[go: up one dir, main page]

US20110299775A1 - Correcting page curl in scanned books - Google Patents

Correcting page curl in scanned books Download PDF

Info

Publication number
US20110299775A1
US20110299775A1 US12/795,809 US79580910A US2011299775A1 US 20110299775 A1 US20110299775 A1 US 20110299775A1 US 79580910 A US79580910 A US 79580910A US 2011299775 A1 US2011299775 A1 US 2011299775A1
Authority
US
United States
Prior art keywords
word
page
distorted
image
words
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US12/795,809
Other languages
English (en)
Inventor
Vladimir Kluzner
Asaf Tzadok
Eugeniusz Walach
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Priority to US12/795,809 priority Critical patent/US20110299775A1/en
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION reassignment INTERNATIONAL BUSINESS MACHINES CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TZADOK, ASAF, WALACH, EUGENIUSZ, KLUZNER, VLADIMIR
Priority to CA2787159A priority patent/CA2787159C/en
Priority to SG2012075552A priority patent/SG184553A1/en
Priority to EP11725403.7A priority patent/EP2529332B1/en
Priority to CN201180025555.6A priority patent/CN102918548B/zh
Priority to MX2012004058A priority patent/MX2012004058A/es
Priority to PCT/EP2011/059199 priority patent/WO2011154320A1/en
Priority to BR112012031190-5A priority patent/BR112012031190B1/pt
Priority to TW100119855A priority patent/TWI483198B/zh
Publication of US20110299775A1 publication Critical patent/US20110299775A1/en
Priority to IL218433A priority patent/IL218433A/en
Priority to US13/654,624 priority patent/US8687916B2/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/387—Composing, repositioning or otherwise geometrically modifying originals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/14—Image acquisition
    • G06V30/146—Aligning or centring of the image pick-up or image-field
    • G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
    • G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/247—Aligning, centring, orientation detection or correction of the image by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids

