Research in automatic writer identification has mainly focused on the statistical approach. This has led to the specification and extraction of statistical features such as run-length distributions, slant distribution, entropy, and edge-hinge distribution. The edge-hinge distribution feature outperforms all other statistical features. Edge-hinge distribution is a feature that characterizes the changes in direction of a writing stroke in handwritten text. The edge-hinge distribution is extracted by means of a window that is slid over an edge-detected binary handwriting image. Whenever the central pixel of the window is on, the two edge fragments (i.e. connected sequences of pixels) emerging from this central pixel are considered. Their directions are measured and stored as pairs. A joint probability distribution is obtained from a large sample of such pairs.
We have improved Laurens van der Maaten's excellent package for writer identification available athttp://www.cs.unimaas.nl/l.vandermaaten/Laurens_van_der_Maaten/Software.html. We consider a complete 2D probability distribution that takes into account all possible combinations of angles pairs, outperforming original code. Code has been tested using IAM Handwriting Database, available athttp://www.iam.unibe.ch/~fki/iamDB/.
Index Terms: Matlab, source, code, writer recognition, writer matching, writer verification, online writer identification, edge-hinge, handwriting, handwritten.
 | Figure 1. Handwritten text | ||
A simple and effective source code for Writer Recognition | |||
Posts
0 comments:
Post a Comment