Online handwriting data acquisition using a video camera

Abstract

A novel method for online data acquisition of cursive handwriting is described. A video camera is used to record the handwriting of a user. From the acquired sequence of images, the movement of the tip of the pen is reconstructed. A prototype of the system has been implemented and tested. In one series of tests, the performance of the system was visually assessed. In another series of experiments, the system was combined with an existing online handwriting recognizer. Good results have been obtained in both sets of experiments.

Automatic Signature Verification: The State of the Art

“…The stylus is also provided with a stress sensor for detecting the pressure applied on the ballpoint and determining the pen-up/pen-down information. There are also alternative approaches that do not require the use of a special stylus, and instead exploit a video camera that is focused on the user while writing on a piece of paper with a normal pen [24], [210], [355]. In this way, handwriting is recovered from the spatiotemporal representation given by the sequence of images.…”

A video-based text and equation editor for LaTeX

“…Moreover, on-line handwriting recognition promises to provide a dynamic means of communication with computers through a pen-like stylus, rather than just a keyboard. This seems to be a more natural way of entering data into computers (Bunke et al, 1999;Wienecke et al, 2001).…”

Recognition of handwritten Arabic alphabet via hand motion tracking

“…However, a number of vision-based handwriting recognition systems for the English language are reported in the literature. For instance in [6,7] a user writes on a piece of paper using a white pen in a controlled lighting environment, a vision system captures the sequences of images and uses the last one to segment out the text. Successive image differences are then applied to the segmented text.…”