Image based document access and related systems, methods, and devices

• US 20070226321A1
• Filed: 03/23/2006
• Published: 09/27/2007
• Est. Priority Date: 03/23/2006
• Status: Abandoned Application

• Current Assignee: RR Donnelley & Sons Company
• Original Assignee: RR Donnelley & Sons Company
• Inventors: Bengtson, Michael
• Application Number:
  US11/388,814
• Publication Number:
  US 20070226321A1
• Time in Patent Office: Days
• US Class Current: 709/219
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324
• CPC Class Codes: H04N 1/00307 with a mobile telephone apparatus constructional features of portable telephone sets H04M1/0202; mobile radio systems H04W84/00
• CPC Class Codes: H04N 1/2179 Interfaces allowing access to a plurality of users, e.g. connection to electronic image libraries
• CPC Class Codes: H04N 1/2183 the stored images being distributed among a plurality of different locations, e.g. among a plurality of users
• CPC Class Codes: H04N 1/2191 for simultaneous, independent access by a plurality of different users
• CPC Class Codes: H04N 2201/0082 Image hardcopy reproducer H04N2201/0091 - H04N2201/0094 take precedence
• CPC Class Codes: H04N 2201/0084 Digital still camera
• CPC Class Codes: H04N 2201/0087 Image storage device
• CPC Class Codes: H04N 2201/3226 of identification information or the like, e.g. ID code, index, title, part of an image, reduced-size image
• CPC Class Codes: H04N 2201/3278 Transmission

Abstract

Methods, systems, and devices for providing to a user information associated with an acquired image are described. A method may include acquiring an image from a printed item, and identifying a virtual rendition of the item based on the content of a portion of the acquired image. A method may include selecting a feature in the acquired image, and providing information based on the feature.

Claims

1. A method for providing information associated with an acquired image, the method comprising:

acquiring an image from a printed item, the printed item associated with a virtual rendition of the printed item stored in a database,

identifying the virtual rendition based on at least a portion of the acquired image,

selecting a feature in the acquired image, and

providing the information based on the feature.

2. The method of claim 1 wherein the image includes text.

3. The method of claim 1 wherein the image includes a logo.

4. The method of claim 1 wherein the image includes a picture of an object having a characteristic shape or color.

5. The method of claim 1 wherein the printed item is part of a catalog.

6. The method of claim 1 wherein the virtual rendition comprises a copy of the printed item.

7. The method of claim 1 wherein the virtual rendition comprises a map of elements on the printed item.

8. The method of claim 1 wherein selecting comprises receiving a user indication of the feature.

9. The method of claim 1 wherein selecting comprises placing a crosshair on the feature.

10. The method of claim 1 wherein the provided information includes a description of an object associated with the characteristic feature, an order form for the object, a URL to a page or portion of a page containing a representation of the object, a link to a specification or other information associated with the object, or a combination thereof.

11. The method of claim 1 wherein identifying the virtual rendition includes transmitting the acquired image to the database and matching at least the portion of the acquired image to at least one image attribute of the virtual rendition.

12. The method of claim 11 wherein the acquired image is transmitted to the database via a local area network, a wide-area network, or the Internet, or a combination thereof.

13. The method of claim 11 wherein acquiring the image acquisition device comprises capturing the image using a cell phone camera.

14. A system for providing information associated with an acquired image, the system comprising:

an image acquisition device configured to acquire an image from a printed item, the image acquisition device further configured to allow a user to select a feature in the acquired image,

a database that stores a virtual rendition of the image from the printed item, and

a processor identifying the virtual rendition based on at least a portion of the acquired image.

15. A method of identifying a printed item based on textual information acquired from a printed item, comprising:

identifying in the textual information at least one word,

comparing a significance of the at least one identified word with textual information of documents stored in a database and containing a virtual rendition of the printed item, and

identifying a document that contains the printed item based on the comparison.

16. The method of claim 15, wherein comparing the significance includes determining an organization of the identified words on the printed item.

