Feature selection for Khmer handwritten text recognition

We propose a model of feature selection for offline handwriting recognition. The targeted area is recognition of Khmer handwritten text. We make use of correlation of features, two dimensional Fourier transformation and Gabor filters. We also pass the reduced data through a distance-based classifier to compare performance of each method. Feature selection is an important step towards improving recognition of handwritten text, especially for alphasyllabary writing systems like Khmer.


Research Team

Computer Science Department, Zaman University, Phnom Penh, Cambodia
UTM Razak School of Engineering and Advanced Technology, University Technology Malaysia, Kuala Lumpur, Malaysia