Summary: Online and Offline Character Recognition Using Alignment to Prototypes
Jonathan Alon, Vassilis Athitsos, and Stan Sclaroff
Computer Science Department
Boston University
Boston, MA 02215
Abstract
Nearest neighbor classifiers are simple to implement, yet
they can model complex non­parametric distributions, and
provide state­of­the­art recognition accuracy in OCR data­
bases. At the same time, they may be too slow for practical
character recognition, especially when they rely on similar­
ity measures that require computationally expensive pair­
wise alignments between characters. This paper proposes
an efficient method for computing an approximate similar­
ity score between two characters based on their exact align­
ment to a small number of prototypes. The proposed method
is applied to both online and offline character recognition,
where similarity is based on widely used and computa­
tionally expensive alignment methods, i.e., Dynamic Time
Warping and the Hungarian method respectively. In both

Source: Athitsos, Vassilis - Department of Computer Science and Engineering, University of Texas at Arlington

Collections: Computer Technologies and Information Sciences