{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:39:41Z","timestamp":1777487981610,"version":"3.51.4"},"reference-count":126,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2005,7,1]],"date-time":"2005-07-01T00:00:00Z","timestamp":1120176000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2005,7]]},"DOI":"10.1007\/s10032-004-0138-z","type":"journal-article","created":{"date-parts":[[2005,6,20]],"date-time":"2005-06-20T13:04:56Z","timestamp":1119272696000},"page":"84-104","source":"Crossref","is-referenced-by-count":309,"title":["Camera-based analysis of text and documents: a survey"],"prefix":"10.1007","volume":"7","author":[{"given":"Jian","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Doermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"138_CR1","doi-asserted-by":"crossref","unstructured":"Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans PAMI 24(9):1167-1183","DOI":"10.1109\/TPAMI.2002.1033210"},{"key":"138_CR2","unstructured":"Bayer BE: Color image array, US Patent 3971056"},{"key":"138_CR3","doi-asserted-by":"crossref","unstructured":"Bertucci E, Pilu M, Mirmehdi M (2003) Text selection by structured light marking for hand-held cameras. In: In: Proc. ICDAR, pp 555-559","DOI":"10.1109\/ICDAR.2003.1227726"},{"key":"138_CR4","doi-asserted-by":"crossref","unstructured":"Brown LG (1992) A survey of image registration techniques. ACM Comput Surv 24(4):325-376","DOI":"10.1145\/146370.146374"},{"key":"138_CR5","doi-asserted-by":"crossref","unstructured":"Brown MS, Seales WB (2001) Document restoration using 3D shape: a general deskewing algorithm for arbitrarily warped documents. In: In: Proc. ICCV, pp 367-374","DOI":"10.1109\/ICCV.2001.937649"},{"key":"138_CR6","unstructured":"Cai M, Song J-Q, Lyu MR (2002) A new approach for video text detection. In: In: Proc. ICIP, pp 117-120"},{"key":"138_CR7","unstructured":"Cao H-G, Ding X-Q, Liu C-S (2003) Rectifying the bound document image captured by the camera: a model based approach. In: In: Proc. ICDAR, pp 71-75"},{"key":"138_CR8","doi-asserted-by":"crossref","unstructured":"Chang SL, Chen LS, Chung YC, Chen SW (2004) Automatic license plate recognition. IEEE Trans Intell Transport Syst 5(1):42-53","DOI":"10.1109\/TITS.2004.825086"},{"key":"138_CR9","doi-asserted-by":"crossref","unstructured":"Capel D, Zisserman A (2000) Super-resolution enhancement of text image sequences. In: In: Proc. ICPR, pp 600-605","DOI":"10.1109\/ICPR.2000.905409"},{"key":"138_CR10","unstructured":"Chen D, Shearer K, Bourlard H (2001) Text enhancement with asymmetric filter for video OCR. In: Proc. ICDAR, pp 192-197"},{"key":"138_CR11","unstructured":"Clark P, Mirmehdi M (2000) Location and recovery of text on oriented surfaces. In: Proc. SPIE Document Recognition and Retrieval VII, pp 267-277"},{"key":"138_CR12","doi-asserted-by":"crossref","unstructured":"Clark P, Mirmehdi M (2000) Finding text regions using localised measures. In: Proc. 11th BMVC, pp 675-684","DOI":"10.5244\/C.14.68"},{"key":"138_CR13","doi-asserted-by":"crossref","unstructured":"Clark P, Mirmehdi M (2001) Estimating the orientation and recovery of text planes in a single image. In: Proc. 12th BMVC, pp 421-430","DOI":"10.5244\/C.15.44"},{"key":"138_CR14","unstructured":"Clark P, Mirmehdi M (2002) On the recovery of oriented documents from single images. In: Proc. Advanced Concepts for Intelligent Vision Systems, pp 