Definitions

  • the present invention relates to book digitization. More specifically the present invention relates to correcting digital scan data of a curled page, such as in the vicinity of the book spine, or other distortion of the page.
  • Printed material may include books, as well as newspapers, journals, magazines, pamphlets, and other periodical literature.
  • access to such material, as well as storage space for such material may often be limited.
  • an institution that holds the material such as a library, museum, or private owner, may be reluctant to lend the book to individuals or other institutions.
  • a researcher or other interested individual who wishes to access such material may have to travel to the location of the material. Even so, access may be limited to a limited period of time or to viewing under special conditions.
  • some publications, such as newspapers and popular magazines may deteriorate quickly.
  • storage space at an institution may be limited.
  • each page or pair of pages of the book is scanned to acquire as series of digitized images of the pages.
  • the digitized images may then be saved in a digital format.
  • the digitized images of the book may be made available to the public either in the form of a digital file, or as reprinted in the form of a facsimile edition of the book.
  • the acquired digitized images may be further processed to extract the textual contents of the book.
  • OCR optical character recognition
  • the contents of the book may thus be made available to the public in the form of a text file.
  • a frequent obstacle to cost-effective digitization of an old book is the distortion of page images due to bending or curling of the pages.
  • the book may not open flat. In such a case, the ends of the pages near the binding may curled or bent.
  • a digitized image of a curled end of the page may appear distorted.
  • Text on the curled portion of the page may be tilted with respect to the line of sight of the scanner.
  • the symbols or letters of the text may be distorted such that they may be difficult to read.
  • the distortion of the letters may render the letters unrecognizable by standard OCR technology.
  • a computer implemented method for correcting distortion in an image of a page with a content includes: identifying a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identifying at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generating a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and applying the global transformation function to pixels of the image of the page.
  • a computer program product stored on a non-transitory tangible computer readable storage medium for correcting distortion in an image of a page with a content.
  • the computer program includes code for: identifying a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identifying at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generating a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and applying the global transformation function to pixels of the image of the page.
  • a data processing system including: a processor; a computer usable medium connected to processor, wherein the computer usable medium contains a set of instructions for correcting distortion in an image of a page with a content.
  • the processor is designed to carry out a set of instructions to: identify a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identify at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generate a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and apply the global transformation function to pixels of the image of the page.
  • FIG. 1 shows a schematic cross-sectional image of a system for correction of distorted images of a page of a book, in accordance with embodiments of the present invention.
  • FIG. 2 shows an example of an image of a page scanned with the system shown in FIG. 1 ;
  • FIG. 3 is a flow chart for a method of correcting distorted page images in accordance with embodiments of the present invention.
  • FIG. 4 is a schematic diagram of a distortion matrix.
  • aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.
  • a computer readable storage medium may be any non-transitory, tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof.
  • a computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++or the like and conventional procedural programming languages, such as the “C” programming language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider for example, AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
  • the computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • a correction application in accordance with embodiments of the present invention may enable obtaining a corrected, flattened, image of a curled page using standard, off the shelf, scanning equipment.
  • the correction application includes taking advantage of undistorted scanned images of all or part of the remainder of the book to determine the likely content of at least a portion of the distorted image.
  • the correction application may search scanned pages of the book for typical content that typifies the contents of the book being scanned.
  • the typical content may include words, sequences of words, clusters of words, or symbols that appear repeatedly at various points in the text.
  • the correction application may then identify an item of the image content that appears to be a distortion of one or more items of the typical content.
  • the correction application may identify a section of text as being a distorted version of a word of the typical content.
  • the correction application may, on the basis of the assumption that the identified item of the image content is a distorted version of an item of the typical content, construct a local transformation.
  • the local transformation may describe the distortion of the item of typical content to form the identified item of the image content.
  • the correction application may then construct a global transformation function that describes the transformation of the entire page.
  • the global transformation function may describe a transformation of an image of a bent page to an image of an flat page with equivalent content.
  • the global transformation function may convert distorted content of the image to the assumed true content of the page.
  • the correction application may calculate the best fit of an image of a distorted page to a particular mathematical model.
  • the correction application may apply a least squares fit algorithm to fit the distorted content to a polynomial function.
  • the correction application may fit the distorted content to a model based on a physical model of an open book.
  • the correction application may apply the transformation function to the image of the page.
  • Application of the transformation function to the image of the page may result in an undistorted image of the page.
  • Fig, 1 shows a schematic cross-sectional image of a system for correction of distorted images of a page of a book, in accordance with embodiments of the present invention.
