithm Using Local Min/Max Operations	adaptive algorithm analysis axis case comm comprehensive conf cybernetics detection digital fast fuzzy govindan gray ieee image images intelligence letters local logic machine medial method methodologies nakagawa note obtaining operations parallel park pattern patterns peleg picture processing ravines recognition references region ridge ridges rosenfeld salari scale seeking shivaprasad skeleton song specification suen survey system thinning trans transformation using wang without zhang
http://dx.doi.org/10.1007/11669487_8	7	Aligning Transcripts to Automatically Segmented Handwritten Manuscripts	acids adaptive aligning alignment allan anal analysis approach arti audio august automatically based bengio biological boxmodify bunke byrne cambridge cation computational computer conf corfu cursive database decemb deng deroo dial document documents durbin dutoit eaker eddy eech emnlp engine english erformance extraction from frontiers full gangalore germany govindara greece ground handwriting handwritten hauptmann historic historical hmms hobby holistic hybrid icassp icslp identi ieee image images improve india intel international jang journal korn krogh lake language lavrenko learning libraries ligence ligent line linguistics lvin mach machine malamud malfrre manmatha manuscript manuscripts mapping march marti matching mitchison model models munich nagy niagara nucleic pages pami pattern phonetic phrase press probabilistic proc proceedings program proteins prototyp rath recognition recognize references retrieval roscheisen rothfeder scale search second segmentation segmented segmenting sentence septemb sequence sigir space srimal statistical synthesis system systems technique television text texts theories tomai tool trans transactions transcript transcripts translation truth unconstrained university using vinciarelli vision watching with word words workshop zhang
http://dx.doi.org/10.1007/11669487_55	54	The Fuzzy-Spatial Descriptor for the Online Graphic Recognition: Overlapping Matrix Algorithm	aaai analysis based calhoun cali calligraphic closed computer conference davis dean descriptor drawings early examples finding florida fonseca fragmentation fuzzy gestures graphic graphics heloise ieee intelligence intelligent interface interfaces international jorge kara kurtoglu machine micheal multi online orlando paths pattern perceptually pimentel press proceddings proceedings processing recognition recognizer recognizing references richard robust rubine saund scribble sezgin sketch sketched sketches spatial specifying spring stahovich stroke symbol symbols symposium templates transactions understanding user using workshop
http://dx.doi.org/10.1007/11669487_41	40	Reconstruction of Orthogonal Polygonal Lines	algorithms along analysis analyzed appendix approximating approximation august automatic beautifier beginning bodansky canadian caricature cartographer chhabra computer current david december defined defining derivation deviations digitized distance douglas drawings empirical equal evaluation expression follows found from given graphics gribov horizontal ieee illustrations inequalities inequality integral intelligence july line lines lncs machine method number obtain obvious orthogonal other parameter part pattern pavlidis performance peucker phillips point points polygonal polyline portugal possible press recognition reconstruction reduction references represent required september similarly some springer standard statistical straight structural syntactic systems these this thomas till transactions values vanwyk vertical where words
http://dx.doi.org/10.1007/11669487_20	19	Application of Bi-gram Driven Chinese Handwritten Character Segmentation for an Address Reading System	address addresses algorithm analysis based bertille binary candidate capable character chinese codes comparison computing conference confusion conjoined contextual correcting delivery dence destination ding document doklady driven engineering envelopes evaluation experimental fujisawa gilloux handwritten ieee insertions international interpretation japanese jimenez july koga large letters levenshtein lexicon line lncs location london marzal masaki matrix names pami paths pattern physics post postal precise proc processing reading recognition references reversals script segmentation selection shortest soviet springer street strings third trans within workshop yacoubi
http://dx.doi.org/10.1007/11669487_44	43	Cut Digits Classification with k-NN Multi-specialist	adaptive aksela algorithms alimoglu alpaydin amsterdam analysis application australia bagging based bauer blurred boosting borders boto brisbane broken bunke canada cascading character class classifer classification classifier classifiers combination combining comparison computational confidence cort cost criteria critic dasarathy data decision devroye digit digits discriminant document duin empirical fairhurst features forms function girdziusas handwriting handwritten hated hierarchical hull icpr ieee improve international iwfhr journal kangas kanji kaynak kittler kohavi laaksonen learning letters line linking lncs lugosi lvarez machine macrostructure mart masks matas mending method methods mining morphological muguerza multiple navarro nearest neighbor neighbourhood noise noisy norms numeral omachi ontario optical overview pami pattern pertubation press printed probabilistic rahman rate recognition reconstruction references representations review rodriguez shomaker sized soraluze specialist springer srihari strategies structural systems techniques theory transactions twostage variable variants verlag voting vuurpijil wang whichello with
