Document
Imaging
Document Imaging Applications| Research
Document
Imaging
Document Imaging Applications |
Search |
It is a typical application, in which incoming documents are digitized (unless they are initially digital), categorized, and archived in electronic form. The whole process may be set for fully automatic operation without human intervention. The digitization phase can be efficiently performed using scanners and facsimile, which are also relatively inexpensive technology. The archiving phase includes image enhancement, compression, recognition and indexing operations. Using state-of-the-art compression technology, images can be compressed to approximately the same size as those used by file formats of common word processing software, or by PostScript files, see Table below.
File Format File Size (Kbytes) 200 dpi 300 dpi Raster document image 470 > 1000 JBIG compressed image ~ 40 60-80 Word-processing file 30-40 Post Script file ~ 90 ASCII text ~ 4 After the document has been archived, its further processing depends on the application. The document may be converted to word-processing compatible format using Optical Character Recognition (OCR) or be indexed.
Document Enhancement:
After digitization document images are usually enhanced in order to correct deficiencies in the original and digitized documents. The enhancement is aimed to produce more readable version of the image (also known as image restoration) as well as to achieve better compression rates. Enhancement methods include deskew and despeckle operations, line and border removal and filtering, and are useful for archival work where the quality of the original paper documents may have faded. Although the noise level can be enough low to affect the document readability, it can degrade the image enough to cause difficulties in the compression.
Optical Character Recognition and document indexing:
The OCR is the technology aimed to recognize alphanumeric content and formatting styles of given document image is widely used to transform them to format of word-processing system just as they were typed manually. The major benefit of formatted text versus raster image is that text could be easily modified.
OCR is also applicable for document indexing or full-text indexing purposes. Document indexing stands for categorizing the documents by some criteria or field (eg. account number, date, name) and usually requires OCR of predefined text regions. Full-text indexing fulfills the needs of the text search on the actual document content and requires ASCII-only-OCR to convert the document into searchable text.
Existing OCR system are often not guarantee the suitable (proper) output to reconstruct document in exact word-processing form. The reason is the plurality of existing document types and styles and high complexity of OCR algorithms often required the human interaction. These factors together with legal requirements for document preservation make it sufficient to store the digitized documents in compressed image form with limited use of OCR e.g. for indexing purpose.
Human Resource Management System
HRMS system is an example application. It maintains records of employees for internal control purpose as well as to comply with legal requirements. Incoming resumes and recommendation letters are faxed or digitized paper documents should be categorized and distributed into appropriate archives for future examination without human intervention. OCR is performed for extracting the vital information from the documents (resumes) and for the indexing purposes. Original paper document are disposed after digitization is completed.
In an image communication system, such as facsimile, image serves as a communication medium. The document is first digitized using an optical scanning device, and is then compressed and transmitted to the recipient, where it is re-printed or archived in an electronic form. The characteristic feature of this application is that the sender and the recipient are separated by a communication channel, usually a telephone line, which is the bottleneck of the system. The sender may not have sufficient memory to hold the entire image for the time between digitization and transfer. In this case, image scanning, compression and transmission are performed simultaneously.
It has been estimated by International Data Corporation (IDC) that about 8,000,000,000 line drawings exist in the world (in 1998). Only about 13 % of them have been designed and originally stored in digital form. Nevertheless, there are still (and will continue to be) a large number of drawings that are stored as paper documents.
A possible solution for engineering images is to perform a Raster-to-Vector conversion (RVC), where the bitmap image is segmented into vector primitives such as line segments, circles, arcs, etc. and stored with any CAD/CAM format.
Raster-to-vector conversion, however, may be problematic because of the high complexity and insufficient accuracy of conversion systems. The conversion process does not necessarily produce a faithful copy of the original document and loss of data is apparent. Moreover, the process is not often automatic, and requires expensive human interaction. Industrial projects have shown that the costs for such data acquisition exceed the hardware and software costs of operational information systems by a ratio of 100:1. At the same time, complete raster-to-vector conversion is necessary only for parametric modeling and control system applications, which constitute less than 19 % of all applications using engineering documents.
Hybrid editing means using both raster and vector data simultaneously, see Figure below. Information can be exchanged back and forth between the two distinctive formats. Typically, the old (digitized) data is kept in the raster background, and new edits are maintained in vector format. These can be drawn either by hand or extracted from the raster image using semi-automatic raster-to-vector conversion. No resources would be wasted on converting every document into CAD format, and the conversion would be made only when so desired. Nor would there be any loss of data without the control of the user.
In Digital Spatial Libraries (DSL), raster map images are usually generated from a map database for digital publishing on CD-ROM or the Web. The images are formed of several semantic layers, which together form the computer-generated color image, see Figure. An an example we use images from the Topographic Map Series 1:20000 of Finland. The main problem in digital spatial libraries is the huge storage size of the images. For example, a single map sheet of 5000x5000 pixels representing a single map sheet of 10x10 km2 requires 12-25 Mb of memory and this is not the limit.
| Updated: 2005 | © Eugene Ageenko |