  • System 10 includes scanner 16 and processor 20 .
  • Scanner 16 may include a platen 22 .
  • book 12 may be opened so as to press exposed page 14 against platen 22 .
  • Book 12 includes binding 24 for binding the pages of book 12 together. Binding 24 may constrain the shapes of pages of book 12 when book 12 is open.
  • binding 24 may hold exposed page 14 in book 12 in such a manner that when book 12 is open, proximal section 14 b of page 14 , proximal to binding 24 , is curved.
  • proximal section 14 b may lie at a distance from, and at an oblique angle to, platen 22 .
  • proximal section 14 b may lie at a distance from, and at an oblique angle to, platen 22 .
  • another distal section 14 a of page 14 , distal to binding 24 may lie substantially flat against platen 22 .
  • scanner 10 typically moves scanner head 18 along platen 22 so as to scan various parts of exposed page 14 .
  • scanner head 18 is elongated in a direction perpendicular to its direction of motion, represented by the arrows in the FIG. 1 , and perpendicular to the plane of the Figure.
  • scanner head 18 may image a substantially flat distal section 14 a of exposed page 14 .
  • scanner 18 may image a distorted proximal section 14 b of exposed page 14 .
  • Processor 20 may include programming for controlling the operation of scanner 16 .
  • processor 20 may control movement of scanner head 18 as well as acquisition of scan data by scanner head 18 .
  • Processor 20 may include programming for receiving scan data from scanner 18 , as well as for analyzing, processing, and outputting the scan results.
  • processor 20 may represent a processor built into scanner 16 , a computer communicating with scanner 16 , or a combination of various processors communicating with one another and with scanner 16 .
  • FIG. 2 shows an example of an image of a page scanned with the system shown in FIG. 1 .
  • Page image 26 includes an undistorted image region 26 a , corresponding to an image of distal section 14 a of exposed page 14 ( FIG. 1 ).
  • page image 26 includes a distorted image region 26 b , corresponding to an image of proximal section 14 b of exposed page 14 ( FIG. 1 ).
  • a correction application running on processor 20 may apply techniques known in the art to identify individual image content components, such as individual words, symbols, or clusters of symbols, within the image.
  • an individual image content component will be referred to as a word, regardless of the content of the component.
  • Such techniques are known and applied, for example, in OCR technology.
  • a technique may identify individual words by identifying the spaces separating the words from one another.
  • a correction application may identify undistorted words 28 a and 29 a in undistorted image region 26 a .
  • the correction application may identify distorted words 28 b and 29 b in distorted image region 26 b.
  • FIG. 3 is a flow chart for a method of correcting distorted page images in accordance with embodiments of the present invention.
  • a correction application in accordance with embodiments of the present invention uses as input an appropriate set of page scan images (step 30 ).
  • the input set of page scan images typically includes images of a set of scanned pages with related or approximately uniform content.
  • the input set may include all of the pages of a book.
  • the input set may include a subset of the page images of the book.
  • different sections of a scanned book may be written in different languages, may be printed in different fonts, or may have very different styles (e.g. a mathematical section consisting largely of equations and another section primarily including narration).
  • the correction application input may be limited to one or more sections with approximately uniform content.
  • a user of the application may indicate the images to be used as input.
  • a correction application may include criteria for identifying such sections containing approximately uniform content.
  • the correction application may then generate a list of words present in the input set (step 32 ).
  • the correction may include applying known word segmentation techniques of OCR to segment each image into separate words (e.g. by identifying spaces the spaces that separate the words from one another).
  • the correction application operating on page image 26 may identify words 28 a , 28 b , 29 a , and 29 b (among others).
  • the correction application may analyze the generated list of words so as to correct the page distortion.
  • the correction application may assume that the words are bi-tonal (e.g. uniformly dark text on a light background). Fading or discoloration of the print, darkening or discoloration of the page, or other effects, may hinder defining the edges of the words.
  • the correction algorithm may apply a standard binarization technique to the words.
  • a typical binarization technique may apply one or more fixed or adaptable thresholds to an image in order to assign to each pixel of the image one of two values (e.g. a value indicating black or a value indicating white).
  • the correction application may apply a low pass spatial filter (e.g. a Gaussian 3 ⁇ 3 filter) to eliminate high spatial frequency components, further defining the edges of words or characters.
  • HQ words are words identifiable as being substantially undistorted.
  • application of standard OCR techniques to a word may yield an OCR interpretation of the word with a high degree of confidence.
  • the correction application may then determine that the interpreted word is an HQ word.
  • Such a technique may be limited to a word in a known language or printed with a known font.
  • the correction application may apply standard baseline determination techniques to the word in order to determine the general shape of the word.
  • the correction application may determine that a word with a substantially straight baseline is an HQ word.
  • the correction application operating on page image 26 FIG. 2
  • the correction application operating on page image 26 may identify HQ words 28 a and 29 a (among others).
  • the correction application may identify words 28 b and 29 b as non-HQ words.
  • Analysis may also include creation of synthetic words (step 36 ).
  • the language or font of letters making up the words may be known, or may be extractable from the list of words.
  • the correction application may then create words using the letters of the font.
  • the correction application may use synthetic words for later comparison with distorted words (described below).
  • the correction application may then match similar words and arrange them into groups of equivalent words (step 38 ).
  • the correction application may apply known shape analysis or OCR techniques to HQ words in a straightforward manner in order to identify similar words.
  • the correction application may first apply one or more known registration techniques. Such techniques may include, for example, minimizing one or more distance measurements, or maximizing a correlation between the words.