http://dx.doi.org/10.1007/11669487_2	1	A Semi-automatic Adaptive OCR for Digital Libraries	amharic analysis anatomy anoop appear applications baird bilinguagl bokser character characters chaudhuri classi computer conf conference correction crumpton cviu david degradation degraded digital document documents doermann extraction feature font fourth free gonzalez hall haralick hartley henry hindi http icdar icpr ieee image images indexing india indian intelligence international issue ittner jain jawahar kahan kanungo kiran kumar language layout learning libraries library machine madigan meshesha methodology methods million model mori nagy namboodiri nonparametric omnidocument optical page pami pattern pavan pavlidis pavlidisi prentice printed proc proceedings processing quality ravi reader recognition references retrieval robert script segment sesh size skew special statistical stuezle survey tapas taxt technoloigies telugu text textual transaction transactions trier twenty understanding validation versatile vision werner woods years
http://dx.doi.org/10.1007/11669487_33	32	Performance Comparison of Six Algorithms for Page Segmentation	algorithm algorithms analysis antonacop application architecture area background baird baseline branch breuel bridson canada casey cattoni chanda character coianiz comp computer cviu data development diagram document ectrum edinburgh electronic empirical enchmarking erformance etition evaluation extraction gatos geometric gorman ground guyon handb haralick hull icdar ieee ijdar image images imaging irst italy iwata japan jose journal journals kanai kanungo karatzas kise korea layout least liang literature measure messelodi methodology metrics modena montreal nagy nartker nding oulos ound page performance phillips princeton proc prototyp pset recognition references research retrieval review rice robust rosenfeld saha sato scienti segmentation seoul seth sets software spie square structure survey system systems technical techniques toolkit tpami trento truthing tsukuba understanding using vincent viswanathan voronoi wahl wong world yanikoglu
http://dx.doi.org/10.1007/11669487_30	29	Efficient Word Retrieval by Means of SOM Clustering and PCA	analysis baird berchtold bitmapped cation chaudhuri chen cient classi cluster clustering clustertree computer curtis data digital dimensions discovery document documents docunents doermann domain duda dynamic from guttman hart hero high highdimensional huang icdar ieee image imaged images index indexing information integration john june keim keyword kise knowledge kohonen kriegel large libraries lncs maps marinai marino matsumoto means mitra nearest neighbor organizing page pages pami parts pattern proc proceedings read recognition references relevant representation retrieval sciences sdair search searching self series sets shape sigmod soda sons spatial spie spotting springer stork structure survey systems text transactions tree trenkle tsujino understanding verlag vision vldb vogt where wiley williams with without word words zalubas zhang
http://dx.doi.org/10.1007/11669487_29	28	Semi-automatic Ground Truth Generation for Chart Image Recognition	alexander algorithm algorithms analysis applications approach automatic background barcelona based carriero chart charts comp complex computer conference constructive detection diagrams document documents doermann dori electronic elements environment erformance evaluation extracting extraction from futrelle generation graphics grec ground grouping haralick hough huang iapr icdar icip icpr ieee image images incremental intelligence international july kakadiaris layout learning leow level line machine method model multi nikolakis onent page pattern perfectdoc performance phillips pixel processing protocol recognition references sami saxena scienti segmentation spain sparse structure systems table technical technique text transactions truth truthing understanding vectorization vision wang watanab workshop yacoub yokokura yuan zhou
http://dx.doi.org/10.1007/11669487_53	52	Automatic Assembling of Cadastral Maps Based on Generalized Hough Transformation	alex analysis approach arbitrary arrangements artificial assembling ballard cadastre central computer conference davis detect detecting digital distributed document drogoul dubreuil europe game generalizing graphics guigues hough ieee intelligence interactive interfaces international january jean laurent marc matching media object pami pattern piece proceeding proceedings puzzle recognition references relaxation resolution scarlatos shape shapes sixth smart solving techniques topology transform using viglino visualization workshop
http://dx.doi.org/10.1007/11669487_38	37	Digitizing a Million Bo oks: Challenges for Do cument Analysis	access addison agents agosti alto ambati analysis architectures archive baird book boston building cagliari cahllenges china cole collections computer conf conference creating davidson delos demand details devanagari dial digital document documents edinburgh excellence first florence framework francisco frommholz generation gonzalez good govindara grid guidance hangzhou hardcopy http hyderabad iapr ieee iiit image india information intelligent international italy january jawahar ject kaufmann knezevic kompalli korea lakshmi lesk libraries library longman lopresti management mehta million millionbooks monday morgan nayak network next niedere orientation orting palo peer pottenger pramod pratha press proceedings processing publishing quality recognition reddy references resources risse robust sankar schek scotland seoul service setlur sixth society supp systems techniques thematic thiel tools trker ulib understanding universal university vamshi washington wesley woods workshop zhejiang