17. The method of claim 15, wherein comparing the significance includes determining a frequency of the at least one identified word, and comparing the frequency of the at least one identified word in the area of the printed item with a frequency of the at least one identified word in a reference text.

18. The method of claim 15, wherein comparing the significance includes determining a spatial relationship between a plurality of identified words.

19. The method of claim 18, wherein determining the spatial relationship includes determining an order of the plurality of identified words in the area of the printed item.

20. The method of claim 15, wherein determining the spatial relationship includes determining coordinates of the at least one identified word in the area of the printed item.

21. The method of claim 15, wherein identifying the document includes retrieving metadata identifying the document.

22. A system for identifying a printed item based on textual information on the printed item, comprising:

a database storing electronic renditions of printed items,

an image acquisition device acquiring an image of the printed item, and

a processor receiving the acquired image and identifying textual information in the acquired image,

wherein the processor determines an attribute of a word in the identified textual information and compares the determined attribute with an attribute associated with an electronic rendition of a printed item stored in the database, and identifies an electronic rendition of the printed item in the database.

23. A method for controlling user access to an electronic library of printed documents, comprising:

receiving a user registration;

receiving information that identifies a physical document;

determining, based on the received information and the user registration, whether a user has rights to access an electronic document corresponding to the physical document;

if the user has rights, identifying, based on the received information, the electronic document in the electronic library that corresponds to the physical document; and

providing to the user access to a copy of the electronic document.

24. The method of claim 23, wherein the information that identifies a physical document comprises an image of at least a portion of the physical document.

25. The method of claim 24, wherein the image comprises text.

26. The method of claim 23, wherein the information that identifies a physical document comprises a serial number associated with the document, a barcode, a UPC code, an electronic tag, a proof of purchase, a user-supplied answer to a query from the electronic library relating to the physical document, or a combination thereof.

27. The method of claim 24, wherein the information comprises topological attributes of printed objects in the image.

28. The method of claim 25, wherein identifying includes converting text into alphanumeric characters by optical character recognition and comparing the converted text with text in the electronic document.

29. The method of claim 23, comprising after the receiving, issuing to the user a request to provide information that identifies the physical document.

30. The method of claim 23, wherein the physical document is a printed document selected from the group consisting of a book, a magazine, a journal, a newspaper, a manual, a reference, and an article.

31. The method of claim 24, wherein the image is produced by a scanner, a digital camera, or a camera of a mobile communication device, or a combination thereof.

32. The method of claim 23, wherein the electronic copy of the document is searchable.

33. The method of claim 23, further comprising creating a personal electronic library for the user.

34. The method of claim 33, further comprising storing in the personal electronic library a pointer to the authorized copy or an electronic version of another user-owned document.

35. The method of claim 33, further comprising providing the registered user an opportunity for allowing another user to access at least a portion of the personal electronic library of the registered user.

36. A system for controlling user access to an electronic library of printed documents, comprising:

a database storing an electronic copy of a physical document, and

a server receiving registration from a client, the server further receiving from the client information that identifies a physical document;

wherein the server determines, based on the received information and the client registration, whether the client has rights to access an electronic copy of the identified physical document, and if the client has rights provides to the user access to the electronic document.

37. A method of extending information content of an image acquired from a printed item, comprising:

acquiring visual information from an area of the image,

accessing a database having stored therein a virtual rendition of the acquired image area or of the printed item associated with the visual information,

identifying in the database the virtual rendition, based on textual information in visual information, and

displaying the virtual rendition.

38. The method of claim 37, wherein displaying the virtual rendition includes overlaying the virtual rendition on the acquired image.

39. The method of claim 37, wherein the overlaid virtual rendition includes an active link specified in the database.

40. The method of claim 39, wherein activation of the active link causes an image from the database other than the virtual rendition to be displayed.

41. The method of claim 39, wherein activation of the active link causes at least one of a video clip, moving graphics, an audio track, a word definition, a web page, and tool tip to be displayed.

42. The method of claim 37, wherein the visual information is acquired by a line scanner, an electronic camera or camera from a mobile communication device, or a combination thereof.

