Handwriting Recognition methods
In text recognition, two mainstream solutions for data input can be identified: offline data input and online data input.
Offline data input
Offline data input is the method used in OCR and ICR applications: it is the result of printed or handwritten text that has been scanned or photographed. It is purely a visual representation of text and does not refer to any dynamic information, such as how the character was written and in which order.
Offline data input is typically used in applications for storing information that has already been acquired, through forms for example. Its main drawback is that scanning or photographing causes "noise" (such as lines or patterns on the paper, extra marks from dust or scratches or a printing process), which detracts from the main image
Online data input
Unlike offline data the way a text is entered is all-important. The ink signal is captured by either:
- A digital pen on patterned paper
- A paper-based capture device
- A pen-sensitive surface such as a touch screen
The information on strokes and trajectories is mathematically represented in an ink signal composed of a sequence of 2D points ordered by time. No matter what the handwriting surface may be, the digital ink is always plotted according to a matrix with x and y axes and a point of origin.
Online data acquisition captures just the information needed, which is trajectory and strokes, to obtain a clear signal. This effective information makes the data easier to process and is suited for more possibilities than offline acquired data.
Texts and images by visionobjects
