Enhancing electronic documents for character recognition

Abstract

Techniques for desirably translating a document image to an editable electronic textual document are presented. Utilizing respective applications, a document processing management component (DPMC) can convert the document image to a grayscale document image, remove noise from such image, rotate such image to reduce or eliminate any skewing of such image, and perform character recognition on the rotated grayscale document image to extract the textual information from such document to generate an electronic textual document. DPMC can associate a document identifier with the electronic textual document, and such document and document identifier can be stored in a data store. When such document is related to a device or other item, a code or textual string can be associated with the device or item, wherein a communication device can scan the code or textual string. In response, DPMC can retrieve such document, or information relating thereto, from the data store.

What is claimed is: 
     
         1 . A method, comprising:
 in response to determining an amount of skew of textual information presented in an image of a document, rotating, by a system comprising a processor, the image of the document, based on a rotation parameter, to reduce the amount of the skew of the textual information to generate a rotated image of the document, in accordance with a defined document processing criterion relating to skew reduction; and   performing, by the system, character recognition on the rotated image of the document to determine characters of the textual information to generate an electronic textual document comprising the characters of the textual information.   
     
     
         2 . The method of  claim 1 , further comprising:
 receiving, by the system, a captured image of the document, wherein the textual information presented in the captured image of the document is at a first angle with respect to a defined axis, wherein the textual information of the document presented in the image of the document is at the first angle, wherein the rotating comprises rotating the image, based on the rotation parameter, to reduce the amount of the skew of the textual information of the document to generate the rotated image of the document comprising the textual information that is at a second angle that corresponds to the defined axis, and wherein the captured image is captured by scanning or photographing the document.   
     
     
         3 . The method of  claim 1 , wherein the textual information presented in the image of the document is not editable or searchable, and wherein the characters of the textual information of the electronic textual document are editable and searchable. 
     
     
         4 . The method of  claim 1 , further comprising:
 converting, by the system, a color image of the document to a grayscaled image of the document, based on a grayscaling parameter; and   modifying, by the system, the grayscaled image of the document, based on a noise parameter, to sharpen, and remove an item determined to be noise from, the grayscaled image of the document, to generate a modified image of the document, wherein the image of the document is based on the modified image of the document.   
     
     
         5 . The method of  claim 4 , wherein the modifying of the grayscaled image of the document, based on the noise parameter, comprises modifying the grayscaled image of the document, based on the noise parameter, to sharpen, and remove a group of items, comprising the item, determined to be the noise from, the image of the document to generate the modified image of the document, and wherein the group of items determined to be the noise comprises a mark determined to be a non-textual stray mark on the grayscaled image of the document or a first portion of the grayscaled image that is determined to be differently colored than a second portion of the grayscaled image that is determined to be a background area of the document. 
     
     
         6 . The method of  claim 1 , further comprising:
 determining, by the system, a group of parameter threshold values based on a group of parameters, in accordance with defined document processing criteria comprising the defined document processing criterion relating to the skew reduction, wherein the group of parameter threshold values comprises a grayscaling parameter threshold value associated with a grayscaling parameter, a noise parameter threshold value associated with the noise parameter, a rotation parameter threshold value associated with the rotation parameter, or a character recognition parameter threshold value associated with a character recognition parameter; and   setting, by the system, the group of parameter threshold values to facilitate the generating of the electronic textual document comprising the characters of the textual information.   
     
     
         7 . The method of  claim 1 , further comprising:
 performing, by the system, a spell checking operation to correct a misspelling of a word of the textual information of the electronic textual document or a grammar check operation to correct a grammar error in the textual information of the electronic textual document.   
     
     
         8 . The method of  claim 1 , further comprising:
 partitioning, by the system, a version of the image of the document into at least a first portion of the version of the image of the document and a second portion of the version of the image of the document; and   in parallel:
 performing, by the system, a first grayscale operation, a first noise-reduction operation, a first skew-reduction operation, or a first character-recognition operation on the first portion of the version of the image of the document; and 
 performing, by the system, a second grayscale operation, a second noise-reduction operation, a second skew-reduction operation, or a second character-recognition operation on the second portion of the version of the image of the document. 
   
     
     
         9 . The method of  claim 1 , further comprising:
 based on an analysis of a version of the image of the document, identifying, by the system, a first portion of the version of the image of the document that comprises visual content and a second portion of the version of the image of the document that comprises the textual information, wherein the visual content does not include any textual information; and   partitioning, by the system, the version of the image of the document into the first portion of the version of the image of the document and the second portion of the version of the image of the document, wherein the character recognition is performed on the textual information presented in the second portion of the version of the image of the document without character recognition being performed on the first portion of the version of the image of the document that comprises the visual content that does not include any textual information.   
     
     
         10 . The method of  claim 1 , further comprising:
 storing, by the system, a group of electronic textual documents, comprising the electronic textual document, in a data store;   receiving, by the system, a search query comprising search information;   in response to the search query, searching, by the system, the data store, comprising the group of electronic textual documents, based on the search information, to generate a search result responsive to the search query, wherein the search result comprises the electronic textual document, and wherein the searching comprises analyzing respective textual information or respective metadata of or associated with respective electronic textual documents of the group of electronic textual documents based on the search information, wherein the respective textual information comprises the characters of the textual information of the electronic textual document; and   presenting, by the system, the search result.   
     