http://dx.doi.org/10.1007/11669487_32	31	Combining Multiple Classifiers for Faster Optical Character Recognition	analysis annals application applied artificial based best bhattacharya boosting character chaudhuri classifier classifiers combining confidence consistency convergence convolutional discriminative diverse document duin early evaluation fusion gori handprinted handwritten hatef icdar icpr ieee intel intelligence kittler ludmila machine majority marinai matas michel milgram model moises multiresolution networks neural numerals oudot pattern platt practice prevost recognition references sako scheme sendis simard soda statistics steinkraus stopping strategies study theoretical tpami train trans visual voting with zhang
http://dx.doi.org/10.1007/11669487_50	49	Segmentation-Driven Recognition Applied to Numerical Field Extraction from Handwritten Incoming Mail Do cuments	ability address alexander algorithms alignements apllications applications applied approach approaches architectures area based bishop bradley bridle cambridge cation character chatelain cheriet class classi code combination combines combining computer conference congedo curve dence digit dimauro directed discriminative documents driven duin dzuba enhanced evaluation extraction faure feature feedforward field filatov frontiers fujisawa gader govindaraju gregory handwriting handwritten herault heutte hidden hybrid icdar icpr ieee impedovo incoming integration international interpretation into iwfhr japan kaufmann keubert koch learning lecourtier letters lexicon likforman line london machine mail manuscrits markov method milgram model models moreau nakashima nato network networks neural neurocomputing numeric numerical olivier outlier outputs oxford pami paquet pattern perrone pirlo pitrelli post postal pour press probabilistic processing rabiner reader readings real recognition references rejection relationships remote robert sabourin sako scoring segmentation selected sequence service signal solution soulie speech springer srihari state states statistical strings structural sulem syntax system techniques technology thode time tokyo traitement trans tutorial under united university using vector veri verlag volgunin which with word workshop
http://dx.doi.org/10.1007/11669487_39	38	Toward File Consolidation by Document Categorization	actes agglomerative algorithm algorithms analysis application applied approach bela bennett categorization classification classifiers cluster clustering combination conference context data demonstration development document documentary dumais estimators etzioni feasibility finland francois gather hearst hierarchical hoffman horvitz hypothesis icdar implementing indicators information international journal korea lamirel learning logical management mapping master meta models multi orleans osinski patent pedersen poznan probabilistic proceedings processing quality rangoni recognition reexamining references reliability research results retrieval return scatter scientometrics search seoul shehadi sigir structure suisse tampere technology text thesis topographic universitv using voorhees zamir zurich
http://dx.doi.org/10.1007/11669487_37	36	Automatic Keyword Extraction from Historical Do cument Images	analysis approach based cation chengfeng chew chinese classi cognitive computer conf conference data document documents dynamic earance eigenfaces eigenspace endent ewritten extraction face feature features fink free gatos handwriting handwritten historical ieee image images indep indexing international journal kawashima keyword konidaris layout manmatha manuscripts marinai marino matching method methods nagasaki neuroscience ntzios otting pattern pentland perantonis pratikakis proc rath real recognition references retrieval riseman search segmentation soda terasawa text time turk using vision warping without word words world writer
http://dx.doi.org/10.1007/11669487_34	33	HVS Inspired System for Script Identification in Indian Multi-script Do cuments	analyser analysis application automatic based bilingual biological block building burr campb cation cells chan chaudhuri chaudhury cluster coghill communication conf conference containing content cortical dang dataset daugman description detection determination devanagari devi dhanya dial digital dimensional discriminating docuements document documents endent energy engineering english eople ernet ervised extraction farrokhnia feature features first fourier frequency from generalized gratings hindi hochb human identi ieee iisc image images incremental indep indian information inspired intelligence intelligent international intl invariant jain kannada kelly kerns krishnamurthi language languages layout libraries line local london lter lters machine mandal marcelja mathematical model morrone muli multilingual murthy nagabhushana national onse optimized orientation padma page pati pattern phase physiol porat printed proc proceedings processing prototyp ramakrishnan recognition references relation representation resolution resp robson rotation sadhana scheme script segmentation sensing separation seth simple sinha space spatial spitz strategies students system technique telugu templates text texture their theory thomas through trainable transaction uncertainty unsup using visibility vision visual wise wood word words workshop zeevi
http://dx.doi.org/10.1007/11669487_16	15	Handwritten Artefact Identification Method for Table Interpretation with Little Use of Previous Knowledge	addison administracao algorithms analysis aplicada application applications arias artefact asano automatic automatique based bounding boxes brasil business cation catolica cell celulas characters chhabra cient clustering company computer conference couasnon dados data dengel different dmos document documents doermann drawing drawings driven economia editora entities estat evaluating existing exploratory extracao extracting extraction facsimile feature features field finding form forms formulae formulaires fourth from generator generic hadano handwritten haralick hill hirano hori iapr icdar icpr identi ieee images intelligence international interpretation journal kashi kasturi kazmier kieninger kinds laboratoire layout letters liang liao line lines lopresti machine manuscritos marukawa master mathematical mcgraw method methods misra modelisation multi musical neves okada parana pattern paulo performance phillips pizano point pour proceedings processing pucpr reasoning recognition recs recursive references robust rouen sako scores shima shimotsuji shinjo sixth stica straight structure structures sugie system systems tabelas table tableaux tables techniques telephone thesis third thom traitement transactions transmitted tukey types universidade universite using various vision wacv wang watanabe wesley wilfong workshop yoda