190-197"},{"key":"138_CR15","doi-asserted-by":"crossref","unstructured":"Clark P, Mirmehdi M (2002) Recognizing text in real scenes. Int J Doc Anal Recog 4(4):243-257","DOI":"10.1007\/s10032-001-0072-2"},{"key":"138_CR16","doi-asserted-by":"crossref","unstructured":"Comelli P, Ferragina P, Granieri MN, Stabile F (1995) Optical recognition of motor vehicle license plates. IEEE Trans Vehicular Technol 44(4):790-799","DOI":"10.1109\/25.467963"},{"key":"138_CR17","doi-asserted-by":"crossref","unstructured":"Crandall D, Antani S, Kasturi R (2003) Extraction of special effects caption text events from digital video. Int J Doc Anal Recog 5(2-3):138-157","DOI":"10.1007\/s10032-002-0091-7"},{"key":"138_CR18","unstructured":"Dance CR (2002) Perspective estimation for document images. In: Proc. SPIE Document Reconition and Retrieval IX, pp 244-254"},{"key":"138_CR19","doi-asserted-by":"crossref","unstructured":"Doermann D (1998) The indexing and retrieval of document images: a survey. Comput Vis Image Understand 70(3):287-298","DOI":"10.1006\/cviu.1998.0692"},{"key":"138_CR20","doi-asserted-by":"crossref","unstructured":"Doermann D, Mihalcik D (2000) Tools and techniques for video performance evaluation. In: Proc. ICPR, pp 167-170","DOI":"10.1109\/ICPR.2000.902888"},{"key":"138_CR21","doi-asserted-by":"crossref","unstructured":"Doncescu A, Bouju A, Quillet V (1997) Former books digital processing: image warping. In: Proc. workshop on document image analysis, pp 5-9","DOI":"10.1109\/DIA.1997.627085"},{"key":"138_CR22","doi-asserted-by":"crossref","unstructured":"Du EY, Chang C-I, Thouin PD (2002) Thresholding video images for text detection. In: Proc. 16th ICPR, 3:919-922","DOI":"10.1109\/ICPR.2002.1048184"},{"key":"138_CR23","doi-asserted-by":"crossref","unstructured":"Elad M, Feuer A (1997) Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images. IEEE Trans Image Process 6(12):1646-1658","DOI":"10.1109\/83.650118"},{"key":"138_CR24","doi-asserted-by":"crossref","unstructured":"Etemad K, Doermann DS, Chellappa R (1997) Multiscale segmentation of unstructured document pages using soft decision integration. IEEE Trans Patt Anal Mach Intell 19(1):92-96","DOI":"10.1109\/34.566817"},{"key":"138_CR25","doi-asserted-by":"crossref","unstructured":"Fekri F, Mersereau RM, Schafer RW (2000) A generalized interpolative vector quantization method for jointly optimal quantization, interpolation, and binarization of text images. IEEE Trans Image Process 9(7):1272-1281","DOI":"10.1109\/83.847839"},{"key":"138_CR26","doi-asserted-by":"crossref","unstructured":"Fink GA, Wienencke M, Sagerer G (2001) Video-based on-line handwriting recognition. In: Proc. ICDAR, pp 226-230","DOI":"10.1109\/ICDAR.2001.953788"},{"key":"138_CR27","unstructured":"Fisher F (2001) Digital camera for document acquisition. In: Proc. symposium on document image understanding technology, pp 75-83"},{"key":"138_CR28","doi-asserted-by":"crossref","unstructured":"Fletcher LA, Kastury R (1988) A robust algorithm for text string separation from mixed text\/graphics images. IEEE Trans Pattern Anal Mach Intell 10(6):910-918","DOI":"10.1109\/34.9112"},{"key":"138_CR29","doi-asserted-by":"crossref","unstructured":"Gargi U, Crandall D, Antani S, Gandhi T, Keener R, Kasturi R (1999) A system for automatic text detection in video. In: Proc. ICDAR, pp 29-32","DOI":"10.1109\/ICDAR.1999.791717"},{"key":"138_CR30","unstructured":"Geist J, Wilkinson RA, Janet S, Grother PJ, Hammond