43. The method of claim 37, wherein acquiring the visual information includes acquiring the visual information from a first area of the image and from a second area of the image, and wherein displaying the virtual rendition includes displaying a first virtual rendition corresponding to the first area and a second virtual rendition corresponding to the second area.

44. The method of claim 43, wherein the visual information from the first and second areas are acquired sequentially, and wherein displaying the first and second virtual renditions is synchronized with the acquisition of the first and second areas.

45. A method of extending information content of an image acquired from a printed item, the method comprising:

acquiring visual information from the item;

using the visual information, identifying in a database an electronic rendition of the image; and

displaying the electronic rendition.

46. A system for extending information content of an image acquired from a printed item, comprising:

an image acquisition device acquiring the image,

a database storing an electronic rendition of the image,

a processor identifying in the database the electronic rendition, based on textual information in the acquired image, and

a display displaying the electronic rendition.

47. A method for providing user access to electronic images of a physical text based on user ownership of the physical text, comprising:

(a) receiving a request for access to one or more electronic images of a physical text in which the request identifies the user submitting the request;

(b) confirming user ownership of the physical text based on the user identity;

(c) consulting one or more access rules that define an amount of content in electronic images of the physical text that can be provided to the user based on the user'"'"'s ownership of the physical text, wherein the defined amount of content for users who own the physical text is greater than an amount of content that may otherwise be provided to users who do not own the physical text; and

(d) providing user access to the one or more electronic images of the physical text in accordance with the one or more access rules.

48. The method of claim 47, further comprising providing access to a user-personalized library of electronic content and automatically including the provided electronic images of the physical text in the user'"'"'s personalized library for later access.

49. The method of claim 48, wherein automatically including the provided electronic images in the user'"'"'s personalized library comprises storing a link in the user'"'"'s personalized library, in which accessing the link provides the user access to the images in a centralized database of images.

50. The method of claim 48, further comprising setting a flag associated with the images in the user'"'"'s personalized library to indicate that user ownership of the physical text has been confirmed.

51. The method of claim 47, wherein confirming user ownership comprises reviewing purchase information pertaining to the user and determining whether the user has purchased the physical text.

52. The method of claim 51, further comprising communicating with a third party regarding purchase information of the user.

53. The method of claim 47, wherein confirming user ownership comprises receiving from the user a receipt evidencing purchase of the physical text.

54. The method of claim 47, wherein confirming user ownership comprises receiving from the user an image of a page from the physical text.

55. The method of claim 47, wherein the one or more access rules permit user access to electronic images of the entire physical text.

56. The method of claim 47, wherein user ownership of the physical text results from the user'"'"'s purchase of an item that the physical text normally accompanies.

57. The method of claim 56, wherein the physical text is an operating manual for the item purchased by the user.

67. The method of claim 48, wherein receiving information indicating a user'"'"'s ownership includes receiving information that the user has purchased as item normally accompanied by the physical text.

58. A method for providing a central database with electronic images of physical texts and enabling access thereto by multiple users, comprising:

(a) acquiring images of pages of physical texts in which identifying information is associated with the images to identify the physical texts from which the images are acquired;

(b) storing the page images and the associated identifying information in the central database;

(c) receiving information indicating a user'"'"'s ownership of a particular physical text; and

(d) enabling the user to access page images of the particular physical text in the central database based on the user'"'"'s ownership of the physical text.

59. The method of claim 58, wherein acquiring images comprises scanning printed pages of a physical text.

60. The method of claim 58, wherein acquiring images comprises receiving page images and associated identifying information from a user upload.

61. The method of claim 60, wherein user-uploaded page images and associated identifying information are automatically included in a personalized library of electronic content maintained at the central database for the user.

62. The method of claim 58, wherein enabling the user to access page images comprises setting a flag associated with the user and the physical work in the central database signifying the user'"'"'s ownership the physical text.

63. The method of claim 58, wherein receiving information indicating a user'"'"'s ownership includes receiving information that the user has purchased the physical text.