http://dx.doi.org/10.1007/11669487_49	48	Robust Chinese Character Recognition by Selection of Binary-Based and Grayscale-Based Classifier	adaptive analysis application automatic based basic blurred bookshelf camera cbdar character characters chinese company complementing degradation degraded discriminant document dual eigenspace estimating features from function generative hagita hardcopy hotta icdar icpr ieee ieice iijima images information ishida japanese kanji katsuyama learning machine march mekada method miyahara model morikita murase nakamura naoi noise ohyama omachi pami parameters pattern patterns printed proc processing publishing recognition references regions resolution robust sawaki selection series seventh shiku smith synthetic takahashi technology template theory trans workshop yanadume
http://dx.doi.org/10.1007/11669487_43	42	The Restoration of Camera Do cuments Through Image Segmentation	agam algorithm algorithms applicable application applications arbitrarily august bound brown cambridge camera canada cation chen clark computer computing confer conference curl curved cylindrical dance dementhon deskewing diego ding distortion document documents doermann dscenes ective ence erations ersp estimation ference flat flattening fourth france fuzzy general graphics http ieee image images interna international july june kaneko kauai kawarago kingston liang mirmhedi miura model morphological nice ninth oints omnipage ontario page pattern persp pilu planar proceedings ration recognition reconstruction recti rectify rectifying references resto restoration retrieval scansoft seales segmentation shap spie stereo structural surface surfaces system text through tional undoing using vancouver vanishing views vision warp with workshop yamashita
http://dx.doi.org/10.1007/11669487_22	21	Bangla/English Script Identification Based on Analysis of Connected Comp onent Profiles	alimi analysis arabic automatic bangla based cation chang character characteristic chaudhuri chaudhury chinese ching classi cluster conf conference content dang data determination devnagari ding distance document documents education elgammal endent engineering english enna environment erentiation europ features font fourth from frontiers ghosh hand handwriting hawaii hochb hybrid identi ieee image images indep indian intelligence intelligent international intl isimade ismail issues john kanoun kelly kerns krishnamurthi language languages large latin learning lecourtier leong line lingual linguini machine multi multilingual multimedia nature navin network neural organizing oriental osium pattern peake printed proceedings processing recognation recognition references research sciences script scripts segmentation self separation seventh sheth singhal sinha sixth size spitz strategies suen symp system techniques templates text thomas trainable trans transactions using wood workshop written xiaozhong zhou
http://dx.doi.org/10.1007/11669487_1	0	Retrieval from Do cument Image Collections	access analysis association balasubramanian basic cation chaudhury classi computer conference cviu cvpr department development devising dictionary digital document doermann duda dynamic english features fellbaum global globalwordnet graphics greenstone harit hart historical http icdar icvgip image images indexing india indian information interactive international jawahar ject john language languages library madhavi manmatha manuscripts matching meshesha million ogden otting pattern proc proceedings processing rath recognition references retrieval searching sethi seventh software sons stork survey tdil techniques technology time transliteration understanding universal using vision vossen vyas warping willey word wordnet york
http://dx.doi.org/10.1007/11669487_46	45	A Metho d for Symb ol Sp otting in Graphical Do cuments	adapted adjancy ahmadi analysis applications approach attributed automatic based belkasim belongie between case collection communication comparative complete computation computer conference contexts cordella description detect distance document documents drawings edinburgh emptoz engineering fast from ghorb graph graphical graphics graphs gray grec handwritten harmonic hybrid ieee image images india inform international invariant invariants jaipur ject jects jose journal learning letters level llados lncs march matching messmer methods moment occluded pami park partially pattern probabilistic puzicha ramel recognition references region relational representation results reversible sanniti shap shen shridar skeletons stable structural study subgraph symb systems tabb techniques theory trans transactions transform understanding using vento vision visual volume well wendling wenyin with zuwala