     
         11 . The method of  claim 10 , further comprising:
 associating, by the system, the respective metadata with the respective electronic textual documents, comprising associating metadata with the electronic textual document, wherein the respective metadata comprises respective codes, respective textual strings, or respective identifier images associated with the respective electronic textual documents,   wherein the receiving of the search query comprises receiving the search query from a first device, in response to the first device scanning or capturing a code, a textual string, or an identifier image associated with a second device, wherein the code, the textual string, or the identifier image corresponds to the metadata associated with the electronic textual document, and wherein the code is a bar code, a quick response code, or a radio frequency identification code.   
     
     
         12 . A system, comprising:
 a processor; and   a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
 in response to determining a deviation of an orientation of textual data presented in an image of a document from a defined angle, adjusting the orientation of the image of the document, based on an orientation parameter, to reduce the deviation of the orientation of the textual data from the defined angle to generate an orientation-adjusted image of the document, in accordance with a defined document processing criterion relating to orientation deviation reduction; and 
 performing character recognition on the orientation-adjusted image of the document to determine characters of the textual data to generate an electronic textual document comprising the characters of the textual data. 
   
     
     
         13 . The system of  claim 12 , wherein the operations further comprise:
 converting a color image of the document to a grayscaled image of the document, based on a grayscaling parameter; and   modifying the grayscaled image of the document, based on a noise parameter, to sharpen, and remove an item determined to be noise from, the grayscaled image of the document, to generate a modified image of the document, wherein the image of the document is based on the modified image of the document.   
     
     
         14 . The system of  claim 13 , wherein a grayscaling application is utilized to facilitate the converting of the color image of the document to the grayscaled image of the document, a noise reduction application is utilized to facilitate the modifying of the grayscaled image of the document, an orientation application is utilized to facilitate the adjusting of the orientation of the image of the document, or a character recognition application is utilized to facilitate the performing of the character recognition on the orientation-adjusted image of the document, and wherein the grayscaling application, the noise reduction application, the orientation application, or the character recognition application is an open source application. 
     
     
         15 . The system of  claim 12 , wherein the operations further comprise:
 determining a group of parameter threshold values based on a group of parameters, in accordance with defined document processing criteria comprising the defined document processing criterion relating to the orientation deviation reduction, and wherein the group of parameter threshold values comprises a grayscaling parameter threshold value associated with a grayscaling parameter, a noise parameter threshold value associated with the noise parameter, an orientation parameter threshold value associated with the orientation parameter, or a character recognition parameter threshold value associated with a character recognition parameter; and   applying the group of parameter threshold values to facilitate the generating of the electronic textual document comprising the characters of the textual data.   
     
     
         16 . The system of  claim 12 , wherein the operations further comprise:
 receiving a captured image of the document, wherein the textual data presented in the captured image of the document is at a first angle with respect to the defined axis, wherein the textual data of the document presented in the image of the document is at the first angle with respect to the defined axis, wherein the adjusting comprises adjusting the orientation of the image of the document, based on the orientation parameter, to reduce the deviation of the orientation of the textual data from the defined angle to generate the orientation-adjusted image of the document that is at a second angle that is substantially same as the defined axis, and wherein the captured image is captured by scanning or photographing the document.   
     
     
         17 . The system of  claim 12 , wherein the operations further comprise:
 storing a group of electronic textual documents, comprising the electronic textual document, in a data store;   receiving a search query comprising search information;   in response to the search query, searching the data store, comprising the group of electronic textual documents, based on the search information, to generate a search result responsive to the search query, wherein the search result comprises the electronic textual document, wherein the searching comprises analyzing respective textual information or respective metadata of respective electronic textual documents of the group of electronic textual documents based on the search information, wherein the textual information presented in the image of the document is not editable or searchable, and wherein the characters of the textual information of the electronic textual document are editable and searchable; and   presenting the search result.   
     
     
         18 . The system of  claim 17 , wherein the operations further comprise:
 associating the respective metadata with the respective electronic textual documents, including associating metadata with the electronic textual document, wherein the respective metadata comprises respective codes, respective textual strings, or respective identifier images, wherein the receiving the search query comprises receiving the search query from a first device, in response to the first device scanning or photographing a code, a textual string, or an identifier image associated with a second device, wherein the code, the textual string, or the identifier image is the metadata associated with the electronic textual document, wherein the code is a bar code, a quick response code, or a radio frequency identification code, and wherein the first device comprises a phone, a scanner, a camera, a computer, an electronic pad, an electronic tablet, electronic eyewear, or electronic bodywear.   
     
     
         19 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
 in response to determining an amount of skew of textual information displayed in an image of a document, rotating the image of the document, based on a rotation parameter, to reduce the amount of the skew of the textual information to generate a rotated image of the document, in accordance with a defined document processing criterion relating to skew reduction; and   translating the rotated image of the document to extract characters of the textual information from the rotated image of the document to generate an electronic textual document comprising the characters of the textual information.   
     
     
         20 . The non-transitory machine-readable medium of  claim 19 , wherein the operations further comprise:
 converting a color image of the document to a grayscaled image of the document, based on a grayscaling parameter; and   altering the grayscaled image of the document, based on a noise parameter, to sharpen, and remove an item determined to be noise from, the grayscaled image of the document, to generate a modified image of the document, wherein the image of the document is based on the modified image of the document.