64. Apparatus for providing user access to electronic images of a physical text based on user ownership of the physical text, comprising:

(a) means for receiving a request from a user to access one or more electronic images of a physical text, wherein the request identifies the user;

(b) means for confirming user ownership of the physical text based on the user'"'"'s identity;

(c) means for consulting one or more access rules that define an amount of content in electronic images that can be provided to the user based on the user'"'"'s ownership of the physical text, wherein the defined amount of content for users who own the physical text is greater than an amount of content that may otherwise be provided to users who do not own the physical text; and

(d) means for providing user access to the one or more requested electronic images in accordance with the one or more access rules.

65. The apparatus of claim 64, further comprising means for providing access to a user-personalized library of electronic content and automatically including the provided electronic images of the physical text in the user'"'"'s personalized library for later access.

66. The apparatus of claim 64, further comprising means for setting a flag associated with the user and a physical text signifying the user'"'"'s ownership of the physical text.

68. A computer implemented method, comprising:

processing a request from a user to access an electronic version of a physical work stored in a data storage, wherein the data storage has electronic versions of a physical works stored therein, the electronic versions of the physical works comprising images of the physical works that, when displayed to the user, appear the same as the physical works;

determining the user'"'"'s ownership of the physical work; and

based on the user'"'"'s ownership of the physical work, providing the user with access to the electronic version of the physical work.

69. The method of claim 68, wherein determining the user'"'"'s ownership comprises reviewing purchase information pertaining to the user and determining whether the user has purchased the physical work.

70. The method of claim 69, further comprising communicating with a third party regarding purchase information of the user.

71. The method of claim 68, wherein determining the user'"'"'s ownership comprises receiving from the user a receipt evidencing purchase of the physical work.

72. The method of claim 68, wherein determining the user'"'"'s ownership comprises receiving from the user an image of a page from the physical work.

73. The method of claim 68, wherein the user'"'"'s ownership of the physical work entitles the user to access the electronic version of the entire physical work.

74. The method of claim 68, wherein the user'"'"'s ownership of the physical work results from the user'"'"'s purchase of an item that the physical work normally accompanies.

75. A method for electronically searching a user-personalized library of content, comprising:

(a) receiving one or more search terms from a user having an electronically-searchable personalized library of content;

(b) electronically searching the full text of the user'"'"'s personalized library for pages of content that match the search terms to produce search results;

(c) providing the search results to the user;

(d) receiving a search result selection from the user; and

(e) providing to the user an image of a page of content in the user'"'"'s personalized library based on the user'"'"'s search result selection.

76. The method of claim 75, further comprising, prior to receiving one or more search terms from the user, establishing an electronically-searchable library of content that includes a page image database and a text searchable database, which library of content is personalized by the user to consist of content selected by the user.

77. The method of claim 76, in which the library of content is personalized by manual selection of content by the user.

78. The method of claim 76, in which the library of content is automatically personalized based on user selection of content for review or purchase.

79. The method of claim 75, in which the user-personalized library of content is established at the time the user conducts the search.

80. The method of claim 75, in which the user'"'"'s personalized library of content is derived from a publicly-accessible general library of content.

81. The method of claim 75, in which providing the search results to the user includes providing a list of content having pages with text that matches the search terms.

82. The method of claim 81, further comprising ranking the content in the list of content according to a predetermined criterion.

83. The method of claim 75, in which providing to the user an image of a page of content includes retrieving the page image from a database of page images stored in computer memory.

84. The method of claim 75, in which the user'"'"'s personalized library is defined after electronically searching a general library of content using the search terms, the user'"'"'s personalized library being fully contained within the general library of content and defining the scope of search results provided to the user.

85. The method of claim 75, further comprising:

(a) providing location information to the user that identifies the location of the search terms in the page image; and

(b) instructing an electronic application of highlight to the page image by the user in accordance with the location information to highlight the search terms in the page image.

86. The method of claim 85, in which the electronic application of highlight to the page image comprises application of a layer of color on or near the search terms.

87. The method of claim 85, in which the electronic application of highlight to the page image comprises placement of a visual indicator next to the search terms.