http://dx.doi.org/10.1007/11669487_31	30	The Effects of OCR Error on the Extraction of Private Information	access accuracy address allen amended analysis andrew applied april august automatic based beckley biing boisen borsack bunescu cartright categorization categorize cation census challenges chilin cient clara classi clustering columbia condit conference coombs correction daniel data david document documents ecca ects edition eech electronic elling engineering entity eric error errors evaluating explorations extraction foia forthcoming freedom freqnames frequently from fundamentals genealogy generations government greenb grishman hall hardcopy hidden high hongyan html http hwang image imaging information input interactive intl isng january jing jose journal juang julie june kazem knowledge languae language lawrence level lopresti lumos marc march markov maryland mccallum media mendenhall miller mining modeling models mooney named names nartker natural noisy novemb occurring ocrsp oratory page pages pereda prentice preparation presence private proc proceedings process processing rabiner ralph raymond razvan realizing recognition recognize redaction references relational retrieval retrieve richard russell santa schwartz scie science sciences sdiut sean shih sigkdd sincich sixth speech spie statistical statistics steve stofsky stone submitted summarizing surnames symp symposium system systems taghva techniques technology terry text thomas tool toolkit understanding university updates usdoj using vegas viewed volume washington weischedel william workshop xvii young
http://dx.doi.org/10.1007/11669487_42	41	A Multiclass Classification Framework for Document Categorization	advances agriculture algorithm allwein analysis annals annual applications approach artificial association bakiri bankert bartlett based bhattacharyya binary boosting cateforization categorization chebyshev classi classification classifiers classifycation cloud codes comparative comparison component computation computational computer conference correcting crammer cristianini dags department design dietterich discriminant ecml eigenvalue engineering environmental error european fast feature features fiers fisher freund ghaoui icml inequalities information intelligence international joachims jordan journal kernel kernels koby kudo lanckriet large learnability learning linguistics lkopf ller machine machines majority many margin marshall mathematical matsumoto meeting methods mika minimax multiclass multivariate national natural nature networks neural nonlinear olkin output pedersen platt press problem problems proceedings processing reducing references relevant report research robust schapire scholkopf schuurmans science selection seventeenthinternational shawe signal singer smola solving spinger springer statistical statistics study support systems taipei taiwan taku taylor technical text theory thirteenth tsch unifying university using vapnik vector verlag weak weston with yang yoav yoram york yuji
http://dx.doi.org/10.1007/11669487_21	20	Language Identification in Degraded and Distorted Do cument Images	analysis annual automatic baird based bergler bloch categorization categorizing cation cavnar chen classes cluster complex computing conference content degraded determination document documents dunning england features from fuzzy germany gram hochberg hybrid icdar identi ieee image images information international into invariant kelly kerns khoury laboratory language line malvern mexico morphological nadal nobile nohl november operations pages pami pattern penn perspective plymouth powalka recognition recti references report research retrieval rotation script shape shapes sherkat spitz state statistical suen sylvania symposium system systems technical templates text texture their thomas tion trenkle university unoriented using vances vegas vision waked whitrow word workshop
http://dx.doi.org/10.1007/11669487_54	53	A Few Steps Towards On-the-Fly Symb ol J Recognition with Relevance Feedback	access accuracy adaptive algorithms analysis appiani applications approach arti automatic automatically based bayesian blostein brodley cambridge canada cation cesarini chen chhabra cial classi colla collection comprehensive computer conference content cordella current databases decision diligenti document documents doermann dosch early ectives examples faloutsos feedback from giacinto gori graphic graphics gupta handwritten hierarchical high historical huang iapr ictai ieee ijcnn image images indexing intelligence international ishikawa jain joint journal kashi kwon lamiroy large learning lecture liao libraries lippman lissier llad lopresti macarthur machine machines manmatha marinai mars mart mehrotra mindreader moments montr multimedia multiple murata nagy nchez nearest networks neural newton notes onada optically optimizing overview pami pattern pawlak persp princeton proceedings processing prototyp query recognition references relevance relevant rendek representation retrieval review revisited roli rothfeder santini scale scanned science search segmenting separation seth shyu similarity sketched smeulders soda space springer steps subramanya supp survey symb systems tabb techniques text through tombre tools towards transactions tree trees understanding using valveny vances vasconcelos vector vento verlag very video vision volume wang wide with words workshop world worring yamada years zernike zhang zhou
http://dx.doi.org/10.1007/11669487_3	2	Contribution to the Discrimination of the Medieval Manuscript Texts: Application in the Palaeography	accueil aiia aiolli alimi analysis approaches april arabic auguest automatic books bouletreau cambridge century ciula classification codicology conference contributions crettez crit cybernetics dang dans derolez digital doctorat document documents duda dynamique early edition eglin exploitation extraction families features fonctionnelle fondsvirtuels from gothic hamadou handwriting haralick hart html http icip identification ieee illcat imprim independent information insa inspections intelligence international invariant item krishnamurthi language lyon machine manuscript medieval medievalist microfilms moalla moesbooks multilingual notizie novembre octobre page palaeographic palaeography pattern press printed proc proceedings prodigi rage recognition references regard representation rotation script searchmsno second segmentation simi sixteenth sona sperduti starita statistical stork structural structuration studies style support system systems text texture their trans tunisie twelfth unifi university using vers villevalenciennes wood zaccagnini
