Katunyoo Sankhuangaw. Off-line handwritten Thai character recognition using Ant-miner algorithm . Master's Degree(Technology of Information System Management). Mahidol University. : Mahidol University, 2009-07-29.
Off-line handwritten Thai character recognition using Ant-miner algorithm
Abstract:
Much research into handwritten Thai character recognition has been attempted,
often using comparison of heads of characters, Fuzzy logic and structure trees, etc. This
paper presents a system of handwritten Thai character recognition, based on an Antminer
algorithm (data mining based on Ant colony optimization). Zoning is initially
used to determine each character. Then three distinct features (also called attributes) of
each character in each zone are extracted. The attributes are Head zone, End point, and
Feature code. All attributes are used to construct the classification rules by an Antminer
algorithm in order to classify 113 Thai characters. For this experiment, the Antminer
algorithm was adapted, with a small change to increase the recognition rate.
The result of this experiment is a 97% recognition rate of the training set
(11,300 characters) and a 74.99% recognition rate of unseen data test (22,600
characters).