Title :
Feature selection for handwritten Chinese based on machine learning
Author :
Liu, Xu-min ; Li, Kai ; Huang, Hou-Kuan
Author_Institution :
Sch. of Comput. & Inf. Technol., Northern Jiaotong Univ., Beijing, China
Abstract :
In this paper, a new approach to feature selection and recognition of handwritten Chinese characters is proposed, and the algorithm for decision tree is successfully used in feature selection and recognition simultaneously based on the theory of machine learning. It extracts some useful features for matching, reduces the number of extracted features and improves recognition speed greatly.
Keywords :
decision trees; feature extraction; handwritten character recognition; learning (artificial intelligence); Chinese character handwritings; decision tree; feature extraction; feature recognition; feature selection; machine learning; Artificial intelligence; Character recognition; Decision trees; Feature extraction; Handwriting recognition; Machine learning; Mathematics; Pattern matching; Pattern recognition; Software libraries;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1259912