88. The method of claim 75, further comprising using one or more access rules to limit an amount of content in one or more page images provided to the user.

89. The method of claim 88, in which the access rules define an aggregate amount of content that can be provided to the user over a time frame.

90. The method of claim 88, in which the access rules define a percentage of content that can be provided to the user over a time frame.

91. The method of claim 88, in which the access rules define the amount of content that can be provided to the user based on content-specific information.

92. The method of claim 88, in which the access rules define the amount of content that can be provided to the user based on user ownership of the content.

93. The method of claim 92, further comprising reviewing purchase records to validate user ownership of the content.

94. The method of claim 88, in which different access rules apply based on the location of the user.

95. The method of claim 88, in which different access rules apply based on the time the content is to be provided to the user.

96. The method of claim 88, in which the access rules define the amount of content that can be provided to the user based on an identification of the user.

97. The method of claim 75, in which a non-text object in the user'"'"'s personalized library is made searchable by including text data related to the object in the electronic search.

98. A method for preparing a user-personalized library of content for electronic searching, comprising:

(a) acquiring a general library of content that includes images and corresponding text of pages of content;

(b) preparing a page image database comprised of the images of pages of content;

(c) preparing a text searchable database comprised of the corresponding text of pages of content; and

(d) receiving from a user a selection of content in the general library to form a user-personalized library of content that the user can electronically search using the text searchable database.

99. The method of claim 98, further comprising defining classes of content and assigning content in the user'"'"'s personalized library to one or more of the classes.

100. The method of claim 99, further comprising limiting a search of the user'"'"'s personalized library to content in a specified class.

101. The method of claim 98, in which the personalized library of content is comprised of content selected by a group of persons constituting a user, the method further comprising enabling persons in the group to conduct searches of the personalized library of content.

102. The method of claim 98, in which the user'"'"'s selection of content in the general library is received based on manual selection by the user.

103. The method of claim 98, in which the user'"'"'s selection of content in the general library is automatically received based on a selection of content by the user for review or purchase.

104. The method of claim 98, further comprising storing the user-personalized library of content in a memory for later retrieval by the user.

105. The method of claim 104, further comprising enabling the user to store and retrieve multiple user-personalized libraries.

106. The method of claim 98, in which the user'"'"'s selection of content in the general library is aided by providing the user with a list of content determined to be related to a subject content.

107. A computer system that provides electronic searching of a user-personalized library of content, comprising a search server in communication with a database server, in which the database server is configured with a general library of content that is accessible to multiple users, the general library including (1) a page image database containing images of pages of content and (2) a text searchable database containing text and identifying information indicating the page images in the page image database that contain the text, the search server being configured with a search engine comprised of computer-implemented instructions that enable the search server to receive one or more search terms from a user having established a personalized library within the general library of content, search the full text of the user'"'"'s personalized library for pages of content that match the search terms, provide the results of the full text search to the user for selection by the user, and provide to the user a page image from the page image database based on the user'"'"'s search result selection.

108. The computer system of claim 107, further comprising an access rights database in the database server with access rules that limit the amount of content in the page image that is provided to the user.

109. The computer system of claim 108, in which the access rules define an aggregate amount of content that can be provided to the user over a time frame.

110. The method of claim 108, in which the access rules define a percentage of content that can be provided to the user over a time frame.

111. The method of claim 108, in which the access rules define the amount of content that can be provided to the user based on content-specific information.

112. The computer system of claim 108, in which the access rules define the amount of content that can be provided to the user based on user ownership of the content.

113. The computer system of claim 112, in which the computer-implemented instructions further enable the search server to validate user ownership of the content by reviewing purchase records pertaining to the user.

114. The computer system of claim 108, in which different access rules apply based on the location of the user.

115. The computer system of claim 108, in which different access rules apply based on the time the content is to be provided to the user.

116. The computer system of claim 108, in which the access rules define the amount of content that can be provided to the user based on an identification of the user.

117. The computer system of claim 107, in which a non-text object in the user'"'"'s personalized library is made searchable by including text data related to the object in the text searchable database.