B, Larsen NW, Klear RM, Burges CJC, Creecy R, Hull JJ, Vogl TP, Wilson CL (1994) The second census optical character recognition systems conference. Technical Report NISTIR 5452, June 1994"},{"key":"138_CR31","doi-asserted-by":"crossref","unstructured":"Gotoh T, Toriu T, Sasaki S, Yoshida M (1988) A flexible vision-based algorithm for a book sorting system. IEEE Trans Pattern Anal Mach Intell 10(3):393-399","DOI":"10.1109\/34.3903"},{"key":"138_CR32","doi-asserted-by":"crossref","unstructured":"Haralik RM (1994) Document image understanding: geometric and logical layout. In: Proc. CVPR, pp 385-390","DOI":"10.1109\/CVPR.1994.323855"},{"key":"138_CR33","doi-asserted-by":"crossref","unstructured":"Hasan YMY, Karam LJ (2000) Morphological text extraction from images. IEEE Trans Image Process 9(11):1079-1983","DOI":"10.1109\/83.877220"},{"key":"138_CR34","unstructured":"Hsieh J-W, Yu S-H, Chen Y-S (2002) Morphology-based license plate detection from complex scenes. In: Proc. ICPR, pp 176-179"},{"key":"138_CR35","doi-asserted-by":"crossref","unstructured":"Hua X-S, Chen X-R, Liu W-Y, Zhang H-J (2001) Automatic location of text in video frames. In: Proc. ACM workshop on multimedia: multimedia information retrieval, pp 24-27","DOI":"10.1145\/500933.500941"},{"key":"138_CR36","unstructured":"Hua X-S, Liu W, Zhang H-J (2001) Automatic performance evaluation for video text detection. In: Proc. ICDAR, pp 545-550"},{"key":"138_CR37","doi-asserted-by":"crossref","unstructured":"Irani M, Peleg S (1991) Improving resolution by image registration. CVGIP Graphical Models and Image Processing 53(3):231-239","DOI":"10.1016\/1049-9652(91)90045-L"},{"key":"138_CR38","doi-asserted-by":"crossref","unstructured":"Jain AK, Yu B (1998) Automatic text location in images and video frames. Pattern Recog 31(12):2055-2076","DOI":"10.1016\/S0031-3203(98)00067-3"},{"key":"138_CR39","doi-asserted-by":"crossref","unstructured":"Jiang WWC (1995) Thresholding and enhancement of text images for character recognition. In: Proc. IEEE international conference on acoustics, speech, and signal processing, 4:2395-2398","DOI":"10.1109\/ICASSP.1995.479975"},{"key":"138_CR40","unstructured":"Jung K, Kim KI, Han J-H (2002) Text extraction in real scene images on planar planes. In: Proc. ICPR, pp 469-472"},{"key":"138_CR41","unstructured":"Jung K, Kim KI, Kurata T, Kourogi M, Han J-H (2002) Text scanner with text detection technology on image sequences. In: Proc. 16th ICPR, 3:473-476"},{"key":"138_CR42","doi-asserted-by":"crossref","unstructured":"Kamada H, Fujimoto K (1999) High-speed, high-accuracy binarization method for recognizing text in images of low spatial resolutions. In: Proc. ICDAR, pp 139-142","DOI":"10.1109\/ICDAR.1999.791744"},{"key":"138_CR43","doi-asserted-by":"crossref","unstructured":"Kanungo T, Haralick RM, Phillips I (1993) Global and local document degradation models. In: Proc. ICDAR, pp 730-734","DOI":"10.1109\/ICDAR.1993.395633"},{"key":"138_CR44","doi-asserted-by":"crossref","unstructured":"Kim H-K (1996) Efficient automatic text location method and content-based indexing and structuring of video database. J Vis Commun Image Represent 7(4):336-344","DOI":"10.1006\/jvci.1996.0029"},{"key":"138_CR45","unstructured":"Kim S, Kim D, Ryu Y, Kim G (2002) A robust license-plate extraction method under complex image conditions. In: Proc. ICPR, pp 216-219"},{"key":"138_CR46","doi-asserted-by":"crossref","unstructured":"Kuo