Model-based character recognition in low resolution

We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to mat...

Full description

Bibliographic Details
Main Authors: Kuhl, Annika, Tan, Tele, Venkatesh, Svetha
Other Authors: NA
Format: Conference Paper
Published: IEEE 2008
Online Access:http://hdl.handle.net/20.500.11937/24471
Description
Summary:We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to match these templates and thereby allowing both character separation and recognition to be achieved at the same time. Thus characters are recognised using their low-resolution appearance only without applying image enhancement methods. Experiments showed that this approach is able to recognise low-resolution alphanumeric text of down to 5 pixels in size.