caa a22 4500 445379529 CHVBK 20180317143013.0 cr unu---uuuuu 170323e20110901xx s 000 0 eng 10.1007/s10032-011-0153-9 doi (NATIONALLICENCE)springer-10.1007/s10032-011-0153-9 Building compact recognizers of handwritten Chinese characters using precision constrained Gaussian model, minimum classification error training and parameter compression [Elektronische Daten] [Yongqiang Wang, Qiang Huo] In our previous work, a so-called precision constrained Gaussian model (PCGM) was proposed for character modeling to design compact recognizers of handwritten Chinese characters. A maximum likelihood training procedure was developed to estimate model parameters from training data. In this paper, we extend the above-mentioned work by using minimum classification error (MCE) training to improve recognition accuracy and using both split vector quantization and scalar quantization techniques to further compress model parameters. Experimental results on a handwritten character recognition task with a vocabulary of 2,965 Kanji characters demonstrate that MCE-trained and compressed PCGM-based classifiers can achieve much higher recognition accuracies than their counterparts based on traditional modified quadratic discriminant function (MQDF) when the footprint of the classifiers has to be made very small, e.g., less than 2MB. Springer-Verlag, 2011 Handwriting recognition nationallicence MQDF nationallicence Covariance modeling nationallicence MCE nationallicence Model compression nationallicence Wang Yongqiang Department of Computer Science, The University of Hong Kong, Hong Kong, China aut Huo Qiang MSRA, 5/F, Beijing Sigma Center, 49 Zhichun Road, Haidian District, 100190, Beijing, People's Republic of China aut International Journal on Document Analysis and Recognition (IJDAR) Springer-Verlag 14/3(2011-09-01), 255-262 1433-2833 14:3<255 2011 14 10032 https://doi.org/10.1007/s10032-011-0153-9 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10032-011-0153-9 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Wang Yongqiang Department of Computer Science, The University of Hong Kong, Hong Kong, China aut NATIONALLICENCE 700 1- Huo Qiang MSRA, 5/F, Beijing Sigma Center, 49 Zhichun Road, Haidian District, 100190, Beijing, People's Republic of China aut NATIONALLICENCE 773 0- International Journal on Document Analysis and Recognition (IJDAR) Springer-Verlag 14/3(2011-09-01), 255-262 1433-2833 14:3<255 2011 14 10032 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer