The technology identifiesand automatically dissection information
Optical Character Recognition technology OCR
OCR technology allows converting image format documents (the photo output of scanners, digital cameras, file photo PDF...) into editable documents (text files, word files, etc.), natural language processing and information dissemination. The application of these technologies to the system helps the management, editing of image documents, and document search becomes simple and convenient Superior features of technology
-Automatic identification and extraction of information: Documentation when bringing up the system, users choose document type (dispatch, report, decision, or some other format ...), then the documents are OCR recognition to text and automatically extract the information fields needed
- Extraction and identification by user-defined template form: the user defined regions need dissect, then, saved. When putting documents onto the system to select the model documentation system will then automatically identify and extract information in the area is marked in the form -Identification and direct extraction on document: select the file need to extract information then select the photo and assign the image with specific information field, the system will recognize and automatically inserted into the corresponding information fields.
Handwriting recognition technology ICR
Handwriting recognition technology, ICR (Intelligent Character Recognition) is the translation from handwritten characters into text with characters that a computer can read. ICR technology is a superior development to the printing letter recognition technology (OCR) in level of development. The object identity of ICR technology is the handwriting and the printed word. ICR technology is similar to optical character recognition (OCR) and sometimes used in conjunction with OCR in processing form.
Handwriting recognition technologies are often used in the identification of the information from the document form. On this documents format, some information was filled out by hand in the fixed position (declarations, registration, tests, etc...). Superior features of technology:
-The quality of the data entered into the guarantee: due to information being processed by ICR technology; the errors caused by data entry are minimized; data quality is better than keyboard input. -Shorten the data processing time when compared to traditional news entry -Ability to deliver results soon following each section: With ICR technology, we can divide the check the identifiable figures of different stages, each stage just check some fields. Therefor it created the possibility of providing early results by each group targets by the flexible efficient way
-Reduce warehouse costs, premises contain survey document, shelf/price contains slip and both personnel management, preservation of the survey forms: the scanned survey document is completed has been kept in full image formats. So kept the survey document a long time after the import is not necessarily. Outside of the scanner, people who test data only works with the computer without the next survey document so require less ground, which reduces the stress from the lack of ground work in the census. The survey document are not delivered or the translated between the different stitches should not necessarily organizing the shelves/reviews contain survey document for ease of searching, not held to preserve separate ones. Employees who preserve, arrange, delivered are also reduced a lot.
Optical mark recognition technology OMR
OMR (Optical Mark Recognition): is an optical mark recognition technology on paper in a certain format. This technology can identify special markings that have been marked on paper in pre-determined optical locations.
It allows the control of some types of image scanners, automatic import and digitization of image data in a well-designed form, checking and adjusting the visual selection on the scanned image and outputting to the form text report to easy access to other data processing software. This technology is often used to process data from questionnaires or quizzes
Superior features of the technology:
- Technology can recognize different marking sizes with precision and highly flexible.
- Adjusting the scanned image to compensate for the low quality of the scan
- Used with a variety of writing tools (pencil, ball point pen, remind pen, ...)
- Easily check the answer through the use of delete or mark with the size bigger.
- To avoid misreading images, OMR technology reads based on time markers, so compensate for technical errors of the scanner - Help saving time and money
Adaptive Document Recognition Technology ADRT
ADRT (Adaptive Document Recognition Technology) is a big step in the document identification technology; an important part and only in ABBYY's OCR techonology. ADRT are used to identify the logical structure, the way to layout as well as the different formats of documents many pages, for example: contents, headers, footers, footnotes, references, photo caption, page numbers ... etc.
When identification results are saved as Microsoft Word, the format is seen as the corresponding object in the Word, not merely the text block.
To achieve accuracy in analyzing the logic structure, layout as well as the format of the document is reviewed and processed by the ADRT documents many pages as a general audience rather than as a collection of separate pages. With ADRT technology, the user will be not losed time for the verification results or losed a little.