  • the correction application may apply additional analysis for matching distorted or other non-HQ words with HQ or synthetic words. For example, the correction application may attempt to compare a distorted word with an HQ word. For example, the correction application may compare overall dimensions or other gross features of the distorted word with those of the HQ words in the list of words. As a result of the comparison, the correction application may identify candidate words of which the distorted word may be a distorted version.
  • the correction application may apply various techniques to attempt to match the distorted word to one or more of the candidate words. For example, the correction application may apply a known registration technique as described above in order to maximize alignment of the distorted word with the candidate HQ word. In addition, the correction application may apply one or more (non-rigid) elastic registration techniques, as are known in the art. An elastic registration technique may attempt to modify the shape of the distorted word so as to match the shape of the candidate HQ word.
  • the correction application may apply an optical flow technique such as a motion estimation technique.
  • the correction application In applying a motion estimation technique, the correction application generates a distortion matrix.
  • the distortion matrix describes a deformation that when applied to the HQ word, warps the image so as to obtain the distorted word (or vice versa).
  • a distortion matrix includes a displacement vector assigned to each pixel of the HQ word. Each displacement vector describes a motion (distance and direction) to be applied to each pixel of the HQ word in order to warp the image so as to form the distorted word.
  • the correction application generates a distortion matrix by applying a variational technique such that the generated distortion matrix describes a best correspondence.
  • the correction application selects a distortion matrix such that a criterion quantity describing the degree of correspondence between pixels of the HQ word and the distorted word is maximized or minimized. Failure to obtain a value of the criterion quantity within a predefined range of values may indicate lack of correspondence between the HQ word and the distorted word.
  • FIG. 4 is a schematic diagram of a distortion matrix. Each arrow 52 of distortion matrix 50 represents a displacement vector assigned to a pixel.
  • the correction application may approximate a distortion matrix by a distortion function.
  • the correction application may fit a polynomial or other suitable transformation function to the HQ word so as to distort the HQ word to an image similar to the distorted word.
  • the fit may include two polynomial functions, each describing the distortion in one of two orthogonal directions (e.g. x and y directions).
  • the correction application may fit a polynomial function to a distortion matrix.
  • the correction application may apply a correction based on the distortion matrix or distortion function (such as the inverse of the distortion matrix or distortion function) to the distorted word in order to obtain a corrected image.
  • a correction based on the distortion matrix or distortion function such as the inverse of the distortion matrix or distortion function
  • the correction application may calculate a word-based correction transformation for transforming a distorted word to an undistorted word (step 40 ).
  • the correction application may generate a set of distorted words on each page of the scanned book that correspond to known words of the list of words.
  • Each distorted word may have an associated distortion matrix or distortion function.
  • the correction application operating on page image 26 may identify distorted word 28 b as a distortion of undistorted word 28 b , and distorted word 29 b as a distortion of undistorted word 29 a.
  • the correction application may calculate a local transformation for the section of the page in which the distorted word is found (step 42 ).
  • the correction may generate a local polynomial function describing the local distortion at the distorted word.
  • the function may include two polynomial functions, each describing the distortion in one of two orthogonal directions (e.g. x and y directions).
  • the correction application may use the set of local transformation functions associated with a single page to generate a function describing the global distortion of the page (step 44 ). For example, the correction application may generate a polynomial function that describes the global distortion of the entire page or of a section of the page containing the distortion. The correction application may fit a single polynomial function (in each of the two orthogonal directions) to a set of local polynomial functions. For example, the correction application may apply least squares techniques to generate the best fit.
  • a correction application in accordance with embodiments of the present invention may employ an alternative technique for generating a global distortion function to describe the global distortion of page.
  • a physical model may exist for the shape of the surface of a page of an open book.
  • a general model may exist for a book having parameters with values within a predetermined range. Such parameters may include, for example, overall dimensions of the book, number of pages, page to which book is open, type of binding, paper thickness, and age of the book.
  • the general model may include one or more parameters whose values may be determinable by fitting transformation functions of distorted words on the page to undistorted words.
  • the correction application may then derive a global correction function for a page from its associated global distortion function and apply the global correction function to the page (step 46 ).
  • the global correction function may be in inverse function of the global distortion function.
  • Application of the global correction function may result in a corrected page image.
  • a global correction function may reduce or eliminate the distortion of all distorted words on the page, whether or not associated with a local distortion function.
  • Further processing of the corrected page image may include, for example, saving an image of the corrected page or applying an OCR to the content of the page.
  • Repeated application of the process may increase accuracy. For example, after application of a global distortion correction, application of OCR to the corrected pages may assist in identifying additional words that were missed previously. Adding the additionally identified words to the list of words and repeating the process with the expanded list of words may result in a more accurate distortion correction.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Editing Of Facsimile Originals (AREA)
US12/795,809 2010-06-08 2010-06-08 Correcting page curl in scanned books Abandoned US20110299775A1 (en)