S-S, Ranganath MV (1995) Real time image enhancement for both text and color photo images. In: Proc. ICIP, 1:159-162","DOI":"10.1109\/ICIP.1995.529064"},{"key":"138_CR47","doi-asserted-by":"crossref","unstructured":"Kurakake S, Kuwano H, Odaka K (1997) Recognition and visual feature matching of text region in video for conceptual indexing. In: Proc. SPIE Storage and Retrieval for Image and Video Databases V, San Jose, CA, 3022:368-379","DOI":"10.1117\/12.263425"},{"key":"138_CR48","doi-asserted-by":"crossref","unstructured":"Kuwano H, Taniguchi Y, Arai H, Mori M, Kurakake S, Kojima H (2000) Telop-on-demand: video structuring and retrieval based on text recognition. In: Proc. IEEE ICME, New York, pp 759-762","DOI":"10.1109\/ICME.2000.871472"},{"key":"138_CR49","doi-asserted-by":"crossref","unstructured":"Lee C-M, Kankanhalli A (1995) Automatic extraction of characters in complex scene images. Int J Pattern Recog Artif Intell 9(1):67-82","DOI":"10.1142\/S0218001495000043"},{"key":"138_CR50","unstructured":"Li C, Ding X-Q, Wu Y-S (2001) Automatic text location in natural scene images. In: Proc. ICDAR, pp 1069-1073"},{"key":"138_CR51","unstructured":"Li J, Gray RM (1998) Text and picture segmentation by the distribution analysis of wavelet coefficients. In: Proc. ICIP, 3:790-794"},{"key":"138_CR52","doi-asserted-by":"crossref","unstructured":"Li H, Kia O, Doermann D (1999) Text enhancement in digital video. In: Proc. 8th ACM conference on information and knowledge management, pp 122-130","DOI":"10.1117\/12.335804"},{"key":"138_CR53","doi-asserted-by":"crossref","unstructured":"Li H, Doermann D (1999) Text enhancement in digital video using multiple frame integration. In: Proc. ACM international multimedia conference, pp 19-22","DOI":"10.1145\/319463.319466"},{"key":"138_CR54","unstructured":"Li H, Doermann D (2000) A video text detection system based on automated training. In: Proc. ICPR, pp 223-226"},{"key":"138_CR55","doi-asserted-by":"crossref","unstructured":"Li H, Doermann D, Kia O (2000) Automatic text detection and tracking in digital video. IEEE Trans Image Process 9(1):147-167","DOI":"10.1109\/83.817607"},{"key":"138_CR56","doi-asserted-by":"crossref","unstructured":"Lienhart R, Stuber F (1996) Automatic text recognition in digital videos. In: Proc. SPIE Image and Video Processing IV, 2666:180-188","DOI":"10.1117\/12.234741"},{"key":"138_CR57","doi-asserted-by":"crossref","unstructured":"Lienhart R, Effelsberg W (2000) Automatic text segmentation and text recognition for video indexing. ACM Multimedia Syst 8:69-81","DOI":"10.1007\/s005300050006"},{"key":"138_CR58","doi-asserted-by":"crossref","unstructured":"Lienhart R, Wernicle A (2002) Localizing and segmenting text in images and videos. IEEE Trans Circuits Syst Video Technol 12(4):256-268","DOI":"10.1109\/76.999203"},{"key":"138_CR59","doi-asserted-by":"crossref","unstructured":"Lopresti D, Zhou J-Y (2000) Locating and recognizing text in WWW images. Inf Retrieval 2:177-206","DOI":"10.1023\/A:1009954710479"},{"key":"138_CR60","doi-asserted-by":"crossref","unstructured":"Lucas SM, Panaretos A, Sosa L, Tang A, Wong S, Young R (2003) ICDAR 2003 robust reading competition. In: Proc. ICDAR, pp 682-687","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"138_CR61","doi-asserted-by":"crossref","unstructured":"Mao S, Kanungo T (2001) Empirical performance evaluation methodology and its application to page segmentation algorithms. IEEE Trans Pattern Anal Mach Intell 23(3):242-256","DOI":"10.1109\/34.910877"},{"key":"138_CR62","doi-asserted-by":"crossref","unstructured":"Margner VF, Karcher P, Pawlowski A-K (1997) On benchmarking of document analysis systems. In: Proc. ICDAR, pp 331-336","DOI":"10.1109\/ICDAR.1997.619866"},{"key":"138_CR63","doi-asserted-by":"crossref","unstructured":"Mariano VY, Min J, Park J-H, Kasturi R, Mihalcik D, Li H, Doermann D, Drayer T (2002) Performance evaluation of object detection algorithm. In: Proc. ICPR, pp 965-969","DOI":"10.1109\/ICPR.2002.1048198"},{"key":"138_CR64","unstructured":"Myers GK (2003) Metrics for evaluating the performance of video text recognition systems. In: Proc. symposium on document image understanding technology, pp 259-263"},{"key":"138_CR65","doi-asserted-by":"crossref","unstructured":"Messalodi S, Modena CM (1999) Automatic identification and skew estimation of text lines in real scene images. Pattern Recog 32(5):791-810","DOI":"10.1016\/S0031-3203(98)00108-3"},{"key":"138_CR66","doi-asserted-by":"crossref","unstructured":"Miene A, Hermes Th, Ioannidis G (2001) Extracting textual inserts from digital videos. In: Proc. ICDAR, pp 1079-1083","DOI":"10.1109\/ICDAR.2001.953952"},{"key":"138_CR67","unstructured":"Mirmehdi M, Palmer PL, Kittler J (1997) Towards optimal zoom for automatic target recognition. In: Proc. 10th Scandinavian conference on image analysis, 1:447-453"},{"key":"138_CR68","unstructured":"Mirmehdi M, Clark P, Lam J (2001) Extracting low resolution text with an active camera for OCR. In: Proc. IX Spanish symposium on pattern recognition and image processing, pp 43-48"},{"key":"138_CR69","doi-asserted-by":"crossref","unstructured":"Moravec KLC (2002) A grayscale reader for camera images of XEROX dataglyphs. In: Proc. 13th BMVC, pp 698-707","DOI":"10.5244\/C.16.68"},{"key":"138_CR70","doi-asserted-by":"crossref","unstructured":"Munich ME, Perona P (2002) Visual input for pen-based computers. IEEE Trans Pattern Anal Mach Intell 24(3):313-328","DOI":"10.1109\/34.990134"},{"key":"138_CR71","unstructured":"Myers GK, Bolles RC, Luong Q-T, Herson JA (2001) Recognition of text in 3-D scenes. In: Proc. symposium on document image understanding technology, pp 85-99"},{"key":"138_CR72","doi-asserted-by":"crossref","unstructured":"Nagy G (2000) Twenty years of document image analysis research in PAMI. IEEE Trans Pattern Anal Mach Intell 22(1):63-84","DOI":"10.1109\/34.824820"},{"key":"138_CR73","unstructured":"Nartker TA, Rice SV (1994) OCR accuracy: UNLV\u2019s second annual test. INFORM 8(1):40-45"},{"key":"138_CR74","unstructured":"Nartker TA, Rice SV (1994) OCR accuracy: UNLV\u2019s third annual test. INFORM 8(8):30-36"},{"key":"138_CR75","doi-asserted-by":"crossref","unstructured":"Newman W, Dance C, Taylor A, Taylor S, Taylor M, Aldhous T (1999) CamWorks: a video-based tool for efficient capture from paper source documents. In: Proc. international conference on multimedia computing and systems, pp 647-653","DOI":"10.1109\/MMCS.1999.778560"},{"key":"138_CR76","doi-asserted-by":"crossref","unstructured":"Ohya J, Shio A, Akamatsu S (1994) Recognizing characters in scene images. IEEE Trans Pattern Anal Mach Intell 16(2):214-220","DOI":"10.1109\/34.273729"},{"key":"138_CR77","doi-asserted-by":"crossref","unstructured":"Pilu M (2001) Undoing paper curl distortion using applicable surfaces. In: Proc. CVPR, pp 67-72","DOI":"10.1109\/CVPR.2001.990457"},{"key":"138_CR78","doi-asserted-by":"crossref","unstructured":"Pilu M (2001) Extraction of illusory linear clues in perspectively skewed documents. In: Proc. CVPR, pp 363-368","DOI":"10.1109\/CVPR.2001.990498"},{"key":"138_CR79","doi-asserted-by":"crossref","unstructured":"Pilu M, Pollard S (2002) A light-weight text image processing method for handheld embedded cameras. In: Proc. BMVC, pp 547-556","DOI":"10.5244\/C.16.53"},{"key":"138_CR80","doi-asserted-by":"crossref","unstructured":"Pilu M, Isgro F (2002) A fast and reliable planar registration method with applications to document stitching. In: Proc. BMVC, pp 688-697","DOI":"10.5244\/C.16.67"},{"key":"138_CR81","doi-asserted-by":"crossref","unstructured":"Plamondon R, Srihari S (2000) On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63-84","DOI":"10.1109\/34.824821"},{"key":"138_CR82","unstructured":"Rice SV, Jenkins FR, Nartker TA (1995) The fourth annual test of OCR accuracy. Technical Report 95-04, Information Science Research Institute, University of Nevada, Las Vegas"},{"key":"138_CR83","unstructured":"Rice SV, Jenkins FR, Nartker TA (1996) The fifth annual test of OCR accuracy. Technical Report 96-02, Information Science Research Institute, University of Nevada, Las Vegas"},{"key":"138_CR84","unstructured":"Rother C (2000) A new approach for vanishing point detection in architectural environments. In: Proc. 11th BMVC, pp 382-391"},{"key":"138_CR85","doi-asserted-by":"crossref","unstructured":"Sato T, Kanade T, Hughes EK, Smith MA (1998) Video OCR for digital news archive. In: Proc. IEEE workshop on content-based access of image and video database, pp 52-60","DOI":"10.1109\/CAIVD.1998.646033"},{"key":"138_CR86","doi-asserted-by":"crossref","unstructured":"Seeger M, Dance C (2001) Binarising camera images for OCR. In: Proc. ICDAR, pp 54-59","DOI":"10.1109\/ICDAR.2001.953754"},{"key":"138_CR87","unstructured":"Shim J-C, Dorai C, Bolle R (1998) Automatic text extraction from video for content-based annotation and retrieval. In: Proc. ICPR, pp 618-620"},{"key":"138_CR88","doi-asserted-by":"crossref","unstructured":"Smeaton AF, P, Over: (2002) The TREC-2002 video track report. In: Proc. TREC","DOI":"10.6028\/NIST.SP.500-251.video-overview"},{"key":"138_CR89","doi-asserted-by":"crossref","unstructured":"Stafford-Fraser Q, Robinson P (1996) BrightBoard: a video-augmented environment. In: Proc. conference on computer human interface, pp 134-141","DOI":"10.1145\/238386.238457"},{"key":"138_CR90","doi-asserted-by":"crossref","unstructured":"Suen H-M, Wang J-F (1996) Text string extraction from images of colour-printed documents. IEE Proc Vis Image Signal Process 143(4):210-216","DOI":"10.1049\/ip-vis:19960325"},{"key":"138_CR91","doi-asserted-by":"crossref","unstructured":"Taylor MJ, Dance CR (1998) Enhancement of document images from cameras. In: Proc. SPIE: Document Recognition V, pp 230-241","DOI":"10.1117\/12.304635"},{"key":"138_CR92","doi-asserted-by":"crossref","unstructured":"Trier OD, Taxt T (1995) Evaluation of binarization methods for document images. IEEE Trans Pattern Anal Mach Intell 17(3):312-315","DOI":"10.1109\/34.368197"},{"key":"138_CR93","doi-asserted-by":"crossref","unstructured":"Vinciarelli A (2002) A Survey on off-line word recognition. Pattern Recogn 35:1433-1446","DOI":"10.1016\/S0031-3203(01)00129-7"},{"key":"138_CR94","unstructured":"Wang H, Kangas J (2001) Character-like region verification for extracting text in scene images. In: Proc. ICDAR, pp 957-962"},{"key":"138_CR95","doi-asserted-by":"crossref","unstructured":"Watanabe Y, Okada Y, Kim Y-B, Takeda T (1998) Translation camera. In: Proc. 14th ICPR, pp 613-617","DOI":"10.1109\/ICPR.1998.711218"},{"key":"138_CR96","doi-asserted-by":"crossref","unstructured":"Wellner P (1993) Interacting with paper on the DigitalDesk. Commun ACM 36(7):87-96","DOI":"10.1145\/159544.159630"},{"key":"138_CR97","doi-asserted-by":"crossref","unstructured":"Wienecke M, Fink GA, Sagerer G (2003) Towards automatic video-based whiteboard reading. In: Proc. ICDAR, pp 87-91","DOI":"10.1109\/ICDAR.2003.1227633"},{"key":"138_CR98","doi-asserted-by":"crossref","unstructured":"Wilkinson RA, Geist J, Janet S, Grother PJ, Burges CJC, Creecy R, Hammond B, Hull JJ, Larsen NJ, Vogle TP, Wilson CL (1992) The first optical character recognition systems conference. Technical Report NISTIR 4912, August 1992","DOI":"10.6028\/NIST.IR.4912"},{"key":"138_CR99","doi-asserted-by":"crossref","unstructured":"Wolf C, Doermann D (2002) Binarization of low quality text using a markov random field model. In: Proc. ICPR, 3:160-163","DOI":"10.1109\/ICPR.2002.1047819"},{"key":"138_CR100","doi-asserted-by":"crossref","unstructured":"Wolf C, Jolion J-M, Chassaing F (2002) Text localization, enhancement and binarization in multimedia documents. In: Proc. ICPR, 4:1037-1040","DOI":"10.1109\/ICPR.2002.1048482"},{"key":"138_CR101","unstructured":"Wolf C (2003) Text detection in images taken from video sequences for semantic indexing. PhD thesis, Institut National de Sciences Appliqu\u00e9es de Lyon, France"},{"key":"138_CR102","doi-asserted-by":"crossref","unstructured":"Wong EK, Chen M-Y () A robust algorithm for text extraction in color video. In: Proc. IEEE international conference on multimedia and expo, pp 797-800","DOI":"10.1109\/ICME.2000.871481"},{"key":"138_CR103","doi-asserted-by":"crossref","unstructured":"Wu V, Manmatha R, Riseman EM (1997) Finding text in images. In: Proc. 2nd ACM international conference on digital libraries, pp 3-12","DOI":"10.1145\/263690.263766"},{"key":"138_CR104","doi-asserted-by":"crossref","unstructured":"Wu V, Manmatha R, Riseman EM (1999) TextFinder: an automatic system to detect and recognize text in images. IEEE Trans Pattern Anal Mach Intell 21(11):1124-1129","DOI":"10.1109\/34.809116"},{"key":"138_CR105","doi-asserted-by":"crossref","unstructured":"Yang J, Gao J, Zhang Y, Waibel A (2001) Towards automatic sign translation. In: Proc. Human Language Technology","DOI":"10.3115\/1072133.1072223"},{"key":"138_CR106","doi-asserted-by":"crossref","unstructured":"Yang J, Gao J, Zhang Y, Chen X, Waibel A (2001) An automatic sign recognition and translation system. In: Proc. workshop on perceptive user interfaces (PUI\u201901)","DOI":"10.1145\/971478.971490"},{"key":"138_CR107","doi-asserted-by":"crossref","unstructured":"Zandifar A, Duraiswami R, Chahine A, Davis L (2002) A video based interface to textual information for the visually impaired. In: Proc. IEEE 4th international conference on multimodal interfaces, pp 325-330","DOI":"10.1109\/ICMI.2002.1167016"},{"key":"138_CR108","doi-asserted-by":"crossref","unstructured":"Zappala A, Gee A, Taylor M (1999) Document mosaicing. Image Vis Comput 17(8):585-595","DOI":"10.1016\/S0262-8856(98)00178-4"},{"key":"138_CR109","unstructured":"Zhang D, Rajendran