118. The computer system of claim 107, in which the search server provides the search results in the form of a list of content having pages with text that matches the search terms, which content in the list of content is ranked according to a predetermined criterion.

119. The computer system of claim 107, in which the computer-implemented instructions further enable the search server to provide location information to the user that identifies the location of search terms in the page image and instruct an electronic application of highlight to the page image by the user in accordance with the location information to highlight the search terms in the page image.

120. The computer system of claim 119, in which the electronic application of highlight to the page image comprises application of a layer of color on or near the search terms.

121. The computer system of claim 119, in which the electronic application of highlight to the page image comprises placement of a visual indicator next to the search terms.

122. A method for identifying a printed page based on textual information acquired from the printed page, the method comprising:

selecting from the information first and second words,

comparing the words with text in electronic documents that include a virtual rendition of the page, and

identifying, based on the comparing, a document that includes the printed page.

123. The method of claim 122 further comprising when the first and second words have first and second positions, respectively, determining the first and second positions.

124. The method of claim 123 wherein determining the first and second positions comprises determining an organization of the selected words.

125. The method of claim 123 wherein determining the first and second positions comprises determining an order of the selected words on the page.

126. The method of claim 123 wherein determining the first and second positions comprises determining a spatial relationship between the selected words.

127. The method of claim 126 wherein determining the spatial relationship comprises determining spatial coordinates of the selected words in at least a portion of the printed page.

128. The method of claim 126 wherein determining the spatial relationship comprises determining spatial coordinates of the selected words in the printed page.

129. The method of claim 123 wherein comparing includes comparing the positions of the words with text in the electronic documents.

130. The method of claim 122 wherein selecting comprises assigning to each of the first and second words a respective significance.

131. The method of claim 130 wherein assigning a significance comprises determining a frequency of a word from reference information that includes word frequency information.

132. The method of claim 131 wherein the reference information is a dictionary.

133. The method of claim 130 wherein:

the information is presented using an alphabet of a language;

each letter of the alphabet has an estimated frequency of occurrence; and

the significance assigned to a word depends on the estimated frequency of a letter in the word.

134. The method of claim 130 wherein assigning a significance comprises determining a word-length of at least one of the words.

135. The method of claim 134 wherein only a word having a word-length greater than a predetermined value is significant.

136. The method of claim 134 wherein the word-length of at least one of the words is defined by the number of letters in the word.

137. The method of claim 130 further comprising assigning a significance to a third word wherein the selecting is based on comparing the significances of the first, second, and third words.

138. The method of claim 137 wherein, when the first and second words have first and second positions, respectively, the comparing includes comparing the first and second positions in the electronic documents.

139. The method of claim 122 wherein identifying the document includes receiving metadata corresponding to the document.

140. The method of claim 122 wherein the textual information is acquired from an image of at least a portion of the printed page.

141. A system for identifying a printed page comprising:

a first processing module for acquiring textual information from the printed page,

a second processing module for selecting from the information first and second words,

a third processing module for performing a comparison of the words with text in electronic documents that include a virtual rendition of the page, and

a fourth processing module for identifying, based on the comparison, a document that includes the printed page.

142. The system of claim 141 further comprising a receiver for receiving an image of the printed page, wherein the first processing module is configured to acquire textual information from the image.

143. The system of claim 141 further comprising an image capture device for capturing an image of the printed page, wherein the first processing module is configured to use the image to acquire textual information.

144. A computer program, disposed on a computer readable medium, for identifying a printed page based on textual information acquired from the printed page, the computer program including instructions for causing a processor to:

select from the information first and second words,

compare the words with text in electronic documents that include a virtual rendition of the page, and

identify, based on comparing, a document that includes the printed page.

145. A system for document retrieval and/or indexing comprising:

a component that receives a captured image of at least a portion of a physical document; and

a search component that locates a match to the document, the search is performed over word-level topological properties of generated images, the generated images being images of at least a portion of one or more electronic documents.

146. The system of claim 145, further comprising a component that generates signature(s) corresponding to one or more of the generated images and generates a signature corresponding to the captured image of the document, the signatures identify the word-layout of the generated images, and the search performed via comparing the signatures of the generated images with the signature of the image of the captured document.

147. The system of claim 146, the signatures corresponding to the one or more generated images and the signature of the image of the captured document are generated at least in part upon a location of at least a portion of each word in the generated images and the image of the captured document, respectively.

148. The system of claim 145, further comprising a component that reduces noise in the captured image of the document.

149. The system of claim 145, further comprising a component that generates a grayscale image of the captured image of the document.

150. The system of claim 145, further comprising a caching component that automatically generates an image of an electronic document at a time such electronic document is printed.

151. The system of claim 150, further comprising an artificial intelligence component that infers which printed documents should have associated stored images.

152. The system of claim 145, wherein at least one of the generated images is associated with an entry within a data store, the entry comprising one or more of an image of a page of an electronic document and a signature that identifies the image of the page, the signature based at least in part upon topological properties of words within the image of the page.

153. The system of claim 152, the one or more of the image of the page of the electronic document and the signature that identifies the image of the page associated with a URL that identifies a location of the electronic document.

154. The system of claim 152, the one or more of the image of the page of the electronic document and the signature that identifies the image of the page associated with the electronic document.

155. The system of claim 152, the one or more of the image of the page of the electronic document and the signature that identifies the image of the page associated with OCR of the image of the page.

170. A personal digital assistant comprising the system of claim 145.

156. A method that facilitates indexing and/or retrieval of a document, comprising:

receiving a captured image of at least a portion of a document; and

searching data store(s) for an electronic document corresponding to the captured image, the search performed via comparing topological word properties within the captured image with topological word properties of generated images corresponding to a plurality of electronic documents.

157. The method of claim 156, further comprising reducing noise in the captured image of the document prior to searching the data store(s).

158. The method of claim 157, wherein reducing noise comprises one or more of:

providing a filter that removes markings that have a width greater than a threshold width;

providing a filter that removes markings with a width less than a threshold width;

providing a filter that removes markings with a height greater than a threshold height; and

providing a filter that removes marking with a height less than a threshold height.

159. The method of claim 156, further comprising generating a grayscale image of the captured image of the document prior to searching the data store(s).

160. A system for indexing and/or retrieval of a document, comprising:

means for generating an image of an electronic document when the electronic document is printed;

means for capturing an image of the document after the document has been printed;

means for retrieving the electronic document, the means based at least in part upon comparing location and width of words within the captured image to the location and width of words within the generated image.

161. The system of claim 160, further comprising:

means for generating a signature that includes features that are highly specific to the generated image; and

means for generating a signature corresponding to the captured image, the signature includes features that are highly specific to the captured image.

162. The system of claim 160, further comprising:

means for generating a signature that includes features that are specific to the generated image; and

means for generating a signature corresponding to the captured image, the signature includes features that are specific to the captured image.

163. The system of claim 162, wherein the features include the spatial coordinates of the words.

164. The system of claim 162, wherein the features include the order of the words.

165. The system of claim 161, further comprising means for accounting for error that occurs when capturing the image of the printed document.

166. The system of claim 162, further comprising means for accounting for error that occurs when capturing the image of the printed document.

167. A system that facilitates indexing and/or retrieval of a document, comprising:

a query component that receives an image of a printed document;

a caching component that generates and stores an image corresponding to the image of the document prior to the query component receiving the image of the printed document; and

a comparison component that retrieves the stored image via comparing at least one of location and width of words within the stored image to location and width of words within the image of the printed document.

168. A computer readable medium having computer executable instructions stored thereon to return stored image(s) of an electronic document to a user based at least in part upon topological word properties of captured image(s) corresponding to the printed document.

169. A computer readable medium having a data structure thereon, the data structure comprising:

a component that receives image(s) of at least a portion of a printed document; and

a search component that facilitates retrieval of an electronic document, the electronic document corresponding to the image(s) of the printed document, the retrieval based at least in part upon similar word-level topological properties when comparing the image(s) of the printed document and generated image(s) of the electronic document.