Handwriting recognition concerns the ability of a computer to get and interpret comprehensible handwritten input from paper documents, photographs, touch-screens and other devices. Two varieties of hhandwriting recognition are principally distinguished: off-line and on-line. The image of the written text may be estimated “off line” from a piece of paper by optical scanning through OCR (optical character recognition) or by IWR (intelligent word recognition). As contrasted to “off-line handwriting recognition”, under “on line handwriting recognition” a real-time digitizing tablet is used for input, for example, by a pen-based computer screen surface.
Off-line handwriting recognition involves the automatic conversion of text into letter codes, which are usable within computer and text-processing applications. The data obtained by this form is regarded as a static representation of handwriting.
The technology is successfully used by businesses which process lots of handwritten documents, like insurance companies. The quality of recognition can be substantially increased by structuring the document, for example, by using forms.
The off-line handwriting recognition is relatively difficult because people have different handwriting styles. Nevertheless, limiting the range of input can allow recognition to be improved. For example, the ZIP code digits are generally read by computer to sort the incoming mail.
In optical character recognition (OCR) typewritten or printed text (usually captured by a scanner) is mechanically or electronically conversed into machine-editable text. When one scans a paper page into a computer, the process results in just an image file a photo of the page. Then OCR software converts it into a text or word processor file.
Intelligent Word Recognition, or IWR, is the recognition of unconstrained handwritten words. IWR recognizes entire handwritten words or phrases instead of character-by-character, like OCR. IWR technology matches handwritten or printed words to a user-defined dictionary, It leads to significantly reducing character errors encountered in typical character-based recognition engines. IWR also eliminates a large percentage of the manual data entry of handwritten documents that, in the past, could be detected only by a human.
New technology on the market utilizes IWR, OCR, and ICR (intelligent character recognition, i.e. an advanced optical character recognition) together. For example, most ICR software has a self-learning system referred to as a neural network, which automatically updates the recognition database for new handwriting patterns. All these achievements open many possibilities for the processing of documents, either constrained (hand printed or machine printed) or unconstrained (freeform cursive). Moreover, a complete handwriting recognition system, as a rule, also handles formatting, performs correct segmentation into characters and finds the most plausible words.
On-line handwriting recognition involves the automatic conversion of text as it is written on a special digitizer or a personal digital assistant (PDA), which is a mobile device, also known as a palmtop computer. PDA sensor picks up the pen-tip movements as well as pen-up/pen-down switching. The obtained signal is converted into letter codes which are usable within computer and text-processing applications.
The elements of an on-line handwriting recognition interface typically include:
Commercial products incorporating handwriting recognition as a replacement for keyboard input were introduced in the early 1980s. Since then advancements in electronics have allowed the computing power necessary for handwriting recognition to fit into a smaller form factor than tablet computers, and handwriting recognition is often used as an input method for hand-held PDAs. Modern handwriting recognition systems are often based on Time Delayed Neural Network (TDNN) classifier, nicknamed “Inferno”, built at Microsoft.
In recent years, several attempts were made to produce ink pens that include digital elements, such that a person could write on paper, and have the resulting text stored digitally. The best known of these use technology developed by Anoto (see also Discussion – The Digital Pen), which has had some success in the education market. The general success of these products is yet to be determined. Nevertheless, a number of companies develop software for digital pens based on Anoto technology.
According to Mountain View, CA, December 1, 2009 – PhatWare Corporation announces the launch of the latest version of PenOffice (PenOffice 3.3), which works with Microsoft Windows 7 and Microsoft Windows Server 2008 R2. PhatWare Corporation is a leading provider of software products and professional services for mobile and desktop computers. Its new product offers customers enhanced security and innovative user interface features. PenOffice 3.3 is an advanced pen-enabled collaboration and handwriting recognition software for Microsoft Windows-based computers. It can be used with any pointing input device, such as graphic tablet, interactive while board, touch screen monitor, Tablet PC, online digital pen, and even standard computer mouse.
In compliance with Stan Miasnikov, president of PhatWare Corp. “Making application compatible with Microsoft Windows 7 and Microsoft Windows Server 2008 R2 helps us offer our customers compelling benefits, including intuitive user interfaces such as pen-based collaboration, improved security and reliability features, full support for multi-core processing, and sophisticated configuration and management features to improve mobile working.”
Although handwriting recognition is an input form that the public has become accustomed to, it has not achieved widespread use in either desktop computers or laptops. It is still generally accepted that keyboard input is both faster and more reliable. As of 2006many PDAs offer handwriting input, sometimes even accepting natural cursive handwriting, but accuracy is still a problem, and some people still find even a simple on-screen keyboard more efficient.
Subscribe with BlogLines
Pages of the blog