http://dx.doi.org/10.1007/11669487_4	3	Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique	adaptative adaptive algorithm analysis ancient application applied approach april archival august automation background baird bedini belaid binarization bleed brazil canada cancellation capture chang chee chris clustering color comparison component conf conference control december decorrelation degradation degraded detection directional document documents dubois duplex edge edinburgh emptoz extraction florence from frontiers gatos global govindaraju hamza handwriting handwritten hartigan historical iapr icarcv icdar icip icml ieee image images intelligence interference international invited italy july learning lebourgeois leedham leydier lncs machine manuscripts maps means method mochi modelling montreal multistage october organizing others patankar pathak pattern perantonis pratikakis principal proc proceedings processing quality recognition reduction references removal remove restoration restoring robotics salerno scanned scanning scotland segmentation self separating september serialized sharma shen show singapore smigiel state statistics systems talk technique techniques text thresholding through tonazzini transactions using varma vision wang wavelet workshop xiaofeng
http://dx.doi.org/10.1007/11669487_27	26	Ground Truth for Layout Analysis Performance Evaluation∗	algorithms analysis annual antonacopoulos assurance august background bangalore bridson brough canada chen classification competition complexshaped computer conference database description design doceng document edinburgh efficient engine engineering english evaluation flexible france gatos grenoble ground haralick icdar ieee image implementation india international karatzas kashi korea layout lecture lncs lopresti meng methodology montreal notes page performance philips press printed proceeding proceedings proofsetting publishing quality recognition references regions representation repurposing retrieval ritchings science segmentation seoul simske south springer sturgill symposium systems tiles tool truthing understanding unlv using vision white
http://dx.doi.org/10.1007/11669487_12	11	A System for Converting PDF Documents into Structured XML Format∗	abbyy according acrobat adobe aiello analysis association automata breuel buchman cambridgedoc capture cattoni character coianiz company computer conference determining dial doceng document documents doermann dori eatcs edition electronic extracting extraction fifth finereader foolabs footer format from geometric hadjar hansbooks haralick header hewlett hidden hierarchical high http icdar image information ingold international irst jean joint jpedal kuich lalanne languages layout messelodi meunier modena monographs nagy omnipage optical optically optimized order packard page pattern pdftron performance phillips portable publishing reading recognition reference references relations report representation review rigamonti ross salomaa scanned scansoft science sciences scientific semirings seth shin smeulders springer structure structures structuring symposium technical techniques techreports their theoretical thick tool understanding verlag wikipedia world xiaofan xpdf
http://dx.doi.org/10.1007/11669487_26	25	Exploratory Analysis System for Semi-structured Engineering Logs	addresses advanced analysis anatomy angluin annotation annual applications architectural architectures arti atlanta automated baird bangalore barcelona based bell bioinformatics blogpulse bunke california cambridge canada cation census cial city classi cleaning colloquium common comparison complex computation computer computing conference content contextual counterexamples cullen data databases design determination dewitt digital discovery dissertation document documents edinburgh engineering etienne eurise exploratory fielding finding finite forms franke from frontiers glance govindaraju grammatical graphics grec guyon handwriting handwritten hellerstein honavar html http hull hurst iapr icdar icgi icpr ieee image images induction inference information intelligence interactive international iowa irvine italy jaipur july kashi labs language languages layout learning lecture limitations loganalysis logs lopresti machine madhvanath markup mirage nagy naughton network notes opinionated opportunities page pami pattern patterns point potter printed proc proceedings processing project proximity prussak quebec queries querying raman ramanaprasad reader reading recognition references regular relational research roma rossmanith sakakibara sanfeliu schomaker science scienti scotland script semi sets shanmugasundaram site slutzki sobue software spitz springer srihari stochastic strings structural structured styles subspaces survey symposium syntactic system table technology theory tomokiyo tools trans trend tufte twenty univ university usps versatile vldb vuurpijl wandaml washington watanabe weblogs website wheel wilfong workshop world years york zaanen zeugmann zhang