Priority Applications (11)

Application Number Priority Date Filing Date Title
US12/795,809 US20110299775A1 (en) 2010-06-08 2010-06-08 Correcting page curl in scanned books
BR112012031190-5A BR112012031190B1 (pt) 2010-06-08 2011-06-03 Método, equipamento de processamento de dados e suporte físico para correção de distorções de página em livros digitalizados
CN201180025555.6A CN102918548B (zh) 2010-06-08 2011-06-03 校正扫描书籍中的页面卷曲
SG2012075552A SG184553A1 (en) 2010-06-08 2011-06-03 Correcting page curl in scanned books
EP11725403.7A EP2529332B1 (en) 2010-06-08 2011-06-03 Correcting page curl in scanned books
CA2787159A CA2787159C (en) 2010-06-08 2011-06-03 Correcting page curl in scanned books
MX2012004058A MX2012004058A (es) 2010-06-08 2011-06-03 Correccion de ondulacion de pagina en libros registrados por exploracion electronica.
PCT/EP2011/059199 WO2011154320A1 (en) 2010-06-08 2011-06-03 Correcting page curl in scanned books
TW100119855A TWI483198B (zh) 2010-06-08 2011-06-07 用於已掃描過書籍中頁面捲曲之校正
IL218433A IL218433A (en) 2010-06-08 2012-03-01 Fix folded pages in scanned books
US13/654,624 US8687916B2 (en) 2010-06-08 2012-10-18 Correcting page curl in scanned books

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US12/795,809 US20110299775A1 (en) 2010-06-08 2010-06-08 Correcting page curl in scanned books

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/654,624 Continuation US8687916B2 (en) 2010-06-08 2012-10-18 Correcting page curl in scanned books

Publications (1)

Publication Number Publication Date
US20110299775A1 true US20110299775A1 (en) 2011-12-08

Family

ID=44461846

Family Applications (2)

Application Number Title Priority Date Filing Date
US12/795,809 Abandoned US20110299775A1 (en) 2010-06-08 2010-06-08 Correcting page curl in scanned books
US13/654,624 Expired - Fee Related US8687916B2 (en) 2010-06-08 2012-10-18 Correcting page curl in scanned books

Family Applications After (1)

Application Number Title Priority Date Filing Date
US13/654,624 Expired - Fee Related US8687916B2 (en) 2010-06-08 2012-10-18 Correcting page curl in scanned books

Country Status (10)

