Normalization-Cooperated Gradient Feature Extraction for Handwritten Character Recognition

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 29; no. 8; pp. 1465 - 1469
• Main Author: Liu, Cheng-Lin
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.08.2007; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial intelligence; Character recognition; Computer science; control theory; systems; Error analysis; Exact sciences and technology; Extraction; Feature extraction; Feature recognition; Handwriting recognition; Histograms; Image databases; Image generation; Image recognition; Intelligence; normalization-cooperated gradient feature (NCGF); Pattern analysis; Pattern recognition. Digital image processing. Computational geometry; Recognition; Shape; Spatial databases; Gradient; Histogram; Image processing; normalization- cooperated gradient feature (NCGF); Pattern recognition; Character recognition; Japanese; Confidence; Database; Chinese; Feature extraction; Manuscript character; Pattern analysis; Artificial intelligence; Pattern extraction

The gradient direction histogram feature has shown superior performance in character recognition. To alleviate the effect of stroke direction distortion caused by shape normalization and provide higher recognition accuracies, we propose a new feature extraction approach, called normalization-coopera...