http://dx.doi.org/10.1007/11669487_45	44	The Impact of OCR Accuracy and Feature Transformation on Automatic Text Classification	accuracy adachi advanced america analysis approach august automatic available based bayes bicknes borsack categorization chang character characters cjlin classification classifiers computing condit conference content csie digital digitization doceng document documents effects electronic engineering english errors evaluating evaluation experimental feature findings fourth france frasconi from frontiers fukumoto fumitaka germany glvq grenoble guntzer guowei handwriting handwritten harvad harvard hidden historical hoch html http hybrid icdar ieee imaging impact improvement index information initiative intelligent international iwfhr january jcdl joint jose journal june junker kimura learning libraries library libsvm linking lumos machines making markov measuring methods missrecognized miyake moagrp moaocr models mult multi murata myka nartker november ohta ohyama online page pages presence preserve proceedings project radcliffe recognition reference references report representations research resources retrieval roanoke science search september seventh shelf similarity soda springer support symposium systems taghva takasu team technology tetsushi text transformation umich uncorrected university vector verlag version virginia vullo wakabayashi wataru with workshop young
http://dx.doi.org/10.1007/11669487_15	14	Notes on Contemp orary Table Recognition	abstraction advances analysis assisted automated automatically automating based berlin blostein chhabra cimiano computer conceptual conference cordy data document dori douglas edinburgh editing eighth embley engineering evaluation extracting extraction finland formatting frames from generation germany graphics hiroshima html hurst iapr icdar identifying india inferences information institute interactive international interpretation interpreting investigations iswc jaipur japan journal knowledge korea language layout lecture liddle lonsdale lopresti model modeling models nagy natural notes observations ontologically ontology opinionated ower paradigms pattern pivk plain polytechnic preliminary press proceedings processing quinn recent recognition recognizing references rensselaer research retrieval science sdair semantic seoul south speci springer strategy structure submission sure survey symposium table tables tabular tampere text texts thesis third tijerino towards transformations university unknown using vegas verlag visual volume wang waterloo wide with workshop world zanibbi
http://dx.doi.org/10.1007/11669487_7	6	Automated Scoring of Handwritten Essays Based on Latent Semantic Analysis	addison address addresses algorithm analysis annap annotation applied assessor australia automated automatic baeza baltus bangalore burstein categorization city codes comprehensive computer concepts conference development discourse document dreher education eiro engine erimental essay essays etter fifth foltz fourth frontiers germany grading greenb handwriting handwritten hull icdar ieee image images incorp india information informing integration intelligence intelligent international interpretation into introduction ject journal june keub laham landauer language larkey latent line machine mahadevan markov matching melb model models modern natural neto olis online oration osium ourne page palmer parsing pattern penman phrase plamondon porter postal proceedings processes processing program prose rater reader reading recognition references remote research retrieval science scoring sdiut semantic sentence service shin sigir software srihari state states stripping student survey symp syntax system techniques technology text tomai transactions unconstrained understanding united university using wesley williams with workshop yates year york zhang
http://dx.doi.org/10.1007/11669487_51	50	Performance Evaluation of Text Detection and Tracking in Video	algorithms analysis antani asian assignment automatic black brown collins combinatorial complexity computer conditions conference connell crandall detection document doermann ellis empirical evaluating evaluation extraction fredman garofolo gatica goldgof hall hampapur heaps icpr ieee images improved information international jain ject journal jung kasturi localization manohar mariano marques merkl method methods metrics mihalcik multi munkres narasimhamurthy nascimento network novel odob onacci optimization ortation papadimitriou pattern perez performance pets prentice problems proc proceedings recognition references river rosin saddle senior siam site smith soundarara source steiglitz surveillance survey systems tarjan techniques testb text their tian tools tracking transp under uses varying video vision volume wenyin workshop zhang zhou
http://dx.doi.org/10.1007/11669487_23	22	Script Identification from Indian Do cuments	anal analysis application automatic based burr cation chan chaudhuri chaudhury chengming classi cluster coghill computing conference content dang dependent detection determination digital document documents duda edge edition energy feature features fifth from gabor hart hochberg http human identi ieee iiit image images independent india indian intell international invariant jain john kelly kerns krishnamurthi language languages library line local london mach matlab ming model morrone multi page pattern phase printed proceedings processing prtools qiang recognition references research rotation royal samachar script second segmentation series seventh sheth signal sinha sivaswamy sixth society sons spitz stork strategies templates text texture their thomas toolbox trainable trans using vision wavelet wiley wood york zealand zhitao zhong