Country Link
US (2) US20110299775A1 (es)
EP (1) EP2529332B1 (es)
CN (1) CN102918548B (es)
BR (1) BR112012031190B1 (es)
CA (1) CA2787159C (es)
IL (1) IL218433A (es)
MX (1) MX2012004058A (es)
SG (1) SG184553A1 (es)
TW (1) TWI483198B (es)
WO (1) WO2011154320A1 (es)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130039598A1 (en) * 2010-06-08 2013-02-14 International Business Machines Corporation Correcting page curl in scanned books
US20130335757A1 (en) * 2012-06-19 2013-12-19 Leon Williams Simulated embossing and imprinting
US20140226878A1 (en) * 2010-10-12 2014-08-14 International Business Machines Corporation Deconvolution of digital images
US20190394346A1 (en) * 2018-06-25 2019-12-26 Sharp Kabushiki Kaisha Book digitization apparatus and book digitization method
US11145037B1 (en) * 2020-12-31 2021-10-12 VoyagerX, Inc. Book scanning using machine-trained model
US20250166403A1 (en) * 2023-11-17 2025-05-22 Abbyy Development Inc. Processing images of deformed indicia-bearing surfaces

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9881405B2 (en) * 2015-12-23 2018-01-30 Intel Corporation Image processor for producing an image on an irregular surface in a wearable device

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5848197A (en) * 1992-04-28 1998-12-08 Olympus Optical Co., Ltd. Image pickup system for obtaining flat image without distortion
US6873732B2 (en) * 2001-07-09 2005-03-29 Xerox Corporation Method and apparatus for resolving perspective distortion in a document image and for calculating line sums in images
US6954290B1 (en) * 2000-11-09 2005-10-11 International Business Machines Corporation Method and apparatus to correct distortion of document copies
US6996290B2 (en) * 2002-01-31 2006-02-07 Hewlett-Packard Development Company, L.P. Binding curvature correction
US7016081B2 (en) * 2000-12-14 2006-03-21 Ricoh Company, Ltd. Image distortion correction apparatus, distortion correction method therefor, recording media, image scanner and image construction apparatus
US20060140504A1 (en) * 2003-10-24 2006-06-29 Fujitsu Limited Program for correcting image distortion, apparatus for correcting image distortion, method for correcting image distortion, and recording medium storing program for correcting image distortion
US20060193533A1 (en) * 2001-08-27 2006-08-31 Tadashi Araki Method and system for correcting distortions in image data scanned from bound originals
US7170644B2 (en) * 2002-08-30 2007-01-30 Xerox Corporation Method and system for reducing distortion in scanned images
US7417765B2 (en) * 2003-03-19 2008-08-26 Ricoh Company, Ltd. Image processing apparatus and method, image processing program, and storage medium
US20080205759A1 (en) * 2007-02-27 2008-08-28 Ali Zandifar Distortion Correction of a Scanned Image
US20090016606A1 (en) * 2005-06-02 2009-01-15 Lumex As Method, system, digital camera and asic for geometric image transformation based on text line searching
US20090103808A1 (en) * 2007-10-22 2009-04-23 Prasenjit Dey Correction of distortion in captured images
US20110072498A1 (en) * 2009-09-21 2011-03-24 Microsoft Corporation Tearing and conformal transformation human interactive proof