RK, Chang S-F (2002) General and domain-specific techniques for detecting and recognizing superimposed text in video. In: Proc. ICIP, 1:593-596"},{"key":"138_CR110","doi-asserted-by":"crossref","unstructured":"Zhang J, Chen X-L, Hanneman A, Yang J, Waibel A (2002) A robust approach for recognition of text embedded in natural scenes. In: Proc. ICPR, pp 204-207","DOI":"10.1109\/ICPR.2002.1047830"},{"key":"138_CR111","doi-asserted-by":"crossref","unstructured":"Zhang Z, Tan CL (2001) Restoration of images scanned from thick bound documents. In: Proc. ICIP, pp 1074-1077","DOI":"10.1109\/ICIP.2001.959235"},{"key":"138_CR112","doi-asserted-by":"crossref","unstructured":"Zhang Z, Tan CL (2003) Correcting document image warping based on regression of curved text lines. In: Proc. ICDAR, pp 589-593","DOI":"10.1109\/ICDAR.2003.1227732"},{"key":"138_CR113","doi-asserted-by":"crossref","unstructured":"Zhang Z, Tan CL, Fan L (2004) Estimation of 3D shape of warped document surface for image restoration. In: Proc. ICPR","DOI":"10.1109\/ICPR.2004.1334172"},{"key":"138_CR114","doi-asserted-by":"crossref","unstructured":"Zhang Z, Tan CL, Fan L (2004) Restoration of curved document images through 3D shape modeling. In: Proc. CVPR, pp 10-15","DOI":"10.1109\/CVPR.2004.1315007"},{"key":"138_CR115","doi-asserted-by":"crossref","unstructured":"Zhong Y, Karu K, Jain AK (1995) Locating text in complex color images. In: Proc. ICDAR, pp 146-149","DOI":"10.1016\/0031-3203(95)00030-4"},{"key":"138_CR116","doi-asserted-by":"crossref","unstructured":"Zhong Y, Zhang H, Jain AK (2000) Automatic caption localization in compressed video. IEEE Trans Pattern Anal Mach Intell 22(4):385-392","DOI":"10.1109\/34.845381"},{"key":"138_CR117","doi-asserted-by":"crossref","unstructured":"Zunino R, Rovetta S (2000) Vector quantization for license-plate location and image coding. IEEE Trans Indust Electr 47(1):159-167","DOI":"10.1109\/41.824138"},{"key":"138_CR118","unstructured":"http:\/\/www.hpl.hp.com\/news\/2002\/apr-jun\/translator.html"},{"key":"138_CR119","unstructured":"http:\/\/www.htsol.com\/Products\/SeeCar.html"},{"key":"138_CR120","unstructured":"http:\/\/fire.relarn.ru\/personal\/andrey\/cobra\/"},{"key":"138_CR121","unstructured":"http:\/\/www.roadtraffic-technology.com\/contractors\/ detection\/perceptics2\/"},{"key":"138_CR122","unstructured":"http:\/\/www.4digitalbooks.com\/products.htm"},{"key":"138_CR123","unstructured":"http:\/\/donswa.home.pipiline.com\/ nytimes.digitizing.html"},{"key":"138_CR124","unstructured":"http:\/\/sourceforge.net\/projects\/viper-toolkit\/"},{"key":"138_CR125","unstructured":"http:\/\/www-nlpir.nist.gov\/projects\/t01v\/"},{"key":"138_CR126","unstructured":"http:\/\/www.casioprojector.com\/yc400\\_overview.html"}],"container-title":["International Journal of Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-004-0138-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-004-0138-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-004-0138-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T20:50:23Z","timestamp":1735764623000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-004-0138-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,7]]},"references-count":126,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2005,7]]}},"alternative-id":["138"],"URL":"https:\/\/doi.org\/10.1007\/s10032-004-0138-z","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,7]]}}}