http://dx.doi.org/10.1007/11669487_13	12	XCDF: A Canonical and Structured Document Format	access acrobat adobe aidas alam algorithms alto amsterdam analyse analysis anjewierden apparatus arabic archives artificial asilomar aspx automatic ayers bagley bayesian bcltechnologies belgian bensafi bloechle bnaic bollacker brailsford browsing canonical capturing case chao cieslik cifed cikm city classification colloque complex component computers conference configuration content conversion converter creating crem cross data default described diagrams dial discovery diuf diva doceng document documents dutch ecrit edinburgh eighth electronic elements emptoz engineering explicit extracting extraction ferret files florence flynn foolabs format france francophone from futrelle giles glance graphic grenoble grimes guillemot hadjar hardy hidden hitz holland home html http huiti iapr icdar identifying idiap image implications implicit incremental index indexing information ingold intelligence interaction international into italy jersey jferret joint jpedal kabel kansas knowledge korea labeling lalanne lawrence layout learning lebourgeois libraries linking links literature logical lovegrove machine management martigny mattercast meeting mekhaldi method methods milwaukee mlmi modal model multimedia multimodal networks newspaper object online onlinetools ontologies outil page paknad palo parizeau partners patent pdftextstream portable pour princeton products published publishing quoz rahman recognition record recorded reference references related representation results retrieval reusable reuse reverse rigamonti robadey rochelle scientific scotland searching seattle segmentation seoul sequence seventh shap signals sixth snowtide souafi specifications structure structured structures study switzerland symposium systems tech templates thirty thomas through tool tools towards unifr using usings variable well wellner with words workshop xcdf xiaofan xpdf
http://dx.doi.org/10.1007/11669487_14	13	Structural Analysis of Mathematical Formulae with Verification Based on Formula Description Grammar	academic anal analysis anderson applied approach automatic berman blostein chan character chaudhuri chou communication conference contextfree cordy database dimensional directed document documents download emptoz engineering equations erimental eset expression expressions fateman first formula formulae fukuda garain garcia grammar ground hand hierarchical html http icdar icpr ieee image infty inftyproject integrated intell interactive international journal kanahori klerer layout link mach malo mathematical mathematics miao mitchell model network nomura okamoto optical osium parsing pattern press printed proc proceedings processing reader reading recognit recognition recognizing recursive references reinfelds representation saint salicetti spie stochastic structural structure survey suzuki symb symp syntactic syntax system systems tamari tokuyasu toumit trans transformation tree truthed uchida using virtual visual yeung zanibbi
http://dx.doi.org/10.1007/11669487_11	10	Document Logical Structure Analysis Based on Perceptive Cycles	algorithms analysis applied behavioral bela bulletin categorization cattell comp comparison context data determining document electronic elissee exdb extraction factors feature guyon http icdar image imaging introduction journal kanungo learning lecun literature logical machine mnist multivariate nagy numb onents pami psychological rangoni recognition references research retain return rosenfelda rules scree siggraph spie structure survey test twenty variable velicer yann years zwick
http://dx.doi.org/10.1007/11669487_24	23	Finding the Best-Fit Bounding-Boxes	aghajan alamitos algorithm amato analysis angle annual applications atlantic august austin automatic baird based best bounding boxes cambridge cattoni ccitt chen city coianiz component compressed computer computing conference december detection determination digitized document documents edition encoding estimation fiducial finding fisher flannery fujinawa fujisawa geometric gorman govindaraju group grouping haralick higashino hinds hough hybrid ieee image images imaging information intelligence international irst january jersey june kailath kasturi korea layout length level line linear machine march messelodi method modena morphological multi nagy nakano normalization november numerical oblique october pami paris pattern postl press printed proceedings processing recipes recognition recursive references report retrieval review rochester scan scientific second seoul september shima skew slide society spitz spse srihari structures subspace symposium systems technical techniques teukolsky text textual transactions transform transforms twenty understanding university using vegas vetterling vision years yuan
http://dx.doi.org/10.1007/11669487_5	4	Networked Document Imaging with Normalization and Optimization	adaptive analysis applications astola august averaging baird based binary bitmap book breuel bunke canada chang city clustering clutering coding colored compound computer conf contrast core covers degraded demjanenko digital document doermann enhancement enhancing extraction feature file filter filters fontanot format from genova halftoning high hobby hull huttunen image images information inverse italy jaisimha janssen journal jpeg kittler koskinen kronenberg ladner mail matas method model morphological multiresolution multiscale nishida palumbo paper part pattern patterns perroud piece popat proc processing quadratic quebec ramponi recognition references resolution restoration restoring riskin scanned september shin signal sobottka soft space spatial spie sridhar system technology text thouin through video werner with
http://dx.doi.org/10.1007/11669487_47	46	Groove Extraction of Phonographic Records	analog analysis anthology approach archive audio austria bapst based biscainho bounding bradley budapest canny cavaglieri computation computational conf conference contours convention dept depth detection digital diniz disk double edge elder electrical elsevier engineering esquef european eusipco extraction fadeyev fibre field finland freeland gill guidelines haber iasa icassp ieee image impulsive ingold intelligence international isbn johnsen machine mechanically milan noise objects optical pami pattern pentland phonographic photography poliak preservation proc proceedings processing production published reconstruction recorded recording recordings records references retrieval robert sense signal society sound storage stotzer sudan tampere temmer thesis threshold tran trans turntable university using vienna visual volume york