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002074351A (ja) * 2000-08-30 2002-03-15 Minolta Co Ltd 歪み補正装置およびその方法ならびに歪み補正プログラムを記録したコンピュータ読み取り可能な記録媒体
US7602995B2 (en) * 2004-02-10 2009-10-13 Ricoh Company, Ltd. Correcting image distortion caused by scanning
US7508978B1 (en) 2004-09-13 2009-03-24 Google Inc. Detection of grooves in scanned images
EP1742459A1 (en) * 2005-06-13 2007-01-10 SONY DEUTSCHLAND GmbH Method for geometry distorsion correction
US7330604B2 (en) * 2006-03-02 2008-02-12 Compulink Management Center, Inc. Model-based dewarping method and apparatus
JP4946376B2 (ja) * 2006-11-15 2012-06-06 富士通株式会社 線織線射影抽出プログラム、線織線射影抽出装置および線織線射影抽出方法
CN101192269B (zh) * 2006-11-29 2012-05-02 佳能株式会社 从图像估计消失点的方法和装置、计算机程序及其存储介质
US8107766B2 (en) * 2008-04-03 2012-01-31 Abbyy Software Ltd. Method and system for straightening out distorted text-lines on images
TWI354198B (en) * 2008-04-18 2011-12-11 Primax Electronics Ltd Notebook computer and method of capturing document
US8195003B2 (en) 2008-06-30 2012-06-05 International Business Machines Corporation Method of correcting digital image distortion caused by a sheet-fed scanner
CN101587540B (zh) * 2009-04-16 2011-08-03 大连理工大学 一种利用页面文档几何失真检测文档来源的打印机取证方法
US20110299775A1 (en) * 2010-06-08 2011-12-08 International Business Machines Corporation Correcting page curl in scanned books

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5848197A (en) * 1992-04-28 1998-12-08 Olympus Optical Co., Ltd. Image pickup system for obtaining flat image without distortion
US6954290B1 (en) * 2000-11-09 2005-10-11 International Business Machines Corporation Method and apparatus to correct distortion of document copies
US7016081B2 (en) * 2000-12-14 2006-03-21 Ricoh Company, Ltd. Image distortion correction apparatus, distortion correction method therefor, recording media, image scanner and image construction apparatus
US6873732B2 (en) * 2001-07-09 2005-03-29 Xerox Corporation Method and apparatus for resolving perspective distortion in a document image and for calculating line sums in images
US20060193533A1 (en) * 2001-08-27 2006-08-31 Tadashi Araki Method and system for correcting distortions in image data scanned from bound originals
US6996290B2 (en) * 2002-01-31 2006-02-07 Hewlett-Packard Development Company, L.P. Binding curvature correction
US7170644B2 (en) * 2002-08-30 2007-01-30 Xerox Corporation Method and system for reducing distortion in scanned images
US7417765B2 (en) * 2003-03-19 2008-08-26 Ricoh Company, Ltd. Image processing apparatus and method, image processing program, and storage medium
US20060140504A1 (en) * 2003-10-24 2006-06-29 Fujitsu Limited Program for correcting image distortion, apparatus for correcting image distortion, method for correcting image distortion, and recording medium storing program for correcting image distortion
US20090016606A1 (en) * 2005-06-02 2009-01-15 Lumex As Method, system, digital camera and asic for geometric image transformation based on text line searching
US20080205759A1 (en) * 2007-02-27 2008-08-28 Ali Zandifar Distortion Correction of a Scanned Image
US20090103808A1 (en) * 2007-10-22 2009-04-23 Prasenjit Dey Correction of distortion in captured images
US20110072498A1 (en) * 2009-09-21 2011-03-24 Microsoft Corporation Tearing and conformal transformation human interactive proof

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130039598A1 (en) * 2010-06-08 2013-02-14 International Business Machines Corporation Correcting page curl in scanned books
US8687916B2 (en) * 2010-06-08 2014-04-01 International Business Machines Corporation Correcting page curl in scanned books
US20140226878A1 (en) * 2010-10-12 2014-08-14 International Business Machines Corporation Deconvolution of digital images
US9508116B2 (en) * 2010-10-12 2016-11-29 International Business Machines Corporation Deconvolution of digital images
US10140495B2 (en) 2010-10-12 2018-11-27 International Business Machines Corporation Deconvolution of digital images
US10803275B2 (en) 2010-10-12 2020-10-13 International Business Machines Corporation Deconvolution of digital images
US20130335757A1 (en) * 2012-06-19 2013-12-19 Leon Williams Simulated embossing and imprinting
US9227428B2 (en) * 2012-06-19 2016-01-05 Electronics For Imaging, Inc. Simulated embossing and imprinting
US20190394346A1 (en) * 2018-06-25 2019-12-26 Sharp Kabushiki Kaisha Book digitization apparatus and book digitization method
US10742830B2 (en) * 2018-06-25 2020-08-11 Sharp Kabushiki Kaisha Book digitization apparatus and book digitization method
US11145037B1 (en) * 2020-12-31 2021-10-12 VoyagerX, Inc. Book scanning using machine-trained model
US20250166403A1 (en) * 2023-11-17 2025-05-22 Abbyy Development Inc. Processing images of deformed indicia-bearing surfaces

Also Published As

Publication number Publication date
EP2529332B1 (en) 2014-02-26
IL218433A (en) 2017-07-31
BR112012031190A2 (pt) 2016-11-01
SG184553A1 (en) 2012-11-29
WO2011154320A1 (en) 2011-12-15
CA2787159C (en) 2018-07-17
CN102918548A (zh) 2013-02-06
MX2012004058A (es) 2012-05-22
US8687916B2 (en) 2014-04-01
IL218433A0 (en) 2012-04-30
BR112012031190B1 (pt) 2021-10-26
CA2787159A1 (en) 2011-12-15
US20130039598A1 (en) 2013-02-14
TW201214300A (en) 2012-04-01
CN102918548B (zh) 2015-09-09
EP2529332A1 (en) 2012-12-05
TWI483198B (zh) 2015-05-01

Similar Documents

Publication Publication Date Title
US8687916B2 (en) Correcting page curl in scanned books
US11657631B2 (en) Scalable, flexible and robust template-based data extraction pipeline
US11663817B2 (en) Automated signature extraction and verification
US9754187B2 (en) Data capture from images of documents with fixed structure
US9922247B2 (en) Comparing documents using a trusted source
US8494273B2 (en) Adaptive optical character recognition on a document with distorted characters
CN112541494B (zh) 文本识别方法、装置、电子设备及存储介质
US20190304066A1 (en) Synthesis method of chinese printed character images and device thereof
KR20150037374A (ko) 카메라로 촬영한 문서 영상을 스캔 문서 영상으로 변환하기 위한 방법, 장치 및 컴퓨터 판독 가능한 기록 매체
US8542398B2 (en) Method and system to select a trim size
US7903876B2 (en) Distortion correction of a captured image
CN109508712A (zh) 一种基于图像的汉语文字识别方法
US9191554B1 (en) Creating an electronic book using video-based input
RU2673015C1 (ru) Способы и системы оптического распознавания символов серии изображений
JP3989733B2 (ja) フォーム処理でのひずみの訂正
US20130315485A1 (en) Textual information extraction method using multiple images
WO2018003074A1 (ja) 画像処理装置、画像処理方法、および、画像処理プログラム
US10366284B1 (en) Image recognition and parsing
RU2657181C1 (ru) Способ улучшения качества распознавания отдельного кадра
Yang et al. Effective geometric restoration of distorted historical document for large‐scale digitisation
US8760670B2 (en) System and method for print production sheet identification
RU2634192C1 (ru) Ввод данных из серии изображений, соответствующих шаблонному документу
Sutapirat et al. Model-based book dewarping method for content-independent document images
CN115050027A (zh) 结构化信息提取方法、系统、控制装置及可读存储介质
CN121095972A (zh) 文档图像处理方法、装置、存储介质以及电子设备

Legal Events

Date Code Title Description
AS Assignment

Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KLUZNER, VLADIMIR;TZADOK, ASAF;WALACH, EUGENIUSZ;SIGNING DATES FROM 20100531 TO 20100608;REEL/FRAME:024499/0296

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO PAY ISSUE FEE